20240811-10:35:20 argv ./main.py --result_dir=results_culture_ref
20240811-10:35:20 args.log_filename train.log
20240811-10:35:20 args.result_dir results_culture_ref
20240811-10:35:20 args.seed 0
20240811-10:35:20 args.resume False
20240811-10:35:20 args.max_percents_of_test_in_train -1
20240811-10:35:20 args.log_command None
20240811-10:35:20 args.nb_epochs 10000
20240811-10:35:20 args.batch_size 25
20240811-10:35:20 args.physical_batch_size None
20240811-10:35:20 args.inference_batch_size 50
20240811-10:35:20 args.nb_train_samples 40000
20240811-10:35:20 args.nb_test_samples 1000
20240811-10:35:20 args.nb_new_c_quizzes_for_train None
20240811-10:35:20 args.nb_new_c_quizzes_for_test None
20240811-10:35:20 args.learning_rate 0.0005
20240811-10:35:20 args.schedule_free False
20240811-10:35:20 args.model 37M
20240811-10:35:20 args.dim_model 512
20240811-10:35:20 args.dim_keys 64
20240811-10:35:20 args.dim_hidden 2048
20240811-10:35:20 args.nb_heads 8
20240811-10:35:20 args.nb_blocks 12
20240811-10:35:20 args.dropout 0.1
20240811-10:35:20 args.deterministic_synthesis False
20240811-10:35:20 args.problem grids
20240811-10:35:20 args.nb_threads 1
20240811-10:35:20 args.gpus all
20240811-10:35:20 args.nb_gpts 5
20240811-10:35:20 args.max_fail_to_validate 3
20240811-10:35:20 args.accuracy_to_make_c_quizzes 0.95
20240811-10:35:20 args.proba_understands 0.95
20240811-10:35:20 args.proba_not_understands 0.1
20240811-10:35:20 args.temperature_hot 1.5
20240811-10:35:20 args.temperature_cold 1
20240811-10:35:20 args.prompt_noise 0.05
20240811-10:35:20 args.dirty_debug False
20240811-10:35:20 args.test None
20240811-10:35:20 args.grids_world_tasks replace_color,translate,grow,frame
20240811-10:35:20 args.grids_science_tasks None
20240811-10:35:20 args.sky_height 6
20240811-10:35:20 args.sky_width 8
20240811-10:35:20 args.sky_nb_birds 3
20240811-10:35:20 args.sky_nb_iterations 2
20240811-10:35:20 args.sky_speed 3
20240811-10:35:25 main_device cuda:0 gpus ['cuda:0', 'cuda:1']
20240811-10:35:25 vocabulary_size 15
20240811-10:35:25 creating model 0 and its w_quizzes
20240811-10:35:38 creating model 1 and its w_quizzes
20240811-10:35:52 creating model 2 and its w_quizzes
20240811-10:36:05 creating model 3 and its w_quizzes
20240811-10:36:19 creating model 4 and its w_quizzes
20240811-10:36:32 nb_parameters 37819407 (37M)
20240811-10:36:32 nb_new_c_quizzes_for_train 400 nb_new_c_quizzes_for_test 10
20240811-10:36:32 wrote state.pth
20240811-10:36:32 --- epoch 0 ----------------------------------------
20240811-10:36:32 current_test_accuracies 0.0000 0.0000 0.0000 0.0000 0.0000
20240811-10:36:32 training model 0
20240811-10:36:32 training model 1
20240811-10:40:11 train_perplexity 0 model 0 2.3087705298027323
20240811-10:40:13 test_perplexity 0 model 0 1.2843638783152984
20240811-10:40:16 train_perplexity 0 model 1 2.5046343870069867
20240811-10:40:18 test_perplexity 0 model 1 1.2879079236894055
20240811-10:40:57 test_accuracy 0 model 0 val 2 / 805
20240811-10:41:01 test_accuracy 0 model 1 val 0 / 815
20240811-10:41:03 wrote gpt_000.pth
20240811-10:41:03 wrote gpt_001.pth
20240811-10:41:16 wrote non_validated_0000_00.png
20240811-10:41:29 wrote non_validated_0000_01.png
20240811-10:41:29 wrote state.pth
20240811-10:41:29 --- epoch 1 ----------------------------------------
20240811-10:41:29 current_test_accuracies 0.0025 0.0000 0.0000 0.0000 0.0000
20240811-10:41:29 training model 1
20240811-10:41:29 training model 2
20240811-10:45:12 train_perplexity 1 model 2 2.3457939902242955
20240811-10:45:13 train_perplexity 1 model 1 1.2761775666635615
20240811-10:45:15 test_perplexity 1 model 2 1.2851834450868667
20240811-10:45:16 test_perplexity 1 model 1 1.228296480415938
20240811-10:46:00 test_accuracy 1 model 2 val 1 / 806
20240811-10:46:02 test_accuracy 1 model 1 val 55 / 814
20240811-10:46:04 wrote gpt_001.pth
20240811-10:46:04 wrote gpt_002.pth
20240811-10:46:17 wrote non_validated_0001_01.png
20240811-10:46:30 wrote non_validated_0001_02.png
20240811-10:46:30 wrote state.pth
20240811-10:46:30 --- epoch 2 ----------------------------------------
20240811-10:46:30 current_test_accuracies 0.0025 0.0676 0.0012 0.0000 0.0000
20240811-10:46:30 training model 3
20240811-10:46:30 training model 4
20240811-10:50:08 train_perplexity 2 model 3 2.338539361536506
20240811-10:50:10 test_perplexity 2 model 3 1.285489983736501
20240811-10:50:13 train_perplexity 2 model 4 2.4034913067205057
20240811-10:50:15 test_perplexity 2 model 4 1.2829012466035703
20240811-10:50:53 test_accuracy 2 model 3 val 3 / 823
20240811-10:50:58 test_accuracy 2 model 4 val 1 / 790
20240811-10:51:00 wrote gpt_003.pth
20240811-10:51:00 wrote gpt_004.pth
20240811-10:51:13 wrote non_validated_0002_03.png
20240811-10:51:26 wrote non_validated_0002_04.png
20240811-10:51:26 wrote state.pth
20240811-10:51:26 --- epoch 3 ----------------------------------------
20240811-10:51:26 current_test_accuracies 0.0025 0.0676 0.0012 0.0036 0.0013
20240811-10:51:26 training model 2
20240811-10:51:26 training model 4
20240811-10:55:11 train_perplexity 3 model 2 1.262974126377856
20240811-10:55:11 train_perplexity 3 model 4 1.269895694343616
20240811-10:55:14 test_perplexity 3 model 2 1.2215494624541219
20240811-10:55:15 test_perplexity 3 model 4 1.229550511202709
20240811-10:56:00 test_accuracy 3 model 2 val 83 / 811
20240811-10:56:02 test_accuracy 3 model 4 val 64 / 781
20240811-10:56:04 wrote gpt_002.pth
20240811-10:56:04 wrote gpt_004.pth
20240811-10:56:17 wrote non_validated_0003_02.png
20240811-10:56:30 wrote non_validated_0003_04.png
20240811-10:56:30 wrote state.pth
20240811-10:56:30 --- epoch 4 ----------------------------------------
20240811-10:56:30 current_test_accuracies 0.0025 0.0676 0.1023 0.0036 0.0819
20240811-10:56:30 training model 0
20240811-10:56:30 training model 3
20240811-11:00:15 train_perplexity 4 model 0 1.2651047489243097
20240811-11:00:16 train_perplexity 4 model 3 1.2657696416033979
20240811-11:00:17 test_perplexity 4 model 0 1.2213414027845697
20240811-11:00:19 test_perplexity 4 model 3 1.2202921211861195
20240811-11:01:03 test_accuracy 4 model 0 val 74 / 813
20240811-11:01:06 test_accuracy 4 model 3 val 70 / 791
20240811-11:01:08 wrote gpt_000.pth
20240811-11:01:09 wrote gpt_003.pth
20240811-11:01:21 wrote non_validated_0004_00.png
20240811-11:01:34 wrote non_validated_0004_03.png
20240811-11:01:34 wrote state.pth
20240811-11:01:34 --- epoch 5 ----------------------------------------
20240811-11:01:34 current_test_accuracies 0.0910 0.0676 0.1023 0.0885 0.0819
20240811-11:01:34 training model 1
20240811-11:01:34 training model 4
20240811-11:05:18 train_perplexity 5 model 1 1.221281139261766
20240811-11:05:20 train_perplexity 5 model 4 1.2181520376656207
20240811-11:05:20 test_perplexity 5 model 1 1.1906410491640023
20240811-11:05:22 test_perplexity 5 model 4 1.1908579636226744
20240811-11:06:06 test_accuracy 5 model 1 val 219 / 801
20240811-11:06:08 test_accuracy 5 model 4 val 192 / 799
20240811-11:06:10 wrote gpt_001.pth
20240811-11:06:11 wrote gpt_004.pth
20240811-11:06:23 wrote non_validated_0005_01.png
20240811-11:06:36 wrote non_validated_0005_04.png
20240811-11:06:36 wrote state.pth
20240811-11:06:36 --- epoch 6 ----------------------------------------
20240811-11:06:36 current_test_accuracies 0.0910 0.2734 0.1023 0.0885 0.2403
20240811-11:06:36 training model 3
20240811-11:06:36 training model 0
20240811-11:10:20 train_perplexity 6 model 3 1.2119915052801344
20240811-11:10:22 train_perplexity 6 model 0 1.2133138735669051
20240811-11:10:22 test_perplexity 6 model 3 1.1830671290763388
20240811-11:10:24 test_perplexity 6 model 0 1.1941543212650367
20240811-11:11:09 test_accuracy 6 model 0 val 202 / 817
20240811-11:11:12 test_accuracy 6 model 3 val 246 / 794
20240811-11:11:14 wrote gpt_003.pth
20240811-11:11:14 wrote gpt_000.pth
20240811-11:11:27 wrote non_validated_0006_03.png
20240811-11:11:40 wrote non_validated_0006_00.png
20240811-11:11:40 wrote state.pth
20240811-11:11:40 --- epoch 7 ----------------------------------------
20240811-11:11:40 current_test_accuracies 0.2472 0.2734 0.1023 0.3098 0.2403
20240811-11:11:40 training model 2
20240811-11:11:40 training model 4
20240811-11:15:23 train_perplexity 7 model 2 1.2125735971572018
20240811-11:15:25 test_perplexity 7 model 2 1.2432000994799361
20240811-11:15:27 train_perplexity 7 model 4 1.1913429580027342
20240811-11:15:29 test_perplexity 7 model 4 1.1753317560343266
20240811-11:16:08 test_accuracy 7 model 2 val 205 / 800
20240811-11:16:13 test_accuracy 7 model 4 val 296 / 799
20240811-11:16:15 wrote gpt_002.pth
20240811-11:16:15 wrote gpt_004.pth
20240811-11:16:28 wrote non_validated_0007_02.png
20240811-11:16:41 wrote non_validated_0007_04.png
20240811-11:16:41 wrote state.pth
20240811-11:16:41 --- epoch 8 ----------------------------------------
20240811-11:16:41 current_test_accuracies 0.2472 0.2734 0.2562 0.3098 0.3705
20240811-11:16:41 training model 0
20240811-11:16:41 training model 2
20240811-11:20:25 train_perplexity 8 model 0 1.1888942355904089
20240811-11:20:27 train_perplexity 8 model 2 1.189957801035849
20240811-11:20:28 test_perplexity 8 model 0 1.1768020435434245
20240811-11:20:29 test_perplexity 8 model 2 1.1730627378717966
20240811-11:21:14 test_accuracy 8 model 2 val 384 / 804
20240811-11:21:16 test_accuracy 8 model 0 val 314 / 788
20240811-11:21:17 wrote gpt_000.pth
20240811-11:21:18 wrote gpt_002.pth
20240811-11:21:31 wrote non_validated_0008_00.png
20240811-11:21:43 wrote non_validated_0008_02.png
20240811-11:21:44 wrote state.pth
20240811-11:21:44 --- epoch 9 ----------------------------------------
20240811-11:21:44 current_test_accuracies 0.3985 0.2734 0.4776 0.3098 0.3705
20240811-11:21:44 training model 1
20240811-11:21:44 training model 3
20240811-11:25:27 train_perplexity 9 model 1 1.1923631089664473
20240811-11:25:29 test_perplexity 9 model 1 1.1786831072150508
20240811-11:25:30 train_perplexity 9 model 3 1.1879896189813255
20240811-11:25:32 test_perplexity 9 model 3 1.1704856842548583
20240811-11:26:14 test_accuracy 9 model 1 val 392 / 821
20240811-11:26:18 test_accuracy 9 model 3 val 391 / 792
20240811-11:26:20 wrote gpt_001.pth
20240811-11:26:20 wrote gpt_003.pth
20240811-11:26:33 wrote non_validated_0009_01.png
20240811-11:26:46 wrote non_validated_0009_03.png
20240811-11:26:46 wrote state.pth
20240811-11:26:46 --- epoch 10 ----------------------------------------
20240811-11:26:46 current_test_accuracies 0.3985 0.4775 0.4776 0.4937 0.3705
20240811-11:26:46 training model 4
20240811-11:26:46 training model 0
20240811-11:30:30 train_perplexity 10 model 4 1.1770237074293946
20240811-11:30:31 test_perplexity 10 model 4 1.1704527994599092
20240811-11:30:33 train_perplexity 10 model 0 1.176431470704085
20240811-11:30:35 test_perplexity 10 model 0 1.1646959600101072
20240811-11:31:17 test_accuracy 10 model 4 val 415 / 825
20240811-11:31:21 test_accuracy 10 model 0 val 441 / 786
20240811-11:31:23 wrote gpt_004.pth
20240811-11:31:24 wrote gpt_000.pth
20240811-11:31:36 wrote non_validated_0010_04.png
20240811-11:31:49 wrote non_validated_0010_00.png
20240811-11:31:49 wrote state.pth
20240811-11:31:49 --- epoch 11 ----------------------------------------
20240811-11:31:49 current_test_accuracies 0.5611 0.4775 0.4776 0.4937 0.5030
20240811-11:31:49 training model 1
20240811-11:31:49 training model 2
20240811-11:35:32 train_perplexity 11 model 1 1.1799185005097201
20240811-11:35:34 test_perplexity 11 model 1 1.1690033236895319
20240811-11:35:35 train_perplexity 11 model 2 1.1764474251961088
20240811-11:35:38 test_perplexity 11 model 2 1.166445267023181
20240811-11:36:20 test_accuracy 11 model 1 val 457 / 811
20240811-11:36:23 test_accuracy 11 model 2 val 408 / 788
20240811-11:36:25 wrote gpt_001.pth
20240811-11:36:26 wrote gpt_002.pth
20240811-11:36:39 wrote non_validated_0011_01.png
20240811-11:36:51 wrote non_validated_0011_02.png
20240811-11:36:51 wrote state.pth
20240811-11:36:51 --- epoch 12 ----------------------------------------
20240811-11:36:51 current_test_accuracies 0.5611 0.5635 0.5178 0.4937 0.5030
20240811-11:36:51 training model 3
20240811-11:36:51 training model 4
20240811-11:40:35 train_perplexity 12 model 3 1.1750885627107304
20240811-11:40:37 test_perplexity 12 model 3 1.1644262409430166
20240811-11:40:38 train_perplexity 12 model 4 1.168422475509083
20240811-11:40:40 test_perplexity 12 model 4 1.1634705505155327
20240811-11:41:25 test_accuracy 12 model 3 val 452 / 784
20240811-11:41:26 test_accuracy 12 model 4 val 501 / 811
20240811-11:41:28 wrote gpt_003.pth
20240811-11:41:28 wrote gpt_004.pth
20240811-11:41:41 wrote non_validated_0012_03.png
20240811-11:41:54 wrote non_validated_0012_04.png
20240811-11:41:54 wrote state.pth
20240811-11:41:54 --- epoch 13 ----------------------------------------
20240811-11:41:54 current_test_accuracies 0.5611 0.5635 0.5178 0.5765 0.6178
20240811-11:41:54 training model 2
20240811-11:41:54 training model 0
20240811-11:45:38 train_perplexity 13 model 2 1.168512007682074
20240811-11:45:40 test_perplexity 13 model 2 1.1596080535606772
20240811-11:45:41 train_perplexity 13 model 0 1.1683728702600182
20240811-11:45:43 test_perplexity 13 model 0 1.1625248143386007
20240811-11:46:28 test_accuracy 13 model 2 val 514 / 794
20240811-11:46:29 test_accuracy 13 model 0 val 514 / 811
20240811-11:46:31 wrote gpt_002.pth
20240811-11:46:32 wrote gpt_000.pth
20240811-11:46:45 wrote non_validated_0013_02.png
20240811-11:46:57 wrote non_validated_0013_00.png
20240811-11:46:57 wrote state.pth
20240811-11:46:57 --- epoch 14 ----------------------------------------
20240811-11:46:57 current_test_accuracies 0.6338 0.5635 0.6474 0.5765 0.6178
20240811-11:46:57 training model 1
20240811-11:46:57 training model 3
20240811-11:50:41 train_perplexity 14 model 1 1.170455080736974
20240811-11:50:43 test_perplexity 14 model 1 1.1625101379782807
20240811-11:50:44 train_perplexity 14 model 3 1.1671861409206714
20240811-11:50:46 test_perplexity 14 model 3 1.159961008570777
20240811-11:51:30 test_accuracy 14 model 3 val 542 / 819
20240811-11:51:32 test_accuracy 14 model 1 val 542 / 797
20240811-11:51:34 wrote gpt_001.pth
20240811-11:51:34 wrote gpt_003.pth
20240811-11:51:47 wrote non_validated_0014_01.png
20240811-11:52:00 wrote non_validated_0014_03.png
20240811-11:52:00 wrote state.pth
20240811-11:52:00 --- epoch 15 ----------------------------------------
20240811-11:52:00 current_test_accuracies 0.6338 0.6801 0.6474 0.6618 0.6178
20240811-11:52:00 training model 4
20240811-11:52:00 training model 0
20240811-11:55:44 train_perplexity 15 model 4 1.163715500518264
20240811-11:55:46 test_perplexity 15 model 4 1.1546568932849557
20240811-11:55:47 train_perplexity 15 model 0 1.1632216868332739
20240811-11:55:50 test_perplexity 15 model 0 1.15533987743538
20240811-11:56:33 test_accuracy 15 model 4 val 556 / 774
20240811-11:56:36 test_accuracy 15 model 0 val 528 / 784
20240811-11:56:38 wrote gpt_004.pth
20240811-11:56:39 wrote gpt_000.pth
20240811-11:56:51 wrote non_validated_0015_04.png
20240811-11:57:04 wrote non_validated_0015_00.png
20240811-11:57:04 wrote state.pth
20240811-11:57:04 --- epoch 16 ----------------------------------------
20240811-11:57:04 current_test_accuracies 0.6735 0.6801 0.6474 0.6618 0.7183
20240811-11:57:04 training model 2
20240811-11:57:04 training model 3
20240811-12:00:48 train_perplexity 16 model 2 1.1628913451175498
20240811-12:00:50 test_perplexity 16 model 2 1.1570209244498548
20240811-12:00:51 train_perplexity 16 model 3 1.1623390923706098
20240811-12:00:53 test_perplexity 16 model 3 1.156578483310671
20240811-12:01:35 test_accuracy 16 model 2 val 582 / 803
20240811-12:01:37 test_accuracy 16 model 3 val 604 / 809
20240811-12:01:39 wrote gpt_002.pth
20240811-12:01:40 wrote gpt_003.pth
20240811-12:01:52 wrote non_validated_0016_02.png
20240811-12:02:05 wrote non_validated_0016_03.png
20240811-12:02:05 wrote state.pth
20240811-12:02:05 --- epoch 17 ----------------------------------------
20240811-12:02:05 current_test_accuracies 0.6735 0.6801 0.7248 0.7466 0.7183
20240811-12:02:05 training model 0
20240811-12:02:05 training model 1
20240811-12:05:50 train_perplexity 17 model 0 1.1598536280706881
20240811-12:05:51 test_perplexity 17 model 0 1.156406068952302
20240811-12:05:53 train_perplexity 17 model 1 1.163893286115679
20240811-12:05:55 test_perplexity 17 model 1 1.1570539172123064
20240811-12:06:40 test_accuracy 17 model 0 val 585 / 777
20240811-12:06:40 test_accuracy 17 model 1 val 597 / 805
20240811-12:06:43 wrote gpt_000.pth
20240811-12:06:43 wrote gpt_001.pth
20240811-12:06:56 wrote non_validated_0017_00.png
20240811-12:07:09 wrote non_validated_0017_01.png
20240811-12:07:09 wrote state.pth
20240811-12:07:09 --- epoch 18 ----------------------------------------
20240811-12:07:09 current_test_accuracies 0.7529 0.7416 0.7248 0.7466 0.7183
20240811-12:07:09 training model 4
20240811-12:07:09 training model 2
20240811-12:10:54 train_perplexity 18 model 4 1.1594975859912482
20240811-12:10:56 train_perplexity 18 model 2 1.1597256209451388
20240811-12:10:56 test_perplexity 18 model 4 1.153774462789966
20240811-12:10:58 test_perplexity 18 model 2 1.1532280813708018
20240811-12:11:43 test_accuracy 18 model 2 val 657 / 818
20240811-12:11:45 test_accuracy 18 model 4 val 614 / 789
20240811-12:11:47 wrote gpt_004.pth
20240811-12:11:48 wrote gpt_002.pth
20240811-12:12:00 wrote non_validated_0018_04.png
20240811-12:12:13 wrote non_validated_0018_02.png
20240811-12:12:13 wrote state.pth
20240811-12:12:13 --- epoch 19 ----------------------------------------
20240811-12:12:13 current_test_accuracies 0.7529 0.7416 0.8032 0.7466 0.7782
20240811-12:12:13 training model 1
20240811-12:12:13 training model 3
20240811-12:15:58 train_perplexity 19 model 1 1.1596861088903352
20240811-12:15:59 test_perplexity 19 model 1 1.1546994477069452
20240811-12:16:00 train_perplexity 19 model 3 1.159533426680577
20240811-12:16:03 test_perplexity 19 model 3 1.1565466699769178
20240811-12:16:44 test_accuracy 19 model 1 val 650 / 810
20240811-12:16:46 test_accuracy 19 model 3 val 654 / 814
20240811-12:16:48 wrote gpt_001.pth
20240811-12:16:49 wrote gpt_003.pth
20240811-12:17:01 wrote non_validated_0019_01.png
20240811-12:17:14 wrote non_validated_0019_03.png
20240811-12:17:14 wrote state.pth
20240811-12:17:14 --- epoch 20 ----------------------------------------
20240811-12:17:14 current_test_accuracies 0.7529 0.8025 0.8032 0.8034 0.7782
20240811-12:17:14 training model 0
20240811-12:17:14 training model 4
20240811-12:20:59 train_perplexity 20 model 0 1.1573314218425843
20240811-12:21:00 train_perplexity 20 model 4 1.1570535138541138
20240811-12:21:02 test_perplexity 20 model 0 1.1529247064083419
20240811-12:21:03 test_perplexity 20 model 4 1.154355637487912
20240811-12:21:47 test_accuracy 20 model 0 val 644 / 804
20240811-12:21:49 test_accuracy 20 model 4 val 663 / 818
20240811-12:21:51 wrote gpt_000.pth
20240811-12:21:52 wrote gpt_004.pth
20240811-12:22:04 wrote non_validated_0020_00.png
20240811-12:22:17 wrote non_validated_0020_04.png
20240811-12:22:17 wrote state.pth
20240811-12:22:17 --- epoch 21 ----------------------------------------
20240811-12:22:17 current_test_accuracies 0.8010 0.8025 0.8032 0.8034 0.8105
20240811-12:22:17 training model 0
20240811-12:22:17 training model 1
20240811-12:26:03 train_perplexity 21 model 0 1.155183841362581
20240811-12:26:04 train_perplexity 21 model 1 1.1579301255914474
20240811-12:26:06 test_perplexity 21 model 0 1.1512222833085095
20240811-12:26:07 test_perplexity 21 model 1 1.151513477854285
20240811-12:26:51 test_accuracy 21 model 0 val 663 / 810
20240811-12:26:52 test_accuracy 21 model 1 val 657 / 808
20240811-12:26:54 wrote gpt_000.pth
20240811-12:26:55 wrote gpt_001.pth
20240811-12:27:08 wrote non_validated_0021_00.png
20240811-12:27:20 wrote non_validated_0021_01.png
20240811-12:27:20 wrote state.pth
20240811-12:27:20 --- epoch 22 ----------------------------------------
20240811-12:27:20 current_test_accuracies 0.8185 0.8131 0.8032 0.8034 0.8105
20240811-12:27:20 training model 2
20240811-12:27:20 training model 3
20240811-12:31:06 train_perplexity 22 model 2 1.1562869222861116
20240811-12:31:07 test_perplexity 22 model 2 1.1525097804406026
20240811-12:31:08 train_perplexity 22 model 3 1.156458452372321
20240811-12:31:10 test_perplexity 22 model 3 1.15435392274063
20240811-12:31:53 test_accuracy 22 model 3 val 681 / 809
20240811-12:31:55 test_accuracy 22 model 2 val 642 / 799
20240811-12:31:57 wrote gpt_002.pth
20240811-12:31:57 wrote gpt_003.pth
20240811-12:32:10 wrote non_validated_0022_02.png
20240811-12:32:23 wrote non_validated_0022_03.png
20240811-12:32:23 wrote state.pth
20240811-12:32:23 --- epoch 23 ----------------------------------------
20240811-12:32:23 current_test_accuracies 0.8185 0.8131 0.8035 0.8418 0.8105
20240811-12:32:23 training model 2
20240811-12:32:23 training model 4
20240811-12:36:09 train_perplexity 23 model 2 1.1554829773249864
20240811-12:36:09 train_perplexity 23 model 4 1.1548313470042413
20240811-12:36:12 test_perplexity 23 model 2 1.1521071366035671
20240811-12:36:13 test_perplexity 23 model 4 1.1505845569618092
20240811-12:36:57 test_accuracy 23 model 4 val 696 / 818
20240811-12:36:59 test_accuracy 23 model 2 val 676 / 778
20240811-12:37:01 wrote gpt_002.pth
20240811-12:37:02 wrote gpt_004.pth
20240811-12:37:15 wrote non_validated_0023_02.png
20240811-12:37:27 wrote non_validated_0023_04.png
20240811-12:37:27 wrote state.pth
20240811-12:37:27 --- epoch 24 ----------------------------------------
20240811-12:37:27 current_test_accuracies 0.8185 0.8131 0.8689 0.8418 0.8509
20240811-12:37:27 training model 1
20240811-12:37:27 training model 0
20240811-12:41:13 train_perplexity 24 model 1 1.1557150422225326
20240811-12:41:13 train_perplexity 24 model 0 1.1538251501682382
20240811-12:41:17 test_perplexity 24 model 1 1.148321260563121
20240811-12:41:17 test_perplexity 24 model 0 1.1519102667688703
20240811-12:42:01 test_accuracy 24 model 1 val 680 / 802
20240811-12:42:04 test_accuracy 24 model 0 val 672 / 794
20240811-12:42:06 wrote gpt_001.pth
20240811-12:42:06 wrote gpt_000.pth
20240811-12:42:19 wrote non_validated_0024_01.png
20240811-12:42:32 wrote non_validated_0024_00.png
20240811-12:42:32 wrote state.pth
20240811-12:42:32 --- epoch 25 ----------------------------------------
20240811-12:42:32 current_test_accuracies 0.8463 0.8479 0.8689 0.8418 0.8509
20240811-12:42:32 training model 3
20240811-12:42:32 training model 0
20240811-12:46:18 train_perplexity 25 model 3 1.1543769085968072
20240811-12:46:19 train_perplexity 25 model 0 1.1528969521464318
20240811-12:46:21 test_perplexity 25 model 3 1.1519338559521382
20240811-12:46:22 test_perplexity 25 model 0 1.1479815313419097
20240811-12:47:08 test_accuracy 25 model 3 val 696 / 812
20240811-12:47:10 test_accuracy 25 model 0 val 687 / 790
20240811-12:47:12 wrote gpt_003.pth
20240811-12:47:13 wrote gpt_000.pth
20240811-12:47:25 wrote non_validated_0025_03.png
20240811-12:47:38 wrote non_validated_0025_00.png
20240811-12:47:38 wrote state.pth
20240811-12:47:38 --- epoch 26 ----------------------------------------
20240811-12:47:38 current_test_accuracies 0.8696 0.8479 0.8689 0.8571 0.8509
20240811-12:47:38 training model 1
20240811-12:47:38 training model 4
20240811-12:51:23 train_perplexity 26 model 1 1.153514208381397
20240811-12:51:25 train_perplexity 26 model 4 1.1531215737409173
20240811-12:51:26 test_perplexity 26 model 1 1.1500830161904465
20240811-12:51:28 test_perplexity 26 model 4 1.1514559524034722
20240811-12:52:12 test_accuracy 26 model 4 val 702 / 805
20240811-12:52:14 test_accuracy 26 model 1 val 677 / 789
20240811-12:52:16 wrote gpt_001.pth
20240811-12:52:17 wrote gpt_004.pth
20240811-12:52:29 wrote non_validated_0026_01.png
20240811-12:52:42 wrote non_validated_0026_04.png
20240811-12:52:42 wrote state.pth
20240811-12:52:42 --- epoch 27 ----------------------------------------
20240811-12:52:42 current_test_accuracies 0.8696 0.8580 0.8689 0.8571 0.8720
20240811-12:52:42 training model 3
20240811-12:52:42 training model 1
20240811-12:56:28 train_perplexity 27 model 3 1.1532878768963313
20240811-12:56:29 train_perplexity 27 model 1 1.1526960820432517
20240811-12:56:31 test_perplexity 27 model 3 1.1504004647582255
20240811-12:56:32 test_perplexity 27 model 1 1.1482620877202214
20240811-12:57:19 test_accuracy 27 model 1 val 698 / 789
20240811-12:57:20 test_accuracy 27 model 3 val 696 / 795
20240811-12:57:22 wrote gpt_003.pth
20240811-12:57:23 wrote gpt_001.pth
20240811-12:57:35 wrote non_validated_0027_03.png
20240811-12:57:48 wrote non_validated_0027_01.png
20240811-12:57:48 wrote state.pth
20240811-12:57:48 --- epoch 28 ----------------------------------------
20240811-12:57:48 current_test_accuracies 0.8696 0.8847 0.8689 0.8755 0.8720
20240811-12:57:48 training model 2
20240811-12:57:48 training model 0
20240811-13:01:34 train_perplexity 28 model 2 1.1528321596665259
20240811-13:01:35 train_perplexity 28 model 0 1.1511659186578669
20240811-13:01:37 test_perplexity 28 model 2 1.1490229072070006
20240811-13:01:38 test_perplexity 28 model 0 1.1502048032989125
20240811-13:02:21 test_accuracy 28 model 2 val 717 / 810
20240811-13:02:22 test_accuracy 28 model 0 val 729 / 826
20240811-13:02:24 wrote gpt_002.pth
20240811-13:02:25 wrote gpt_000.pth
20240811-13:02:38 wrote non_validated_0028_02.png
20240811-13:02:50 wrote non_validated_0028_00.png
20240811-13:02:50 wrote state.pth
20240811-13:02:50 --- epoch 29 ----------------------------------------
20240811-13:02:50 current_test_accuracies 0.8826 0.8847 0.8852 0.8755 0.8720
20240811-13:02:50 training model 4
20240811-13:02:50 training model 3
20240811-13:06:36 train_perplexity 29 model 4 1.1526050016252325
20240811-13:06:37 train_perplexity 29 model 3 1.1517090346567533
20240811-13:06:39 test_perplexity 29 model 4 1.150847271771437
20240811-13:06:40 test_perplexity 29 model 3 1.1451197782637903
20240811-13:07:24 test_accuracy 29 model 4 val 710 / 801
20240811-13:07:27 test_accuracy 29 model 3 val 718 / 783
20240811-13:07:29 wrote gpt_004.pth
20240811-13:07:30 wrote gpt_003.pth
20240811-13:07:43 wrote non_validated_0029_04.png
20240811-13:07:55 wrote non_validated_0029_03.png
20240811-13:07:55 wrote state.pth
20240811-13:07:55 --- epoch 30 ----------------------------------------
20240811-13:07:55 current_test_accuracies 0.8826 0.8847 0.8852 0.9170 0.8864
20240811-13:07:55 training model 0
20240811-13:07:55 training model 1
20240811-13:11:41 train_perplexity 30 model 0 1.1505880459142983
20240811-13:11:42 train_perplexity 30 model 1 1.151018977535587
20240811-13:11:44 test_perplexity 30 model 0 1.1508150017383425
20240811-13:11:45 test_perplexity 30 model 1 1.1511941971516446
20240811-13:12:29 test_accuracy 30 model 0 val 732 / 810
20240811-13:12:30 test_accuracy 30 model 1 val 741 / 812
20240811-13:12:32 wrote gpt_000.pth
20240811-13:12:32 wrote gpt_001.pth
20240811-13:12:45 wrote non_validated_0030_00.png
20240811-13:12:58 wrote non_validated_0030_01.png
20240811-13:12:58 wrote state.pth
20240811-13:12:58 --- epoch 31 ----------------------------------------
20240811-13:12:58 current_test_accuracies 0.9037 0.9126 0.8852 0.9170 0.8864
20240811-13:12:58 training model 2
20240811-13:12:58 training model 4
20240811-13:16:44 train_perplexity 31 model 2 1.1519234653584915
20240811-13:16:44 train_perplexity 31 model 4 1.151026234682521
20240811-13:16:46 test_perplexity 31 model 2 1.149570071111463
20240811-13:16:48 test_perplexity 31 model 4 1.1496288047144032
20240811-13:17:32 test_accuracy 31 model 4 val 705 / 800
20240811-13:17:34 test_accuracy 31 model 2 val 714 / 793
20240811-13:17:36 wrote gpt_002.pth
20240811-13:17:37 wrote gpt_004.pth
20240811-13:17:50 wrote non_validated_0031_02.png
20240811-13:18:02 wrote non_validated_0031_04.png
20240811-13:18:02 wrote state.pth
20240811-13:18:02 --- epoch 32 ----------------------------------------
20240811-13:18:02 current_test_accuracies 0.9037 0.9126 0.9004 0.9170 0.8813
20240811-13:18:02 training model 4
20240811-13:18:02 training model 2
20240811-13:21:48 train_perplexity 32 model 4 1.1506649935060982
20240811-13:21:48 train_perplexity 32 model 2 1.1507922587916792
20240811-13:21:52 test_perplexity 32 model 4 1.146380347983469
20240811-13:21:52 test_perplexity 32 model 2 1.150034638483712
20240811-13:22:37 test_accuracy 32 model 2 val 742 / 806
20240811-13:22:39 test_accuracy 32 model 4 val 707 / 788
20240811-13:22:41 wrote gpt_004.pth
20240811-13:22:41 wrote gpt_002.pth
20240811-13:22:54 wrote non_validated_0032_04.png
20240811-13:23:07 wrote non_validated_0032_02.png
20240811-13:23:07 wrote state.pth
20240811-13:23:07 --- epoch 33 ----------------------------------------
20240811-13:23:07 current_test_accuracies 0.9037 0.9126 0.9206 0.9170 0.8972
20240811-13:23:07 training model 4
20240811-13:23:07 training model 0
20240811-13:26:53 train_perplexity 33 model 4 1.1496870154024807
20240811-13:26:53 train_perplexity 33 model 0 1.1500608477224277
20240811-13:26:57 test_perplexity 33 model 4 1.1474215889640538
20240811-13:26:57 test_perplexity 33 model 0 1.149264784376239
20240811-13:27:44 test_accuracy 33 model 4 val 703 / 769
20240811-13:27:44 test_accuracy 33 model 0 val 691 / 784
20240811-13:27:46 wrote gpt_004.pth
20240811-13:27:47 wrote gpt_000.pth
20240811-13:28:00 wrote non_validated_0033_04.png
20240811-13:28:12 wrote non_validated_0033_00.png
20240811-13:28:13 wrote state.pth
20240811-13:28:13 --- epoch 34 ----------------------------------------
20240811-13:28:13 current_test_accuracies 0.8814 0.9126 0.9206 0.9170 0.9142
20240811-13:28:13 training model 0
20240811-13:28:13 training model 1
20240811-13:31:58 train_perplexity 34 model 0 1.1493619668486452
20240811-13:31:59 train_perplexity 34 model 1 1.1507220045097533
20240811-13:32:02 test_perplexity 34 model 0 1.1477343862083869
20240811-13:32:02 test_perplexity 34 model 1 1.1485989045453056
20240811-13:32:47 test_accuracy 34 model 0 val 733 / 801
20240811-13:32:49 test_accuracy 34 model 1 val 731 / 798
20240811-13:32:51 wrote gpt_000.pth
20240811-13:32:52 wrote gpt_001.pth
20240811-13:33:05 wrote non_validated_0034_00.png
20240811-13:33:17 wrote non_validated_0034_01.png
20240811-13:33:17 wrote state.pth
20240811-13:33:17 --- epoch 35 ----------------------------------------
20240811-13:33:17 current_test_accuracies 0.9151 0.9160 0.9206 0.9170 0.9142
20240811-13:33:17 training model 4
20240811-13:33:17 training model 0
20240811-13:37:03 train_perplexity 35 model 4 1.149304851661424
20240811-13:37:04 train_perplexity 35 model 0 1.1491076600931553
20240811-13:37:07 test_perplexity 35 model 4 1.1478786133754493
20240811-13:37:07 test_perplexity 35 model 0 1.146706613975148
20240811-13:37:54 test_accuracy 35 model 4 val 733 / 792
20240811-13:37:56 test_accuracy 35 model 0 val 725 / 794
20240811-13:37:58 wrote gpt_004.pth
20240811-13:37:58 wrote gpt_000.pth
20240811-13:38:11 wrote non_validated_0035_04.png
20240811-13:38:24 wrote non_validated_0035_00.png
20240811-13:38:24 wrote state.pth
20240811-13:38:24 --- epoch 36 ----------------------------------------
20240811-13:38:24 current_test_accuracies 0.9131 0.9160 0.9206 0.9170 0.9255
20240811-13:38:24 training model 0
20240811-13:38:24 training model 1
20240811-13:42:10 train_perplexity 36 model 0 1.1486604693562865
20240811-13:42:10 train_perplexity 36 model 1 1.1496088136198872
20240811-13:42:13 test_perplexity 36 model 0 1.1443590870430493
20240811-13:42:14 test_perplexity 36 model 1 1.1484020115083866
20240811-13:43:02 test_accuracy 36 model 1 val 747 / 798
20240811-13:43:02 test_accuracy 36 model 0 val 736 / 788
20240811-13:43:04 wrote gpt_000.pth
20240811-13:43:05 wrote gpt_001.pth
20240811-13:43:18 wrote non_validated_0036_00.png
20240811-13:43:30 wrote non_validated_0036_01.png
20240811-13:43:30 wrote state.pth
20240811-13:43:30 --- epoch 37 ----------------------------------------
20240811-13:43:30 current_test_accuracies 0.9340 0.9361 0.9206 0.9170 0.9255
20240811-13:43:30 training model 3
20240811-13:43:30 training model 2
20240811-13:47:17 train_perplexity 37 model 3 1.1511987347014447
20240811-13:47:17 train_perplexity 37 model 2 1.1506863709565276
20240811-13:47:20 test_perplexity 37 model 3 1.1479214606541246
20240811-13:47:20 test_perplexity 37 model 2 1.1464039956049408
20240811-13:48:05 test_accuracy 37 model 3 val 718 / 804
20240811-13:48:08 test_accuracy 37 model 2 val 738 / 790
20240811-13:48:10 wrote gpt_003.pth
20240811-13:48:10 wrote gpt_002.pth
20240811-13:48:23 wrote non_validated_0037_03.png
20240811-13:48:36 wrote non_validated_0037_02.png
20240811-13:48:36 wrote state.pth
20240811-13:48:36 --- epoch 38 ----------------------------------------
20240811-13:48:36 current_test_accuracies 0.9340 0.9361 0.9342 0.8930 0.9255
20240811-13:48:36 training model 3
20240811-13:48:36 training model 4
20240811-13:52:22 train_perplexity 38 model 3 1.1503912876898306
20240811-13:52:22 train_perplexity 38 model 4 1.1486600963958888
20240811-13:52:25 test_perplexity 38 model 3 1.1508481866688545
20240811-13:52:26 test_perplexity 38 model 4 1.1502321756544194
20240811-13:53:11 test_accuracy 38 model 3 val 743 / 819
20240811-13:53:13 test_accuracy 38 model 4 val 740 / 793
20240811-13:53:15 wrote gpt_003.pth
20240811-13:53:16 wrote gpt_004.pth
20240811-13:53:28 wrote non_validated_0038_03.png
20240811-13:53:41 wrote non_validated_0038_04.png
20240811-13:53:41 wrote state.pth
20240811-13:53:41 --- epoch 39 ----------------------------------------
20240811-13:53:41 current_test_accuracies 0.9340 0.9361 0.9342 0.9072 0.9332
20240811-13:53:41 training model 3
20240811-13:53:41 training model 4
20240811-13:57:27 train_perplexity 39 model 3 1.1496197220354052
20240811-13:57:28 train_perplexity 39 model 4 1.1482261439141899
20240811-13:57:31 test_perplexity 39 model 3 1.1477212795110165
20240811-13:57:31 test_perplexity 39 model 4 1.146756716838605
20240811-13:58:14 test_accuracy 39 model 4 val 754 / 802
20240811-13:58:17 test_accuracy 39 model 3 val 712 / 763
20240811-13:58:19 wrote gpt_003.pth
20240811-13:58:19 wrote gpt_004.pth
20240811-13:58:32 wrote non_validated_0039_03.png
20240811-13:58:45 wrote non_validated_0039_04.png
20240811-13:58:45 wrote state.pth
20240811-13:58:45 --- epoch 40 ----------------------------------------
20240811-13:58:45 current_test_accuracies 0.9340 0.9361 0.9342 0.9332 0.9401
20240811-13:58:45 training model 3
20240811-13:58:45 training model 0
20240811-14:02:31 train_perplexity 40 model 3 1.149284260796885
20240811-14:02:31 train_perplexity 40 model 0 1.1484551537170262
20240811-14:02:35 test_perplexity 40 model 3 1.1481180813987402
20240811-14:02:35 test_perplexity 40 model 0 1.1481723747797394
20240811-14:03:19 test_accuracy 40 model 3 val 747 / 814
20240811-14:03:22 test_accuracy 40 model 0 val 743 / 799
20240811-14:03:24 wrote gpt_003.pth
20240811-14:03:24 wrote gpt_000.pth
20240811-14:03:37 wrote non_validated_0040_03.png
20240811-14:03:50 wrote non_validated_0040_00.png
20240811-14:03:50 wrote state.pth
20240811-14:03:50 --- epoch 41 ----------------------------------------
20240811-14:03:50 current_test_accuracies 0.9299 0.9361 0.9342 0.9177 0.9401
20240811-14:03:50 training model 3
20240811-14:03:50 training model 0
20240811-14:07:36 train_perplexity 41 model 3 1.1486284909253464
20240811-14:07:36 train_perplexity 41 model 0 1.1479098727808537
20240811-14:07:39 test_perplexity 41 model 3 1.1456946655807116
20240811-14:07:40 test_perplexity 41 model 0 1.1454877483088064
20240811-14:08:22 test_accuracy 41 model 3 val 755 / 801
20240811-14:08:26 test_accuracy 41 model 0 val 737 / 792
20240811-14:08:28 wrote gpt_003.pth
20240811-14:08:28 wrote gpt_000.pth
20240811-14:08:41 wrote non_validated_0041_03.png
20240811-14:08:54 wrote non_validated_0041_00.png
20240811-14:08:54 wrote state.pth
20240811-14:08:54 --- epoch 42 ----------------------------------------
20240811-14:08:54 current_test_accuracies 0.9306 0.9361 0.9342 0.9426 0.9401
20240811-14:08:54 training model 0
20240811-14:08:54 training model 2
20240811-14:12:39 train_perplexity 42 model 0 1.1472209529700295
20240811-14:12:40 train_perplexity 42 model 2 1.149638963893599
20240811-14:12:41 test_perplexity 42 model 0 1.1466419691390657
20240811-14:12:43 test_perplexity 42 model 2 1.145006013119478
20240811-14:13:27 test_accuracy 42 model 0 val 755 / 803
20240811-14:13:29 test_accuracy 42 model 2 val 744 / 798
20240811-14:13:31 wrote gpt_000.pth
20240811-14:13:32 wrote gpt_002.pth
20240811-14:13:44 wrote non_validated_0042_00.png
20240811-14:13:57 wrote non_validated_0042_02.png
20240811-14:13:57 wrote state.pth
20240811-14:13:57 --- epoch 43 ----------------------------------------
20240811-14:13:57 current_test_accuracies 0.9402 0.9361 0.9323 0.9426 0.9401
20240811-14:13:57 training model 2
20240811-14:13:57 training model 1
20240811-14:17:43 train_perplexity 43 model 2 1.1492274133324887
20240811-14:17:43 train_perplexity 43 model 1 1.1491002577097456
20240811-14:17:47 test_perplexity 43 model 2 1.1459763406090386
20240811-14:17:47 test_perplexity 43 model 1 1.1456766874348774
20240811-14:18:32 test_accuracy 43 model 1 val 761 / 805
20240811-14:18:33 test_accuracy 43 model 2 val 732 / 780
20240811-14:18:35 wrote gpt_002.pth
20240811-14:18:36 wrote gpt_001.pth
20240811-14:18:48 wrote non_validated_0043_02.png
20240811-14:19:01 wrote non_validated_0043_01.png
20240811-14:19:01 wrote state.pth
20240811-14:19:01 --- epoch 44 ----------------------------------------
20240811-14:19:01 current_test_accuracies 0.9402 0.9453 0.9385 0.9426 0.9401
20240811-14:19:01 training model 2
20240811-14:19:01 training model 4
20240811-14:22:48 train_perplexity 44 model 2 1.1489224437597305
20240811-14:22:48 train_perplexity 44 model 4 1.1476815908808422
20240811-14:22:51 test_perplexity 44 model 2 1.147380642755189
20240811-14:22:51 test_perplexity 44 model 4 1.147767229822174
20240811-14:23:36 test_accuracy 44 model 4 val 762 / 817
20240811-14:23:38 test_accuracy 44 model 2 val 726 / 787
20240811-14:23:39 wrote gpt_002.pth
20240811-14:23:40 wrote gpt_004.pth
20240811-14:23:53 wrote non_validated_0044_02.png
20240811-14:24:06 wrote non_validated_0044_04.png
20240811-14:24:06 wrote state.pth
20240811-14:24:06 --- epoch 45 ----------------------------------------
20240811-14:24:06 current_test_accuracies 0.9402 0.9453 0.9225 0.9426 0.9327
20240811-14:24:06 training model 2
20240811-14:24:06 training model 4
20240811-14:27:51 train_perplexity 45 model 2 1.1481806774825205
20240811-14:27:52 train_perplexity 45 model 4 1.1478874336528235
20240811-14:27:55 test_perplexity 45 model 2 1.146816536888605
20240811-14:27:55 test_perplexity 45 model 4 1.1440781345064641
20240811-14:28:43 test_accuracy 45 model 2 val 743 / 799
20240811-14:28:44 test_accuracy 45 model 4 val 733 / 774
20240811-14:28:46 wrote gpt_002.pth
20240811-14:28:47 wrote gpt_004.pth
20240811-14:28:59 wrote non_validated_0045_02.png
20240811-14:29:12 wrote non_validated_0045_04.png
20240811-14:29:12 wrote state.pth
20240811-14:29:12 --- epoch 46 ----------------------------------------
20240811-14:29:12 current_test_accuracies 0.9402 0.9453 0.9299 0.9426 0.9470
20240811-14:29:12 training model 2
20240811-14:29:12 training model 0
20240811-14:32:58 train_perplexity 46 model 2 1.1481587338275039
20240811-14:32:59 train_perplexity 46 model 0 1.1474479276946223
20240811-14:33:01 test_perplexity 46 model 2 1.149019330473654
20240811-14:33:02 test_perplexity 46 model 0 1.145954707176635
20240811-14:33:46 test_accuracy 46 model 2 val 757 / 807
20240811-14:33:49 test_accuracy 46 model 0 val 756 / 798
20240811-14:33:51 wrote gpt_002.pth
20240811-14:33:51 wrote gpt_000.pth
20240811-14:34:04 wrote non_validated_0046_02.png
20240811-14:34:17 wrote non_validated_0046_00.png
20240811-14:34:17 wrote state.pth
20240811-14:34:17 --- epoch 47 ----------------------------------------
20240811-14:34:17 current_test_accuracies 0.9474 0.9453 0.9380 0.9426 0.9470
20240811-14:34:17 training model 2
20240811-14:34:17 training model 3
20240811-14:38:02 train_perplexity 47 model 2 1.1473496979072786
20240811-14:38:04 train_perplexity 47 model 3 1.1485306980656365
20240811-14:38:04 test_perplexity 47 model 2 1.1449732568359665
20240811-14:38:06 test_perplexity 47 model 3 1.1464669188681018
20240811-14:38:50 test_accuracy 47 model 3 val 752 / 803
20240811-14:38:53 test_accuracy 47 model 2 val 750 / 797
20240811-14:38:55 wrote gpt_002.pth
20240811-14:38:55 wrote gpt_003.pth
20240811-14:39:08 wrote non_validated_0047_02.png
20240811-14:39:21 wrote non_validated_0047_03.png
20240811-14:39:21 wrote state.pth
20240811-14:39:21 --- epoch 48 ----------------------------------------
20240811-14:39:21 current_test_accuracies 0.9474 0.9453 0.9410 0.9365 0.9470
20240811-14:39:21 training model 3
20240811-14:39:21 training model 2
20240811-14:43:07 train_perplexity 48 model 3 1.1482771438819037
20240811-14:43:07 train_perplexity 48 model 2 1.147857253568708
20240811-14:43:10 test_perplexity 48 model 3 1.1471824619415443
20240811-14:43:11 test_perplexity 48 model 2 1.1457999626680115
20240811-14:43:55 test_accuracy 48 model 3 val 757 / 806
20240811-14:43:56 test_accuracy 48 model 2 val 783 / 815
20240811-14:43:58 wrote gpt_003.pth
20240811-14:43:59 wrote gpt_002.pth
20240811-14:44:11 wrote non_validated_0048_03.png
20240811-14:44:24 wrote non_validated_0048_02.png
20240811-14:44:24 wrote state.pth
20240811-14:44:24 --- epoch 49 ----------------------------------------
20240811-14:44:24 current_test_accuracies 0.9474 0.9453 0.9607 0.9392 0.9470
20240811-14:44:24 training model 3
20240811-14:44:24 training model 1
20240811-14:48:10 train_perplexity 49 model 3 1.1480989684192695
20240811-14:48:10 train_perplexity 49 model 1 1.1487543136235332
20240811-14:48:13 test_perplexity 49 model 3 1.1463971221672549
20240811-14:48:14 test_perplexity 49 model 1 1.1491325485171666
20240811-14:48:59 test_accuracy 49 model 3 val 779 / 808
20240811-14:49:01 test_accuracy 49 model 1 val 740 / 792
20240811-14:49:03 wrote gpt_003.pth
20240811-14:49:04 wrote gpt_001.pth
20240811-14:49:17 wrote non_validated_0049_03.png
20240811-14:49:29 wrote non_validated_0049_01.png
20240811-14:49:30 wrote state.pth
20240811-14:49:30 --- epoch 50 ----------------------------------------
20240811-14:49:30 current_test_accuracies 0.9474 0.9343 0.9607 0.9641 0.9470
20240811-14:49:30 training model 1
20240811-14:49:30 training model 4
20240811-14:53:16 train_perplexity 50 model 1 1.1480083297034795
20240811-14:53:16 train_perplexity 50 model 4 1.147430289217174
20240811-14:53:19 test_perplexity 50 model 1 1.1478278889398081
20240811-14:53:20 test_perplexity 50 model 4 1.1457907919667754
20240811-14:54:06 test_accuracy 50 model 1 val 726 / 774
20240811-14:54:08 test_accuracy 50 model 4 val 745 / 796
20240811-14:54:10 wrote gpt_001.pth
20240811-14:54:10 wrote gpt_004.pth
20240811-14:54:23 wrote non_validated_0050_01.png
20240811-14:54:36 wrote non_validated_0050_04.png
20240811-14:54:36 wrote state.pth
20240811-14:54:36 --- epoch 51 ----------------------------------------
20240811-14:54:36 current_test_accuracies 0.9474 0.9380 0.9607 0.9641 0.9359
20240811-14:54:36 training model 4
20240811-14:54:36 training model 1
20240811-14:58:22 train_perplexity 51 model 4 1.1475131358362076
20240811-14:58:22 train_perplexity 51 model 1 1.1479239874664324
20240811-14:58:25 test_perplexity 51 model 4 1.1450487309902455
20240811-14:58:25 test_perplexity 51 model 1 1.1487684728373748
20240811-14:59:11 test_accuracy 51 model 1 val 799 / 831
20240811-14:59:13 test_accuracy 51 model 4 val 774 / 799
20240811-14:59:15 wrote gpt_004.pth
20240811-14:59:16 wrote gpt_001.pth
20240811-14:59:28 wrote non_validated_0051_04.png
20240811-14:59:41 wrote non_validated_0051_01.png
20240811-14:59:41 wrote state.pth
20240811-14:59:41 --- epoch 52 ----------------------------------------
20240811-14:59:41 current_test_accuracies 0.9474 0.9615 0.9607 0.9641 0.9687
20240811-14:59:41 training model 0
20240811-14:59:41 training model 2
20240811-15:03:27 train_perplexity 52 model 0 1.1472647154487732
20240811-15:03:27 train_perplexity 52 model 2 1.1473869976055622
20240811-15:03:31 test_perplexity 52 model 0 1.1473227170557767
20240811-15:03:31 test_perplexity 52 model 2 1.143755664995278
20240811-15:04:17 test_accuracy 52 model 0 val 770 / 810
20240811-15:04:18 test_accuracy 52 model 2 val 767 / 794
20240811-15:04:20 wrote gpt_000.pth
20240811-15:04:21 wrote gpt_002.pth
20240811-15:04:33 wrote non_validated_0052_00.png
20240811-15:04:46 wrote non_validated_0052_02.png
20240811-15:04:46 wrote state.pth
20240811-15:04:46 --- epoch 53 ----------------------------------------
20240811-15:04:46 current_test_accuracies 0.9506 0.9615 0.9660 0.9641 0.9687
20240811-15:05:56 keep c_quizzes model 2 validated 3 / 410 (0.73%) nb_accumulated 3 / 410 (finishes Sun 17:44 -- 154/h)
20240811-15:06:44 keep c_quizzes model 2 validated 2 / 410 (0.49%) nb_accumulated 5 / 410 (finishes Sun 17:45 -- 152/h)
20240811-15:07:32 keep c_quizzes model 4 validated 2 / 410 (0.49%) nb_accumulated 7 / 410 (finishes Sun 17:46 -- 152/h)
20240811-15:08:19 keep c_quizzes model 1 validated 2 / 410 (0.49%) nb_accumulated 9 / 410 (finishes Sun 17:46 -- 151/h)
20240811-15:09:08 keep c_quizzes model 3 validated 3 / 410 (0.73%) nb_accumulated 12 / 410 (finishes Sun 17:33 -- 165/h)
20240811-15:09:55 keep c_quizzes model 2 validated 1 / 410 (0.24%) nb_accumulated 13 / 410 (finishes Sun 17:47 -- 151/h)
20240811-15:10:43 keep c_quizzes model 3 validated 4 / 410 (0.98%) nb_accumulated 17 / 410 (finishes Sun 17:28 -- 171/h)
20240811-15:11:31 keep c_quizzes model 0 validated 3 / 410 (0.73%) nb_accumulated 20 / 410 (finishes Sun 17:23 -- 177/h)
20240811-15:12:19 keep c_quizzes model 1 validated 1 / 410 (0.24%) nb_accumulated 21 / 410 (finishes Sun 17:32 -- 166/h)
20240811-15:13:07 keep c_quizzes model 0 validated 1 / 410 (0.24%) nb_accumulated 22 / 410 (finishes Sun 17:40 -- 158/h)
20240811-15:13:55 keep c_quizzes model 0 validated 3 / 410 (0.73%) nb_accumulated 25 / 410 (finishes Sun 17:34 -- 164/h)
20240811-15:14:43 keep c_quizzes model 3 validated 0 / 410 (0.00%) nb_accumulated 25 / 410 (finishes Sun 17:47 -- 150/h)
20240811-15:15:30 keep c_quizzes model 2 validated 3 / 410 (0.73%) nb_accumulated 28 / 410 (finishes Sun 17:41 -- 156/h)
20240811-15:16:18 keep c_quizzes model 4 validated 1 / 410 (0.24%) nb_accumulated 29 / 410 (finishes Sun 17:47 -- 150/h)
20240811-15:17:06 keep c_quizzes model 3 validated 0 / 410 (0.00%) nb_accumulated 29 / 410 (finishes Sun 17:58 -- 141/h)
20240811-15:17:53 keep c_quizzes model 0 validated 0 / 410 (0.00%) nb_accumulated 29 / 410 (finishes Sun 18:10 -- 132/h)
20240811-15:18:41 keep c_quizzes model 2 validated 2 / 410 (0.49%) nb_accumulated 31 / 410 (finishes Sun 18:08 -- 133/h)
20240811-15:19:29 keep c_quizzes model 0 validated 3 / 410 (0.73%) nb_accumulated 34 / 410 (finishes Sun 18:02 -- 138/h)
20240811-15:20:16 keep c_quizzes model 0 validated 1 / 410 (0.24%) nb_accumulated 35 / 410 (finishes Sun 18:06 -- 135/h)
20240811-15:21:04 keep c_quizzes model 3 validated 2 / 410 (0.49%) nb_accumulated 37 / 410 (finishes Sun 18:05 -- 136/h)
20240811-15:21:52 keep c_quizzes model 3 validated 0 / 410 (0.00%) nb_accumulated 37 / 410 (finishes Sun 18:14 -- 129/h)
20240811-15:22:40 keep c_quizzes model 3 validated 0 / 410 (0.00%) nb_accumulated 37 / 410 (finishes Sun 18:23 -- 124/h)
20240811-15:23:27 keep c_quizzes model 2 validated 4 / 410 (0.98%) nb_accumulated 41 / 410 (finishes Sun 18:11 -- 131/h)
20240811-15:24:15 keep c_quizzes model 4 validated 1 / 410 (0.24%) nb_accumulated 42 / 410 (finishes Sun 18:14 -- 129/h)
20240811-15:25:03 keep c_quizzes model 1 validated 1 / 410 (0.24%) nb_accumulated 43 / 410 (finishes Sun 18:18 -- 127/h)
20240811-15:25:50 keep c_quizzes model 4 validated 2 / 410 (0.49%) nb_accumulated 45 / 410 (finishes Sun 18:16 -- 128/h)
20240811-15:26:38 keep c_quizzes model 2 validated 1 / 410 (0.24%) nb_accumulated 46 / 410 (finishes Sun 18:19 -- 126/h)
20240811-15:27:26 keep c_quizzes model 4 validated 1 / 410 (0.24%) nb_accumulated 47 / 410 (finishes Sun 18:22 -- 124/h)
20240811-15:28:13 keep c_quizzes model 4 validated 2 / 410 (0.49%) nb_accumulated 49 / 410 (finishes Sun 18:20 -- 125/h)
20240811-15:29:01 keep c_quizzes model 1 validated 0 / 410 (0.00%) nb_accumulated 49 / 410 (finishes Sun 18:27 -- 121/h)
20240811-15:29:49 keep c_quizzes model 4 validated 0 / 410 (0.00%) nb_accumulated 49 / 410 (finishes Sun 18:34 -- 117/h)
20240811-15:30:36 keep c_quizzes model 1 validated 0 / 410 (0.00%) nb_accumulated 49 / 410 (finishes Sun 18:40 -- 113/h)
20240811-15:31:24 keep c_quizzes model 4 validated 1 / 410 (0.24%) nb_accumulated 50 / 410 (finishes Sun 18:43 -- 112/h)
20240811-15:32:12 keep c_quizzes model 3 validated 1 / 410 (0.24%) nb_accumulated 51 / 410 (finishes Sun 18:45 -- 111/h)
20240811-15:33:00 keep c_quizzes model 3 validated 2 / 410 (0.49%) nb_accumulated 53 / 410 (finishes Sun 18:43 -- 112/h)
20240811-15:33:47 keep c_quizzes model 1 validated 0 / 410 (0.00%) nb_accumulated 53 / 410 (finishes Sun 18:49 -- 109/h)
20240811-15:34:35 keep c_quizzes model 4 validated 1 / 410 (0.24%) nb_accumulated 54 / 410 (finishes Sun 18:51 -- 108/h)
20240811-15:35:23 keep c_quizzes model 4 validated 0 / 410 (0.00%) nb_accumulated 54 / 410 (finishes Sun 18:57 -- 105/h)
20240811-15:36:11 keep c_quizzes model 1 validated 2 / 410 (0.49%) nb_accumulated 56 / 410 (finishes Sun 18:54 -- 106/h)
20240811-15:36:58 keep c_quizzes model 4 validated 1 / 410 (0.24%) nb_accumulated 57 / 410 (finishes Sun 18:56 -- 106/h)
20240811-15:37:46 keep c_quizzes model 3 validated 1 / 410 (0.24%) nb_accumulated 58 / 410 (finishes Sun 18:58 -- 105/h)
20240811-15:38:34 keep c_quizzes model 2 validated 2 / 410 (0.49%) nb_accumulated 60 / 410 (finishes Sun 18:55 -- 106/h)
20240811-15:39:22 keep c_quizzes model 1 validated 1 / 410 (0.24%) nb_accumulated 61 / 410 (finishes Sun 18:57 -- 105/h)
20240811-15:40:09 keep c_quizzes model 0 validated 3 / 410 (0.73%) nb_accumulated 64 / 410 (finishes Sun 18:51 -- 108/h)
20240811-15:40:57 keep c_quizzes model 1 validated 0 / 410 (0.00%) nb_accumulated 64 / 410 (finishes Sun 18:56 -- 106/h)
20240811-15:41:45 keep c_quizzes model 4 validated 2 / 410 (0.49%) nb_accumulated 66 / 410 (finishes Sun 18:54 -- 107/h)
20240811-15:42:33 keep c_quizzes model 4 validated 2 / 410 (0.49%) nb_accumulated 68 / 410 (finishes Sun 18:52 -- 108/h)
20240811-15:43:20 keep c_quizzes model 0 validated 1 / 410 (0.24%) nb_accumulated 69 / 410 (finishes Sun 18:53 -- 107/h)
20240811-15:44:08 keep c_quizzes model 2 validated 3 / 410 (0.73%) nb_accumulated 72 / 410 (finishes Sun 18:48 -- 109/h)
20240811-15:44:56 keep c_quizzes model 1 validated 3 / 410 (0.73%) nb_accumulated 75 / 410 (finishes Sun 18:44 -- 112/h)
20240811-15:45:43 keep c_quizzes model 1 validated 3 / 410 (0.73%) nb_accumulated 78 / 410 (finishes Sun 18:40 -- 114/h)
20240811-15:46:31 keep c_quizzes model 4 validated 0 / 410 (0.00%) nb_accumulated 78 / 410 (finishes Sun 18:44 -- 112/h)
20240811-15:47:19 keep c_quizzes model 3 validated 2 / 410 (0.49%) nb_accumulated 80 / 410 (finishes Sun 18:42 -- 112/h)
20240811-15:48:06 keep c_quizzes model 0 validated 0 / 410 (0.00%) nb_accumulated 80 / 410 (finishes Sun 18:46 -- 110/h)
20240811-15:48:54 keep c_quizzes model 1 validated 2 / 410 (0.49%) nb_accumulated 82 / 410 (finishes Sun 18:45 -- 111/h)
20240811-15:49:42 keep c_quizzes model 2 validated 1 / 410 (0.24%) nb_accumulated 83 / 410 (finishes Sun 18:46 -- 110/h)
20240811-15:50:30 keep c_quizzes model 0 validated 2 / 410 (0.49%) nb_accumulated 85 / 410 (finishes Sun 18:45 -- 111/h)
20240811-15:51:17 keep c_quizzes model 4 validated 4 / 410 (0.98%) nb_accumulated 89 / 410 (finishes Sun 18:39 -- 114/h)
20240811-15:52:05 keep c_quizzes model 1 validated 1 / 410 (0.24%) nb_accumulated 90 / 410 (finishes Sun 18:40 -- 114/h)
20240811-15:52:53 keep c_quizzes model 4 validated 0 / 410 (0.00%) nb_accumulated 90 / 410 (finishes Sun 18:43 -- 112/h)
20240811-15:53:40 keep c_quizzes model 1 validated 0 / 410 (0.00%) nb_accumulated 90 / 410 (finishes Sun 18:47 -- 110/h)
20240811-15:54:28 keep c_quizzes model 3 validated 0 / 410 (0.00%) nb_accumulated 90 / 410 (finishes Sun 18:51 -- 108/h)
20240811-15:55:16 keep c_quizzes model 0 validated 3 / 410 (0.73%) nb_accumulated 93 / 410 (finishes Sun 18:47 -- 110/h)
20240811-15:56:03 keep c_quizzes model 4 validated 1 / 410 (0.24%) nb_accumulated 94 / 410 (finishes Sun 18:48 -- 109/h)
20240811-15:56:51 keep c_quizzes model 3 validated 2 / 410 (0.49%) nb_accumulated 96 / 410 (finishes Sun 18:47 -- 110/h)
20240811-15:57:39 keep c_quizzes model 1 validated 2 / 410 (0.49%) nb_accumulated 98 / 410 (finishes Sun 18:46 -- 111/h)
20240811-15:58:26 keep c_quizzes model 1 validated 2 / 410 (0.49%) nb_accumulated 100 / 410 (finishes Sun 18:44 -- 111/h)
20240811-15:59:14 keep c_quizzes model 1 validated 2 / 410 (0.49%) nb_accumulated 102 / 410 (finishes Sun 18:43 -- 112/h)
20240811-16:00:02 keep c_quizzes model 2 validated 0 / 410 (0.00%) nb_accumulated 102 / 410 (finishes Sun 18:46 -- 110/h)
20240811-16:00:50 keep c_quizzes model 4 validated 1 / 410 (0.24%) nb_accumulated 103 / 410 (finishes Sun 18:47 -- 110/h)
20240811-16:01:37 keep c_quizzes model 3 validated 2 / 410 (0.49%) nb_accumulated 105 / 410 (finishes Sun 18:46 -- 110/h)
20240811-16:02:25 keep c_quizzes model 2 validated 0 / 410 (0.00%) nb_accumulated 105 / 410 (finishes Sun 18:49 -- 109/h)
20240811-16:03:13 keep c_quizzes model 3 validated 3 / 410 (0.73%) nb_accumulated 108 / 410 (finishes Sun 18:46 -- 110/h)
20240811-16:04:00 keep c_quizzes model 3 validated 1 / 410 (0.24%) nb_accumulated 109 / 410 (finishes Sun 18:47 -- 110/h)
20240811-16:04:48 keep c_quizzes model 3 validated 0 / 410 (0.00%) nb_accumulated 109 / 410 (finishes Sun 18:50 -- 108/h)
20240811-16:05:36 keep c_quizzes model 1 validated 0 / 410 (0.00%) nb_accumulated 109 / 410 (finishes Sun 18:53 -- 107/h)
20240811-16:06:23 keep c_quizzes model 4 validated 1 / 410 (0.24%) nb_accumulated 110 / 410 (finishes Sun 18:54 -- 107/h)
20240811-16:07:11 keep c_quizzes model 3 validated 2 / 410 (0.49%) nb_accumulated 112 / 410 (finishes Sun 18:53 -- 107/h)
20240811-16:07:59 keep c_quizzes model 4 validated 5 / 410 (1.22%) nb_accumulated 117 / 410 (finishes Sun 18:46 -- 111/h)
20240811-16:08:47 keep c_quizzes model 3 validated 2 / 410 (0.49%) nb_accumulated 119 / 410 (finishes Sun 18:45 -- 111/h)
20240811-16:09:34 keep c_quizzes model 0 validated 1 / 410 (0.24%) nb_accumulated 120 / 410 (finishes Sun 18:46 -- 111/h)
20240811-16:10:22 keep c_quizzes model 2 validated 0 / 410 (0.00%) nb_accumulated 120 / 410 (finishes Sun 18:48 -- 109/h)
20240811-16:11:10 keep c_quizzes model 4 validated 2 / 410 (0.49%) nb_accumulated 122 / 410 (finishes Sun 18:47 -- 110/h)
20240811-16:11:57 keep c_quizzes model 0 validated 0 / 410 (0.00%) nb_accumulated 122 / 410 (finishes Sun 18:50 -- 108/h)
20240811-16:12:45 keep c_quizzes model 3 validated 1 / 410 (0.24%) nb_accumulated 123 / 410 (finishes Sun 18:51 -- 108/h)
20240811-16:13:33 keep c_quizzes model 2 validated 2 / 410 (0.49%) nb_accumulated 125 / 410 (finishes Sun 18:50 -- 109/h)
20240811-16:14:20 keep c_quizzes model 2 validated 1 / 410 (0.24%) nb_accumulated 126 / 410 (finishes Sun 18:51 -- 108/h)
20240811-16:15:08 keep c_quizzes model 2 validated 2 / 410 (0.49%) nb_accumulated 128 / 410 (finishes Sun 18:50 -- 109/h)
20240811-16:15:56 keep c_quizzes model 0 validated 0 / 410 (0.00%) nb_accumulated 128 / 410 (finishes Sun 18:52 -- 107/h)
20240811-16:16:44 keep c_quizzes model 1 validated 1 / 410 (0.24%) nb_accumulated 129 / 410 (finishes Sun 18:53 -- 107/h)
20240811-16:17:31 keep c_quizzes model 1 validated 1 / 410 (0.24%) nb_accumulated 130 / 410 (finishes Sun 18:54 -- 107/h)
20240811-16:18:19 keep c_quizzes model 1 validated 5 / 410 (1.22%) nb_accumulated 135 / 410 (finishes Sun 18:48 -- 110/h)
20240811-16:19:07 keep c_quizzes model 2 validated 2 / 410 (0.49%) nb_accumulated 137 / 410 (finishes Sun 18:47 -- 110/h)
20240811-16:19:55 keep c_quizzes model 3 validated 2 / 410 (0.49%) nb_accumulated 139 / 410 (finishes Sun 18:46 -- 110/h)
20240811-16:20:42 keep c_quizzes model 2 validated 3 / 410 (0.73%) nb_accumulated 142 / 410 (finishes Sun 18:44 -- 112/h)
20240811-16:21:30 keep c_quizzes model 1 validated 1 / 410 (0.24%) nb_accumulated 143 / 410 (finishes Sun 18:44 -- 111/h)
20240811-16:22:18 keep c_quizzes model 4 validated 4 / 410 (0.98%) nb_accumulated 147 / 410 (finishes Sun 18:41 -- 113/h)
20240811-16:23:05 keep c_quizzes model 3 validated 2 / 410 (0.49%) nb_accumulated 149 / 410 (finishes Sun 18:40 -- 114/h)
20240811-16:23:53 keep c_quizzes model 1 validated 2 / 410 (0.49%) nb_accumulated 151 / 410 (finishes Sun 18:39 -- 114/h)
20240811-16:24:41 keep c_quizzes model 4 validated 4 / 410 (0.98%) nb_accumulated 155 / 410 (finishes Sun 18:36 -- 116/h)
20240811-16:25:29 keep c_quizzes model 2 validated 2 / 410 (0.49%) nb_accumulated 157 / 410 (finishes Sun 18:35 -- 116/h)
20240811-16:26:17 keep c_quizzes model 4 validated 0 / 410 (0.00%) nb_accumulated 157 / 410 (finishes Sun 18:37 -- 115/h)
20240811-16:27:04 keep c_quizzes model 0 validated 2 / 410 (0.49%) nb_accumulated 159 / 410 (finishes Sun 18:37 -- 115/h)
20240811-16:27:52 keep c_quizzes model 2 validated 3 / 410 (0.73%) nb_accumulated 162 / 410 (finishes Sun 18:35 -- 116/h)
20240811-16:28:40 keep c_quizzes model 0 validated 0 / 410 (0.00%) nb_accumulated 162 / 410 (finishes Sun 18:37 -- 115/h)
20240811-16:29:28 keep c_quizzes model 1 validated 1 / 410 (0.24%) nb_accumulated 163 / 410 (finishes Sun 18:37 -- 115/h)
20240811-16:30:16 keep c_quizzes model 0 validated 1 / 410 (0.24%) nb_accumulated 164 / 410 (finishes Sun 18:38 -- 115/h)
20240811-16:31:03 keep c_quizzes model 0 validated 2 / 410 (0.49%) nb_accumulated 166 / 410 (finishes Sun 18:37 -- 115/h)
20240811-16:31:51 keep c_quizzes model 1 validated 3 / 410 (0.73%) nb_accumulated 169 / 410 (finishes Sun 18:36 -- 116/h)
20240811-16:32:39 keep c_quizzes model 3 validated 4 / 410 (0.98%) nb_accumulated 173 / 410 (finishes Sun 18:33 -- 118/h)
20240811-16:33:27 keep c_quizzes model 1 validated 2 / 410 (0.49%) nb_accumulated 175 / 410 (finishes Sun 18:32 -- 118/h)
20240811-16:34:15 keep c_quizzes model 3 validated 4 / 410 (0.98%) nb_accumulated 179 / 410 (finishes Sun 18:29 -- 120/h)
20240811-16:35:02 keep c_quizzes model 3 validated 1 / 410 (0.24%) nb_accumulated 180 / 410 (finishes Sun 18:30 -- 119/h)
20240811-16:35:50 keep c_quizzes model 0 validated 2 / 410 (0.49%) nb_accumulated 182 / 410 (finishes Sun 18:29 -- 119/h)
20240811-16:36:38 keep c_quizzes model 4 validated 2 / 410 (0.49%) nb_accumulated 184 / 410 (finishes Sun 18:29 -- 120/h)
20240811-16:37:25 keep c_quizzes model 3 validated 0 / 410 (0.00%) nb_accumulated 184 / 410 (finishes Sun 18:31 -- 119/h)
20240811-16:38:13 keep c_quizzes model 1 validated 2 / 410 (0.49%) nb_accumulated 186 / 410 (finishes Sun 18:30 -- 119/h)
20240811-16:39:01 keep c_quizzes model 0 validated 2 / 410 (0.49%) nb_accumulated 188 / 410 (finishes Sun 18:30 -- 119/h)
20240811-16:39:48 keep c_quizzes model 4 validated 0 / 410 (0.00%) nb_accumulated 188 / 410 (finishes Sun 18:32 -- 118/h)
20240811-16:40:36 keep c_quizzes model 4 validated 2 / 410 (0.49%) nb_accumulated 190 / 410 (finishes Sun 18:31 -- 118/h)
20240811-16:41:24 keep c_quizzes model 2 validated 5 / 410 (1.22%) nb_accumulated 195 / 410 (finishes Sun 18:27 -- 121/h)
20240811-16:42:11 keep c_quizzes model 0 validated 2 / 410 (0.49%) nb_accumulated 197 / 410 (finishes Sun 18:27 -- 121/h)
20240811-16:42:59 keep c_quizzes model 2 validated 0 / 410 (0.00%) nb_accumulated 197 / 410 (finishes Sun 18:29 -- 120/h)
20240811-16:43:47 keep c_quizzes model 3 validated 3 / 410 (0.73%) nb_accumulated 200 / 410 (finishes Sun 18:27 -- 121/h)
20240811-16:44:35 keep c_quizzes model 2 validated 2 / 410 (0.49%) nb_accumulated 202 / 410 (finishes Sun 18:27 -- 121/h)
20240811-16:45:22 keep c_quizzes model 4 validated 4 / 410 (0.98%) nb_accumulated 206 / 410 (finishes Sun 18:25 -- 122/h)
20240811-16:46:10 keep c_quizzes model 0 validated 2 / 410 (0.49%) nb_accumulated 208 / 410 (finishes Sun 18:24 -- 123/h)
20240811-16:46:58 keep c_quizzes model 1 validated 1 / 410 (0.24%) nb_accumulated 209 / 410 (finishes Sun 18:25 -- 122/h)
20240811-16:47:45 keep c_quizzes model 2 validated 1 / 410 (0.24%) nb_accumulated 210 / 410 (finishes Sun 18:25 -- 122/h)
20240811-16:48:33 keep c_quizzes model 3 validated 1 / 410 (0.24%) nb_accumulated 211 / 410 (finishes Sun 18:26 -- 121/h)
20240811-16:49:21 keep c_quizzes model 1 validated 4 / 410 (0.98%) nb_accumulated 215 / 410 (finishes Sun 18:24 -- 123/h)
20240811-16:50:08 keep c_quizzes model 0 validated 2 / 410 (0.49%) nb_accumulated 217 / 410 (finishes Sun 18:23 -- 123/h)
20240811-16:50:56 keep c_quizzes model 0 validated 1 / 410 (0.24%) nb_accumulated 218 / 410 (finishes Sun 18:24 -- 123/h)
20240811-16:51:44 keep c_quizzes model 1 validated 3 / 410 (0.73%) nb_accumulated 221 / 410 (finishes Sun 18:23 -- 123/h)
20240811-16:52:31 keep c_quizzes model 0 validated 1 / 410 (0.24%) nb_accumulated 222 / 410 (finishes Sun 18:23 -- 123/h)
20240811-16:53:19 keep c_quizzes model 0 validated 2 / 410 (0.49%) nb_accumulated 224 / 410 (finishes Sun 18:23 -- 123/h)
20240811-16:54:07 keep c_quizzes model 0 validated 2 / 410 (0.49%) nb_accumulated 226 / 410 (finishes Sun 18:23 -- 124/h)
20240811-16:54:55 keep c_quizzes model 2 validated 1 / 410 (0.24%) nb_accumulated 227 / 410 (finishes Sun 18:23 -- 123/h)
20240811-16:55:42 keep c_quizzes model 0 validated 1 / 410 (0.24%) nb_accumulated 228 / 410 (finishes Sun 18:24 -- 123/h)
20240811-16:56:30 keep c_quizzes model 3 validated 2 / 410 (0.49%) nb_accumulated 230 / 410 (finishes Sun 18:23 -- 123/h)
20240811-16:57:18 keep c_quizzes model 1 validated 0 / 410 (0.00%) nb_accumulated 230 / 410 (finishes Sun 18:25 -- 122/h)
20240811-16:58:06 keep c_quizzes model 1 validated 2 / 410 (0.49%) nb_accumulated 232 / 410 (finishes Sun 18:25 -- 122/h)
20240811-16:58:53 keep c_quizzes model 1 validated 0 / 410 (0.00%) nb_accumulated 232 / 410 (finishes Sun 18:26 -- 121/h)
20240811-16:59:41 keep c_quizzes model 4 validated 2 / 410 (0.49%) nb_accumulated 234 / 410 (finishes Sun 18:26 -- 122/h)
20240811-17:00:28 keep c_quizzes model 0 validated 2 / 410 (0.49%) nb_accumulated 236 / 410 (finishes Sun 18:25 -- 122/h)
20240811-17:01:16 keep c_quizzes model 2 validated 1 / 410 (0.24%) nb_accumulated 237 / 410 (finishes Sun 18:26 -- 122/h)
20240811-17:02:04 keep c_quizzes model 3 validated 0 / 410 (0.00%) nb_accumulated 237 / 410 (finishes Sun 18:27 -- 121/h)
20240811-17:02:51 keep c_quizzes model 4 validated 1 / 410 (0.24%) nb_accumulated 238 / 410 (finishes Sun 18:28 -- 120/h)
20240811-17:03:39 keep c_quizzes model 0 validated 1 / 410 (0.24%) nb_accumulated 239 / 410 (finishes Sun 18:28 -- 120/h)
20240811-17:04:27 keep c_quizzes model 1 validated 1 / 410 (0.24%) nb_accumulated 240 / 410 (finishes Sun 18:29 -- 120/h)
20240811-17:05:14 keep c_quizzes model 0 validated 1 / 410 (0.24%) nb_accumulated 241 / 410 (finishes Sun 18:29 -- 120/h)
20240811-17:06:02 keep c_quizzes model 3 validated 2 / 410 (0.49%) nb_accumulated 243 / 410 (finishes Sun 18:29 -- 120/h)
20240811-17:06:50 keep c_quizzes model 3 validated 2 / 410 (0.49%) nb_accumulated 245 / 410 (finishes Sun 18:29 -- 120/h)
20240811-17:07:38 keep c_quizzes model 3 validated 1 / 410 (0.24%) nb_accumulated 246 / 410 (finishes Sun 18:29 -- 120/h)
20240811-17:08:26 keep c_quizzes model 2 validated 1 / 410 (0.24%) nb_accumulated 247 / 410 (finishes Sun 18:30 -- 119/h)
20240811-17:09:13 keep c_quizzes model 3 validated 2 / 410 (0.49%) nb_accumulated 249 / 410 (finishes Sun 18:29 -- 120/h)
20240811-17:10:01 keep c_quizzes model 3 validated 2 / 410 (0.49%) nb_accumulated 251 / 410 (finishes Sun 18:29 -- 120/h)
20240811-17:10:49 keep c_quizzes model 4 validated 2 / 410 (0.49%) nb_accumulated 253 / 410 (finishes Sun 18:29 -- 120/h)
20240811-17:11:37 keep c_quizzes model 2 validated 0 / 410 (0.00%) nb_accumulated 253 / 410 (finishes Sun 18:30 -- 119/h)
20240811-17:12:24 keep c_quizzes model 1 validated 3 / 410 (0.73%) nb_accumulated 256 / 410 (finishes Sun 18:29 -- 120/h)
20240811-17:13:12 keep c_quizzes model 3 validated 1 / 410 (0.24%) nb_accumulated 257 / 410 (finishes Sun 18:29 -- 120/h)
20240811-17:14:00 keep c_quizzes model 3 validated 0 / 410 (0.00%) nb_accumulated 257 / 410 (finishes Sun 18:30 -- 119/h)
20240811-17:14:48 keep c_quizzes model 2 validated 1 / 410 (0.24%) nb_accumulated 258 / 410 (finishes Sun 18:31 -- 119/h)
20240811-17:15:36 keep c_quizzes model 1 validated 2 / 410 (0.49%) nb_accumulated 260 / 410 (finishes Sun 18:31 -- 119/h)
20240811-17:16:23 keep c_quizzes model 4 validated 0 / 410 (0.00%) nb_accumulated 260 / 410 (finishes Sun 18:32 -- 118/h)
20240811-17:17:11 keep c_quizzes model 3 validated 2 / 410 (0.49%) nb_accumulated 262 / 410 (finishes Sun 18:31 -- 118/h)
20240811-17:17:59 keep c_quizzes model 3 validated 1 / 410 (0.24%) nb_accumulated 263 / 410 (finishes Sun 18:32 -- 118/h)
20240811-17:18:46 keep c_quizzes model 4 validated 0 / 410 (0.00%) nb_accumulated 263 / 410 (finishes Sun 18:33 -- 117/h)
20240811-17:19:34 keep c_quizzes model 4 validated 4 / 410 (0.98%) nb_accumulated 267 / 410 (finishes Sun 18:31 -- 118/h)
20240811-17:20:22 keep c_quizzes model 3 validated 4 / 410 (0.98%) nb_accumulated 271 / 410 (finishes Sun 18:29 -- 119/h)
20240811-17:21:10 keep c_quizzes model 3 validated 1 / 410 (0.24%) nb_accumulated 272 / 410 (finishes Sun 18:30 -- 119/h)
20240811-17:21:57 keep c_quizzes model 3 validated 0 / 410 (0.00%) nb_accumulated 272 / 410 (finishes Sun 18:31 -- 118/h)
20240811-17:22:45 keep c_quizzes model 0 validated 0 / 410 (0.00%) nb_accumulated 272 / 410 (finishes Sun 18:32 -- 118/h)
20240811-17:23:32 keep c_quizzes model 4 validated 3 / 410 (0.73%) nb_accumulated 275 / 410 (finishes Sun 18:31 -- 118/h)
20240811-17:24:20 keep c_quizzes model 4 validated 0 / 410 (0.00%) nb_accumulated 275 / 410 (finishes Sun 18:32 -- 118/h)
20240811-17:25:08 keep c_quizzes model 1 validated 3 / 410 (0.73%) nb_accumulated 278 / 410 (finishes Sun 18:31 -- 118/h)
20240811-17:25:56 keep c_quizzes model 0 validated 3 / 410 (0.73%) nb_accumulated 281 / 410 (finishes Sun 18:30 -- 119/h)
20240811-17:26:43 keep c_quizzes model 4 validated 1 / 410 (0.24%) nb_accumulated 282 / 410 (finishes Sun 18:31 -- 119/h)
20240811-17:27:31 keep c_quizzes model 1 validated 2 / 410 (0.49%) nb_accumulated 284 / 410 (finishes Sun 18:30 -- 119/h)
20240811-17:28:19 keep c_quizzes model 1 validated 0 / 410 (0.00%) nb_accumulated 284 / 410 (finishes Sun 18:32 -- 118/h)
20240811-17:29:07 keep c_quizzes model 2 validated 2 / 410 (0.49%) nb_accumulated 286 / 410 (finishes Sun 18:31 -- 118/h)
20240811-17:29:55 keep c_quizzes model 1 validated 1 / 410 (0.24%) nb_accumulated 287 / 410 (finishes Sun 18:32 -- 118/h)
20240811-17:30:42 keep c_quizzes model 4 validated 1 / 410 (0.24%) nb_accumulated 288 / 410 (finishes Sun 18:32 -- 118/h)
20240811-17:31:30 keep c_quizzes model 3 validated 0 / 410 (0.00%) nb_accumulated 288 / 410 (finishes Sun 18:33 -- 117/h)
20240811-17:32:18 keep c_quizzes model 2 validated 2 / 410 (0.49%) nb_accumulated 290 / 410 (finishes Sun 18:33 -- 117/h)
20240811-17:33:06 keep c_quizzes model 2 validated 3 / 410 (0.73%) nb_accumulated 293 / 410 (finishes Sun 18:32 -- 118/h)
20240811-17:33:53 keep c_quizzes model 1 validated 1 / 410 (0.24%) nb_accumulated 294 / 410 (finishes Sun 18:32 -- 118/h)
20240811-17:34:41 keep c_quizzes model 2 validated 1 / 410 (0.24%) nb_accumulated 295 / 410 (finishes Sun 18:33 -- 118/h)
20240811-17:35:29 keep c_quizzes model 0 validated 0 / 410 (0.00%) nb_accumulated 295 / 410 (finishes Sun 18:34 -- 117/h)
20240811-17:36:16 keep c_quizzes model 2 validated 1 / 410 (0.24%) nb_accumulated 296 / 410 (finishes Sun 18:34 -- 117/h)
20240811-17:37:04 keep c_quizzes model 4 validated 2 / 410 (0.49%) nb_accumulated 298 / 410 (finishes Sun 18:34 -- 117/h)
20240811-17:37:52 keep c_quizzes model 4 validated 0 / 410 (0.00%) nb_accumulated 298 / 410 (finishes Sun 18:35 -- 116/h)
20240811-17:38:40 keep c_quizzes model 4 validated 2 / 410 (0.49%) nb_accumulated 300 / 410 (finishes Sun 18:35 -- 116/h)
20240811-17:39:27 keep c_quizzes model 2 validated 7 / 410 (1.71%) nb_accumulated 307 / 410 (finishes Sun 18:31 -- 119/h)
20240811-17:40:15 keep c_quizzes model 0 validated 2 / 410 (0.49%) nb_accumulated 309 / 410 (finishes Sun 18:31 -- 119/h)
20240811-17:41:03 keep c_quizzes model 3 validated 1 / 410 (0.24%) nb_accumulated 310 / 410 (finishes Sun 18:31 -- 119/h)
20240811-17:41:51 keep c_quizzes model 2 validated 3 / 410 (0.73%) nb_accumulated 313 / 410 (finishes Sun 18:30 -- 119/h)
20240811-17:42:38 keep c_quizzes model 1 validated 0 / 410 (0.00%) nb_accumulated 313 / 410 (finishes Sun 18:31 -- 118/h)
20240811-17:43:26 keep c_quizzes model 1 validated 2 / 410 (0.49%) nb_accumulated 315 / 410 (finishes Sun 18:31 -- 119/h)
20240811-17:44:14 keep c_quizzes model 1 validated 1 / 410 (0.24%) nb_accumulated 316 / 410 (finishes Sun 18:31 -- 118/h)
20240811-17:45:01 keep c_quizzes model 1 validated 2 / 410 (0.49%) nb_accumulated 318 / 410 (finishes Sun 18:31 -- 119/h)
20240811-17:45:49 keep c_quizzes model 3 validated 1 / 410 (0.24%) nb_accumulated 319 / 410 (finishes Sun 18:31 -- 118/h)
20240811-17:46:37 keep c_quizzes model 0 validated 1 / 410 (0.24%) nb_accumulated 320 / 410 (finishes Sun 18:32 -- 118/h)
20240811-17:47:25 keep c_quizzes model 1 validated 2 / 410 (0.49%) nb_accumulated 322 / 410 (finishes Sun 18:31 -- 118/h)
20240811-17:48:12 keep c_quizzes model 0 validated 0 / 410 (0.00%) nb_accumulated 322 / 410 (finishes Sun 18:32 -- 118/h)
20240811-17:49:00 keep c_quizzes model 4 validated 1 / 410 (0.24%) nb_accumulated 323 / 410 (finishes Sun 18:33 -- 118/h)
20240811-17:49:47 keep c_quizzes model 3 validated 2 / 410 (0.49%) nb_accumulated 325 / 410 (finishes Sun 18:32 -- 118/h)
20240811-17:50:35 keep c_quizzes model 2 validated 1 / 410 (0.24%) nb_accumulated 326 / 410 (finishes Sun 18:33 -- 117/h)
20240811-17:51:23 keep c_quizzes model 3 validated 2 / 410 (0.49%) nb_accumulated 328 / 410 (finishes Sun 18:33 -- 118/h)
20240811-17:52:11 keep c_quizzes model 2 validated 1 / 410 (0.24%) nb_accumulated 329 / 410 (finishes Sun 18:33 -- 117/h)
20240811-17:52:58 keep c_quizzes model 1 validated 4 / 410 (0.98%) nb_accumulated 333 / 410 (finishes Sun 18:31 -- 118/h)
20240811-17:53:46 keep c_quizzes model 3 validated 1 / 410 (0.24%) nb_accumulated 334 / 410 (finishes Sun 18:32 -- 118/h)
20240811-17:54:34 keep c_quizzes model 0 validated 4 / 410 (0.98%) nb_accumulated 338 / 410 (finishes Sun 18:30 -- 119/h)
20240811-17:55:22 keep c_quizzes model 2 validated 0 / 410 (0.00%) nb_accumulated 338 / 410 (finishes Sun 18:31 -- 118/h)
20240811-17:56:10 keep c_quizzes model 2 validated 4 / 410 (0.98%) nb_accumulated 342 / 410 (finishes Sun 18:30 -- 119/h)
20240811-17:56:58 keep c_quizzes model 0 validated 4 / 410 (0.98%) nb_accumulated 346 / 410 (finishes Sun 18:28 -- 120/h)
20240811-17:57:46 keep c_quizzes model 2 validated 0 / 410 (0.00%) nb_accumulated 346 / 410 (finishes Sun 18:29 -- 120/h)
20240811-17:58:34 keep c_quizzes model 3 validated 3 / 410 (0.73%) nb_accumulated 349 / 410 (finishes Sun 18:28 -- 120/h)
20240811-17:59:22 keep c_quizzes model 1 validated 2 / 410 (0.49%) nb_accumulated 351 / 410 (finishes Sun 18:28 -- 120/h)
20240811-18:00:10 keep c_quizzes model 1 validated 0 / 410 (0.00%) nb_accumulated 351 / 410 (finishes Sun 18:29 -- 120/h)
20240811-18:00:57 keep c_quizzes model 1 validated 3 / 410 (0.73%) nb_accumulated 354 / 410 (finishes Sun 18:28 -- 120/h)
20240811-18:01:45 keep c_quizzes model 0 validated 0 / 410 (0.00%) nb_accumulated 354 / 410 (finishes Sun 18:29 -- 120/h)
20240811-18:02:33 keep c_quizzes model 4 validated 1 / 410 (0.24%) nb_accumulated 355 / 410 (finishes Sun 18:30 -- 119/h)
20240811-18:03:21 keep c_quizzes model 3 validated 0 / 410 (0.00%) nb_accumulated 355 / 410 (finishes Sun 18:31 -- 119/h)
20240811-18:04:09 keep c_quizzes model 2 validated 2 / 410 (0.49%) nb_accumulated 357 / 410 (finishes Sun 18:30 -- 119/h)
20240811-18:04:56 keep c_quizzes model 3 validated 2 / 410 (0.49%) nb_accumulated 359 / 410 (finishes Sun 18:30 -- 119/h)
20240811-18:05:44 keep c_quizzes model 1 validated 2 / 410 (0.49%) nb_accumulated 361 / 410 (finishes Sun 18:30 -- 119/h)
20240811-18:06:32 keep c_quizzes model 0 validated 1 / 410 (0.24%) nb_accumulated 362 / 410 (finishes Sun 18:30 -- 119/h)
20240811-18:07:20 keep c_quizzes model 2 validated 2 / 410 (0.49%) nb_accumulated 364 / 410 (finishes Sun 18:30 -- 119/h)
20240811-18:08:08 keep c_quizzes model 3 validated 3 / 410 (0.73%) nb_accumulated 367 / 410 (finishes Sun 18:29 -- 120/h)
20240811-18:08:56 keep c_quizzes model 0 validated 1 / 410 (0.24%) nb_accumulated 368 / 410 (finishes Sun 18:29 -- 119/h)
20240811-18:09:43 keep c_quizzes model 2 validated 2 / 410 (0.49%) nb_accumulated 370 / 410 (finishes Sun 18:29 -- 120/h)
20240811-18:10:31 keep c_quizzes model 4 validated 2 / 410 (0.49%) nb_accumulated 372 / 410 (finishes Sun 18:29 -- 120/h)
20240811-18:11:19 keep c_quizzes model 0 validated 0 / 410 (0.00%) nb_accumulated 372 / 410 (finishes Sun 18:30 -- 119/h)
20240811-18:12:07 keep c_quizzes model 0 validated 4 / 410 (0.98%) nb_accumulated 376 / 410 (finishes Sun 18:29 -- 120/h)
20240811-18:12:55 keep c_quizzes model 4 validated 2 / 410 (0.49%) nb_accumulated 378 / 410 (finishes Sun 18:28 -- 120/h)
20240811-18:13:43 keep c_quizzes model 4 validated 0 / 410 (0.00%) nb_accumulated 378 / 410 (finishes Sun 18:29 -- 120/h)
20240811-18:14:31 keep c_quizzes model 3 validated 0 / 410 (0.00%) nb_accumulated 378 / 410 (finishes Sun 18:30 -- 119/h)
20240811-18:15:19 keep c_quizzes model 3 validated 4 / 410 (0.98%) nb_accumulated 382 / 410 (finishes Sun 18:29 -- 120/h)
20240811-18:16:07 keep c_quizzes model 0 validated 3 / 410 (0.73%) nb_accumulated 385 / 410 (finishes Sun 18:28 -- 120/h)
20240811-18:16:54 keep c_quizzes model 0 validated 2 / 410 (0.49%) nb_accumulated 387 / 410 (finishes Sun 18:28 -- 120/h)
20240811-18:17:42 keep c_quizzes model 2 validated 1 / 410 (0.24%) nb_accumulated 388 / 410 (finishes Sun 18:28 -- 120/h)
20240811-18:18:30 keep c_quizzes model 2 validated 0 / 410 (0.00%) nb_accumulated 388 / 410 (finishes Sun 18:29 -- 120/h)
20240811-18:19:17 keep c_quizzes model 4 validated 0 / 410 (0.00%) nb_accumulated 388 / 410 (finishes Sun 18:30 -- 119/h)
20240811-18:20:05 keep c_quizzes model 0 validated 0 / 410 (0.00%) nb_accumulated 388 / 410 (finishes Sun 18:31 -- 119/h)
20240811-18:20:53 keep c_quizzes model 1 validated 2 / 410 (0.49%) nb_accumulated 390 / 410 (finishes Sun 18:30 -- 119/h)
20240811-18:21:41 keep c_quizzes model 1 validated 0 / 410 (0.00%) nb_accumulated 390 / 410 (finishes Sun 18:31 -- 118/h)
20240811-18:22:29 keep c_quizzes model 3 validated 2 / 410 (0.49%) nb_accumulated 392 / 410 (finishes Sun 18:31 -- 118/h)
20240811-18:23:16 keep c_quizzes model 2 validated 3 / 410 (0.73%) nb_accumulated 395 / 410 (finishes Sun 18:30 -- 119/h)
20240811-18:24:04 keep c_quizzes model 2 validated 0 / 410 (0.00%) nb_accumulated 395 / 410 (finishes Sun 18:31 -- 118/h)
20240811-18:24:52 keep c_quizzes model 1 validated 0 / 410 (0.00%) nb_accumulated 395 / 410 (finishes Sun 18:32 -- 118/h)
20240811-18:25:40 keep c_quizzes model 4 validated 1 / 410 (0.24%) nb_accumulated 396 / 410 (finishes Sun 18:32 -- 118/h)
20240811-18:26:28 keep c_quizzes model 3 validated 1 / 410 (0.24%) nb_accumulated 397 / 410 (finishes Sun 18:33 -- 118/h)
20240811-18:27:16 keep c_quizzes model 3 validated 1 / 410 (0.24%) nb_accumulated 398 / 410 (finishes Sun 18:33 -- 117/h)
20240811-18:28:03 keep c_quizzes model 0 validated 0 / 410 (0.00%) nb_accumulated 398 / 410 (finishes Sun 18:34 -- 117/h)
20240811-18:28:51 keep c_quizzes model 2 validated 1 / 410 (0.24%) nb_accumulated 399 / 410 (finishes Sun 18:34 -- 117/h)
20240811-18:29:39 keep c_quizzes model 0 validated 1 / 410 (0.24%) nb_accumulated 400 / 410 (finishes Sun 18:34 -- 117/h)
20240811-18:30:27 keep c_quizzes model 1 validated 2 / 410 (0.49%) nb_accumulated 402 / 410 (finishes Sun 18:34 -- 117/h)
20240811-18:31:14 keep c_quizzes model 1 validated 4 / 410 (0.98%) nb_accumulated 406 / 410 (finishes Sun 18:33 -- 117/h)
20240811-18:32:02 keep c_quizzes model 1 validated 0 / 410 (0.00%) nb_accumulated 406 / 410 (finishes Sun 18:34 -- 117/h)
20240811-18:32:50 keep c_quizzes model 1 validated 1 / 410 (0.24%) nb_accumulated 407 / 410 (finishes Sun 18:34 -- 117/h)
20240811-18:33:38 keep c_quizzes model 2 validated 7 / 410 (1.71%) nb_accumulated 414 / 410 (finishes now! -- 118/h)
20240811-18:33:41 wrote c_quizzes.pth
20240811-18:33:41 training model 0
20240811-18:33:41 training model 1
20240811-18:37:26 train_perplexity 53 model 0 1.1474544016981203
20240811-18:37:26 train_perplexity 53 model 1 1.1482292102427907
20240811-18:37:30 test_perplexity 53 model 0 1.1483183634063734
20240811-18:37:30 test_perplexity 53 model 1 1.1463821004253498
20240811-18:38:52 argv ./main.py --result_dir=results_culture_ref --resume --seed=123
20240811-18:38:52 args.log_filename train.log
20240811-18:38:52 args.result_dir results_culture_ref
20240811-18:38:52 args.seed 123
20240811-18:38:52 args.resume True
20240811-18:38:52 args.max_percents_of_test_in_train -1
20240811-18:38:52 args.log_command None
20240811-18:38:52 args.nb_epochs 10000
20240811-18:38:52 args.batch_size 25
20240811-18:38:52 args.physical_batch_size None
20240811-18:38:52 args.inference_batch_size 50
20240811-18:38:52 args.nb_train_samples 40000
20240811-18:38:52 args.nb_test_samples 1000
20240811-18:38:52 args.nb_new_c_quizzes_for_train None
20240811-18:38:52 args.nb_new_c_quizzes_for_test None
20240811-18:38:52 args.learning_rate 0.0005
20240811-18:38:52 args.schedule_free False
20240811-18:38:52 args.model 37M
20240811-18:38:52 args.dim_model 512
20240811-18:38:52 args.dim_keys 64
20240811-18:38:52 args.dim_hidden 2048
20240811-18:38:52 args.nb_heads 8
20240811-18:38:52 args.nb_blocks 12
20240811-18:38:52 args.dropout 0.5
20240811-18:38:52 args.deterministic_synthesis False
20240811-18:38:52 args.problem grids
20240811-18:38:52 args.nb_threads 1
20240811-18:38:52 args.gpus all
20240811-18:38:52 args.nb_gpts 5
20240811-18:38:52 args.max_fail_to_validate 3
20240811-18:38:52 args.accuracy_to_make_c_quizzes 0.95
20240811-18:38:52 args.proba_understands 0.95
20240811-18:38:52 args.proba_not_understands 0.1
20240811-18:38:52 args.temperature_hot 1.5
20240811-18:38:52 args.temperature_cold 1
20240811-18:38:52 args.prompt_noise 0.05
20240811-18:38:52 args.dirty_debug False
20240811-18:38:52 args.test None
20240811-18:38:52 args.grids_world_tasks replace_color,translate,grow,frame
20240811-18:38:52 args.grids_science_tasks None
20240811-18:38:52 args.sky_height 6
20240811-18:38:52 args.sky_width 8
20240811-18:38:52 args.sky_nb_birds 3
20240811-18:38:52 args.sky_nb_iterations 2
20240811-18:38:52 args.sky_speed 3
20240811-18:38:52 main_device cuda:0 gpus ['cuda:0', 'cuda:1']
20240811-18:38:52 vocabulary_size 15
20240811-18:38:52 creating model 0 and its w_quizzes
20240811-18:39:05 creating model 1 and its w_quizzes
20240811-18:39:18 creating model 2 and its w_quizzes
20240811-18:39:32 creating model 3 and its w_quizzes
20240811-18:39:45 creating model 4 and its w_quizzes
20240811-18:39:59 successfully loaded gpt_000.pth
20240811-18:39:59 successfully loaded gpt_001.pth
20240811-18:39:59 successfully loaded gpt_002.pth
20240811-18:40:00 successfully loaded gpt_003.pth
20240811-18:40:00 successfully loaded gpt_004.pth
20240811-18:40:00 successfully loaded c_quizzes.pth
20240811-18:40:00 successfully loaded state.pth
20240811-18:40:00 nb_parameters 37819407 (37M)
20240811-18:40:00 nb_new_c_quizzes_for_train 400 nb_new_c_quizzes_for_test 10
20240811-18:40:00 wrote state.pth
20240811-18:40:00 --- epoch 53 ----------------------------------------
20240811-18:40:00 current_test_accuracies 0.9506 0.9615 0.9660 0.9641 0.9687
20240811-18:41:09 keep c_quizzes model 0 validated 34 / 410 (8.29%) nb_accumulated 34 / 410 (finishes Sun 18:53 -- 1776/h)
20240811-18:41:58 keep c_quizzes model 0 validated 38 / 410 (9.27%) nb_accumulated 72 / 410 (finishes Sun 18:51 -- 2193/h)
20240812-16:19:08 argv ./main.py --result_dir=results_culture_ref --resume --seed=124
20240812-16:19:08 args.log_filename train.log
20240812-16:19:08 args.result_dir results_culture_ref
20240812-16:19:08 args.seed 124
20240812-16:19:08 args.resume True
20240812-16:19:08 args.max_percents_of_test_in_train -1
20240812-16:19:08 args.log_command None
20240812-16:19:08 args.nb_epochs 10000
20240812-16:19:08 args.batch_size 25
20240812-16:19:08 args.physical_batch_size None
20240812-16:19:08 args.inference_batch_size 50
20240812-16:19:08 args.nb_train_samples 40000
20240812-16:19:08 args.nb_test_samples 1000
20240812-16:19:08 args.nb_new_c_quizzes_for_train None
20240812-16:19:08 args.nb_new_c_quizzes_for_test None
20240812-16:19:08 args.learning_rate 0.0005
20240812-16:19:08 args.schedule_free False
20240812-16:19:08 args.model 37M
20240812-16:19:08 args.dim_model 512
20240812-16:19:08 args.dim_keys 64
20240812-16:19:08 args.dim_hidden 2048
20240812-16:19:08 args.nb_heads 8
20240812-16:19:08 args.nb_blocks 12
20240812-16:19:08 args.dropout 0.5
20240812-16:19:08 args.deterministic_synthesis False
20240812-16:19:08 args.problem grids
20240812-16:19:08 args.nb_threads 1
20240812-16:19:08 args.gpus all
20240812-16:19:08 args.nb_gpts 5
20240812-16:19:08 args.min_succeed_to_validate 2
20240812-16:19:08 args.max_fail_to_validate 3
20240812-16:19:08 args.accuracy_to_make_c_quizzes 0.95
20240812-16:19:08 args.proba_understands 0.95
20240812-16:19:08 args.proba_not_understands 0.5
20240812-16:19:08 args.temperature_hot 1.5
20240812-16:19:08 args.temperature_cold 1
20240812-16:19:08 args.prompt_noise 0.05
20240812-16:19:08 args.dirty_debug False
20240812-16:19:08 args.test None
20240812-16:19:08 args.grids_world_tasks replace_color,translate,grow,frame
20240812-16:19:08 args.grids_science_tasks None
20240812-16:19:08 args.sky_height 6
20240812-16:19:08 args.sky_width 8
20240812-16:19:08 args.sky_nb_birds 3
20240812-16:19:08 args.sky_nb_iterations 2
20240812-16:19:08 args.sky_speed 3
20240812-16:19:08 main_device cuda:0 gpus ['cuda:0', 'cuda:1']
20240812-16:19:08 vocabulary_size 15
20240812-16:19:08 creating model 0 and its w_quizzes
20240812-16:19:22 creating model 1 and its w_quizzes
20240812-16:19:36 creating model 2 and its w_quizzes
20240812-16:19:50 creating model 3 and its w_quizzes
20240812-16:20:03 creating model 4 and its w_quizzes
20240812-16:20:17 successfully loaded gpt_000.pth
20240812-16:20:17 successfully loaded gpt_001.pth
20240812-16:20:17 successfully loaded gpt_002.pth
20240812-16:20:18 successfully loaded gpt_003.pth
20240812-16:20:18 successfully loaded gpt_004.pth
20240812-16:20:18 successfully loaded c_quizzes.pth
20240812-16:20:18 successfully loaded state.pth
20240812-16:20:18 nb_parameters 37819407 (37M)
20240812-16:20:18 nb_new_c_quizzes_for_train 400 nb_new_c_quizzes_for_test 10
20240812-16:20:18 wrote state.pth
20240812-16:20:18 --- epoch 53 ----------------------------------------
20240812-16:20:18 current_test_accuracies 0.9506 0.9615 0.9660 0.9641 0.9687
20240812-16:21:32 keep c_quizzes model 1 validated 21 / 410 (5.12%) nb_accumulated 21 / 410 (finishes Mon 16:44 -- 1019/h)
20240812-16:22:21 keep c_quizzes model 3 validated 16 / 410 (3.90%) nb_accumulated 37 / 410 (finishes Mon 16:43 -- 1078/h)
20240812-16:23:11 keep c_quizzes model 3 validated 17 / 410 (4.15%) nb_accumulated 54 / 410 (finishes Mon 16:42 -- 1124/h)
20240812-16:24:00 keep c_quizzes model 4 validated 13 / 410 (3.17%) nb_accumulated 67 / 410 (finishes Mon 16:42 -- 1085/h)
20240812-16:24:49 keep c_quizzes model 4 validated 22 / 410 (5.37%) nb_accumulated 89 / 410 (finishes Mon 16:41 -- 1180/h)
20240812-16:25:39 keep c_quizzes model 2 validated 12 / 410 (2.93%) nb_accumulated 101 / 410 (finishes Mon 16:42 -- 1132/h)
20240812-16:26:28 keep c_quizzes model 4 validated 17 / 410 (4.15%) nb_accumulated 118 / 410 (finishes Mon 16:41 -- 1146/h)
20240812-16:27:17 keep c_quizzes model 0 validated 17 / 410 (4.15%) nb_accumulated 135 / 410 (finishes Mon 16:41 -- 1158/h)
20240812-16:28:07 keep c_quizzes model 1 validated 12 / 410 (2.93%) nb_accumulated 147 / 410 (finishes Mon 16:42 -- 1128/h)
20240812-16:28:56 keep c_quizzes model 1 validated 17 / 410 (4.15%) nb_accumulated 164 / 410 (finishes Mon 16:41 -- 1139/h)
20240812-16:29:45 keep c_quizzes model 4 validated 15 / 410 (3.66%) nb_accumulated 179 / 410 (finishes Mon 16:41 -- 1135/h)
20240812-16:30:35 keep c_quizzes model 1 validated 15 / 410 (3.66%) nb_accumulated 194 / 410 (finishes Mon 16:42 -- 1132/h)
20240812-16:31:24 keep c_quizzes model 2 validated 19 / 410 (4.63%) nb_accumulated 213 / 410 (finishes Mon 16:41 -- 1150/h)
20240812-16:32:13 keep c_quizzes model 1 validated 18 / 410 (4.39%) nb_accumulated 231 / 410 (finishes Mon 16:41 -- 1162/h)
20240812-16:33:03 keep c_quizzes model 2 validated 21 / 410 (5.12%) nb_accumulated 252 / 410 (finishes Mon 16:41 -- 1185/h)
20240812-16:33:52 keep c_quizzes model 0 validated 13 / 410 (3.17%) nb_accumulated 265 / 410 (finishes Mon 16:41 -- 1171/h)
20240812-16:34:41 keep c_quizzes model 0 validated 8 / 410 (1.95%) nb_accumulated 273 / 410 (finishes Mon 16:41 -- 1138/h)
20240812-16:35:31 keep c_quizzes model 3 validated 8 / 410 (1.95%) nb_accumulated 281 / 410 (finishes Mon 16:42 -- 1108/h)
20240812-16:36:20 keep c_quizzes model 2 validated 12 / 410 (2.93%) nb_accumulated 293 / 410 (finishes Mon 16:42 -- 1096/h)
20240812-16:37:09 keep c_quizzes model 0 validated 20 / 410 (4.88%) nb_accumulated 313 / 410 (finishes Mon 16:42 -- 1113/h)
20240812-16:37:59 keep c_quizzes model 4 validated 16 / 410 (3.90%) nb_accumulated 329 / 410 (finishes Mon 16:42 -- 1116/h)
20240812-16:38:48 keep c_quizzes model 2 validated 18 / 410 (4.39%) nb_accumulated 347 / 410 (finishes Mon 16:42 -- 1124/h)
20240812-16:39:38 keep c_quizzes model 1 validated 16 / 410 (3.90%) nb_accumulated 363 / 410 (finishes Mon 16:42 -- 1126/h)
20240812-16:40:27 keep c_quizzes model 3 validated 14 / 410 (3.41%) nb_accumulated 377 / 410 (finishes Mon 16:42 -- 1122/h)
20240812-16:41:16 keep c_quizzes model 3 validated 23 / 410 (5.61%) nb_accumulated 400 / 410 (finishes Mon 16:41 -- 1144/h)
20240812-16:42:06 keep c_quizzes model 4 validated 20 / 410 (4.88%) nb_accumulated 420 / 410 (finishes now! -- 1156/h)
20240812-16:42:09 wrote c_quizzes.pth
20240812-16:42:09 training model 0
20240812-16:42:09 training model 1
20240812-16:45:54 train_perplexity 53 model 0 1.1669679473616248
20240812-16:45:54 train_perplexity 53 model 1 1.168363392918749
20240812-16:45:57 test_perplexity 53 model 0 1.1483573001357044
20240812-16:45:58 test_perplexity 53 model 1 1.1490918316975125
20240812-16:46:41 test_accuracy 53 model 0 val 729 / 805
20240812-16:46:43 test_accuracy 53 model 1 val 764 / 817
20240812-16:46:45 wrote gpt_000.pth
20240812-16:46:45 wrote gpt_001.pth
20240812-16:46:58 wrote non_validated_0053_00.png
20240812-16:47:11 wrote non_validated_0053_01.png
20240812-16:47:11 wrote state.pth
20240812-16:47:11 --- epoch 54 ----------------------------------------
20240812-16:47:11 current_test_accuracies 0.9056 0.9351 0.0000 0.0000 0.0000
20240812-16:47:11 training model 2
20240812-16:47:11 training model 3
20240812-16:50:56 train_perplexity 54 model 2 1.1667959507610504
20240812-16:50:57 train_perplexity 54 model 3 1.169126778944096
20240812-16:50:59 test_perplexity 54 model 2 1.1478063903080684
20240812-16:51:00 test_perplexity 54 model 3 1.1491466210492132
20240812-16:51:44 test_accuracy 54 model 2 val 738 / 800
20240812-16:51:44 test_accuracy 54 model 3 val 759 / 819
20240812-16:51:47 wrote gpt_002.pth
20240812-16:51:47 wrote gpt_003.pth
20240812-16:52:00 wrote non_validated_0054_02.png
20240812-16:52:13 wrote non_validated_0054_03.png
20240812-16:52:13 wrote state.pth
20240812-16:52:13 --- epoch 55 ----------------------------------------
20240812-16:52:13 current_test_accuracies 0.9056 0.9351 0.9225 0.9267 0.0000
20240812-16:52:13 training model 4
20240812-16:52:13 training model 0
20240812-16:55:57 train_perplexity 55 model 4 1.1645721546384369
20240812-16:55:59 test_perplexity 55 model 4 1.1484134078638568
20240812-16:56:01 train_perplexity 55 model 0 1.1572614312875469
20240812-16:56:03 test_perplexity 55 model 0 1.1484202343514152
20240812-16:56:45 test_accuracy 55 model 4 val 772 / 833
20240812-16:56:49 test_accuracy 55 model 0 val 726 / 781
20240812-16:56:51 wrote gpt_004.pth
20240812-16:56:51 wrote gpt_000.pth
20240812-16:57:04 wrote non_validated_0055_04.png
20240812-16:57:17 wrote non_validated_0055_00.png
20240812-16:57:17 wrote state.pth
20240812-16:57:17 --- epoch 56 ----------------------------------------
20240812-16:57:17 current_test_accuracies 0.9296 0.9351 0.9225 0.9267 0.9268
20240812-16:57:17 training model 2
20240812-16:57:17 training model 3
20240812-17:01:02 train_perplexity 56 model 2 1.1566208980427806
20240812-17:01:03 test_perplexity 56 model 2 1.1481575825596166
20240812-17:01:04 train_perplexity 56 model 3 1.1583096664086385
20240812-17:01:06 test_perplexity 56 model 3 1.1484414385836708
20240812-17:01:50 test_accuracy 56 model 2 val 735 / 793
20240812-17:01:52 test_accuracy 56 model 3 val 729 / 799
20240812-17:01:53 wrote gpt_002.pth
20240812-17:01:54 wrote gpt_003.pth
20240812-17:02:07 wrote non_validated_0056_02.png
20240812-17:02:20 wrote non_validated_0056_03.png
20240812-17:02:20 wrote state.pth
20240812-17:02:20 --- epoch 57 ----------------------------------------
20240812-17:02:20 current_test_accuracies 0.9296 0.9351 0.9269 0.9124 0.9268
20240812-17:02:20 training model 3
20240812-17:02:20 training model 4
20240812-17:06:06 train_perplexity 57 model 3 1.1560411863628695
20240812-17:06:07 train_perplexity 57 model 4 1.1556733804178763
20240812-17:06:09 test_perplexity 57 model 3 1.1485612462356314
20240812-17:06:10 test_perplexity 57 model 4 1.1458217372416288
20240812-17:06:57 test_accuracy 57 model 3 val 732 / 796
20240812-17:06:58 test_accuracy 57 model 4 val 749 / 799
20240812-17:07:00 wrote gpt_003.pth
20240812-17:07:01 wrote gpt_004.pth
20240812-17:07:14 wrote non_validated_0057_03.png
20240812-17:07:27 wrote non_validated_0057_04.png
20240812-17:07:27 wrote state.pth
20240812-17:07:27 --- epoch 58 ----------------------------------------
20240812-17:07:27 current_test_accuracies 0.9296 0.9351 0.9269 0.9196 0.9374
20240812-17:07:27 training model 3
20240812-17:07:27 training model 2
20240812-17:11:12 train_perplexity 58 model 3 1.1542653950622077
20240812-17:11:14 train_perplexity 58 model 2 1.1547393728472468
20240812-17:11:14 test_perplexity 58 model 3 1.1462180756175173
20240812-17:11:16 test_perplexity 58 model 2 1.146848743291753
20240812-17:12:00 test_accuracy 58 model 2 val 759 / 807
20240812-17:12:01 test_accuracy 58 model 3 val 762 / 809
20240812-17:12:03 wrote gpt_003.pth
20240812-17:12:03 wrote gpt_002.pth
20240812-17:12:16 wrote non_validated_0058_03.png
20240812-17:12:29 wrote non_validated_0058_02.png
20240812-17:12:29 wrote state.pth
20240812-17:12:29 --- epoch 59 ----------------------------------------
20240812-17:12:29 current_test_accuracies 0.9296 0.9351 0.9405 0.9419 0.9374
20240812-17:12:29 training model 0
20240812-17:12:29 training model 1
20240812-17:16:14 train_perplexity 59 model 0 1.15519469595863
20240812-17:16:16 train_perplexity 59 model 1 1.1572173735250835
20240812-17:16:17 test_perplexity 59 model 0 1.1483879810360866
20240812-17:16:18 test_perplexity 59 model 1 1.1472131287620233
20240812-17:17:07 test_accuracy 59 model 0 val 751 / 796
20240812-17:17:08 test_accuracy 59 model 1 val 762 / 799
20240812-17:17:10 wrote gpt_000.pth
20240812-17:17:10 wrote gpt_001.pth
20240812-17:17:23 wrote non_validated_0059_00.png
20240812-17:17:36 wrote non_validated_0059_01.png
20240812-17:17:36 wrote state.pth
20240812-17:17:36 --- epoch 60 ----------------------------------------
20240812-17:17:36 current_test_accuracies 0.9435 0.9537 0.9405 0.9419 0.9374
20240812-17:17:36 training model 4
20240812-17:17:36 training model 2
20240812-17:21:21 train_perplexity 60 model 4 1.1540258159734824
20240812-17:21:23 train_perplexity 60 model 2 1.15427144336728
20240812-17:21:23 test_perplexity 60 model 4 1.1434968787464956
20240812-17:21:25 test_perplexity 60 model 2 1.147418173447081
20240812-17:22:09 test_accuracy 60 model 2 val 766 / 814
20240812-17:22:11 test_accuracy 60 model 4 val 738 / 778
20240812-17:22:13 wrote gpt_004.pth
20240812-17:22:14 wrote gpt_002.pth
20240812-17:22:27 wrote non_validated_0060_04.png
20240812-17:22:40 wrote non_validated_0060_02.png
20240812-17:22:40 wrote state.pth
20240812-17:22:40 --- epoch 61 ----------------------------------------
20240812-17:22:40 current_test_accuracies 0.9435 0.9537 0.9410 0.9419 0.9486
20240812-17:22:40 training model 2
20240812-17:22:40 training model 3
20240812-17:26:25 train_perplexity 61 model 2 1.1531803251161452
20240812-17:26:27 train_perplexity 61 model 3 1.1539435571208951
20240812-17:26:27 test_perplexity 61 model 2 1.1450347640938832
20240812-17:26:29 test_perplexity 61 model 3 1.1459568440335615
20240812-17:27:10 test_accuracy 61 model 2 val 744 / 800
20240812-17:27:11 test_accuracy 61 model 3 val 753 / 805
20240812-17:27:13 wrote gpt_002.pth
20240812-17:27:14 wrote gpt_003.pth
20240812-17:27:27 wrote non_validated_0061_02.png
20240812-17:27:39 wrote non_validated_0061_03.png
20240812-17:27:40 wrote state.pth
20240812-17:27:40 --- epoch 62 ----------------------------------------
20240812-17:27:40 current_test_accuracies 0.9435 0.9537 0.9300 0.9354 0.9486
20240812-17:27:40 training model 2
20240812-17:27:40 training model 3
20240812-17:31:24 train_perplexity 62 model 2 1.1524433952175364
20240812-17:31:26 train_perplexity 62 model 3 1.153592625283667
20240812-17:31:27 test_perplexity 62 model 2 1.1503331279067595
20240812-17:31:28 test_perplexity 62 model 3 1.1486266291396694
20240812-17:32:12 test_accuracy 62 model 2 val 753 / 821
20240812-17:32:13 test_accuracy 62 model 3 val 754 / 800
20240812-17:32:14 wrote gpt_002.pth
20240812-17:32:15 wrote gpt_003.pth
20240812-17:32:28 wrote non_validated_0062_02.png
20240812-17:32:41 wrote non_validated_0062_03.png
20240812-17:32:41 wrote state.pth
20240812-17:32:41 --- epoch 63 ----------------------------------------
20240812-17:32:41 current_test_accuracies 0.9435 0.9537 0.9172 0.9425 0.9486
20240812-17:32:41 training model 2
20240812-17:32:41 training model 3
20240812-17:36:26 train_perplexity 63 model 2 1.1521255036825464
20240812-17:36:27 train_perplexity 63 model 3 1.1523618787054377
20240812-17:36:28 test_perplexity 63 model 2 1.1449325359762434
20240812-17:36:30 test_perplexity 63 model 3 1.1461964408241412
20240812-17:37:17 test_accuracy 63 model 3 val 749 / 791
20240812-17:37:18 test_accuracy 63 model 2 val 755 / 788
20240812-17:37:20 wrote gpt_002.pth
20240812-17:37:20 wrote gpt_003.pth
20240812-17:37:33 wrote non_validated_0063_02.png
20240812-17:37:46 wrote non_validated_0063_03.png
20240812-17:37:46 wrote state.pth
20240812-17:37:46 --- epoch 64 ----------------------------------------
20240812-17:37:46 current_test_accuracies 0.9435 0.9537 0.9581 0.9469 0.9486
20240812-17:37:46 training model 0
20240812-17:37:46 training model 3
20240812-17:41:31 train_perplexity 64 model 0 1.1540459998739605
20240812-17:41:32 train_perplexity 64 model 3 1.1519321496782806
20240812-17:41:34 test_perplexity 64 model 0 1.1457690706950059
20240812-17:41:35 test_perplexity 64 model 3 1.1472081892279566
20240812-17:42:19 test_accuracy 64 model 3 val 774 / 801
20240812-17:42:21 test_accuracy 64 model 0 val 726 / 776
20240812-17:42:23 wrote gpt_000.pth
20240812-17:42:23 wrote gpt_003.pth
20240812-17:42:36 wrote non_validated_0064_00.png
20240812-17:42:49 wrote non_validated_0064_03.png
20240812-17:42:49 wrote state.pth
20240812-17:42:49 --- epoch 65 ----------------------------------------
20240812-17:42:49 current_test_accuracies 0.9356 0.9537 0.9581 0.9663 0.9486
20240812-17:42:49 training model 0
20240812-17:42:49 training model 4
20240812-17:46:35 train_perplexity 65 model 0 1.1529227858831381
20240812-17:46:35 train_perplexity 65 model 4 1.1533889179933086
20240812-17:46:37 test_perplexity 65 model 0 1.147496507202527
20240812-17:46:39 test_perplexity 65 model 4 1.1470338169614231
20240812-17:47:25 test_accuracy 65 model 0 val 745 / 790
20240812-17:47:26 test_accuracy 65 model 4 val 721 / 769
20240812-17:47:28 wrote gpt_000.pth
20240812-17:47:28 wrote gpt_004.pth
20240812-17:47:41 wrote non_validated_0065_00.png
20240812-17:47:54 wrote non_validated_0065_04.png
20240812-17:47:54 wrote state.pth
20240812-17:47:54 --- epoch 66 ----------------------------------------
20240812-17:47:54 current_test_accuracies 0.9430 0.9537 0.9581 0.9663 0.9376
20240812-17:47:54 training model 4
20240812-17:47:54 training model 0
20240812-17:51:41 train_perplexity 66 model 4 1.1521118077496333
20240812-17:51:43 test_perplexity 66 model 4 1.1456750173762058
20240812-17:51:43 train_perplexity 66 model 0 1.152702382973359
20240812-17:51:45 test_perplexity 66 model 0 1.147621268082804
20240812-17:52:31 test_accuracy 66 model 4 val 756 / 796
20240812-17:52:33 test_accuracy 66 model 0 val 744 / 788
20240812-17:52:35 wrote gpt_004.pth
20240812-17:52:35 wrote gpt_000.pth
20240812-17:52:48 wrote non_validated_0066_04.png
20240812-17:53:01 wrote non_validated_0066_00.png
20240812-17:53:01 wrote state.pth
20240812-17:53:01 --- epoch 67 ----------------------------------------
20240812-17:53:01 current_test_accuracies 0.9442 0.9537 0.9581 0.9663 0.9497
20240812-17:53:01 training model 0
20240812-17:53:01 training model 4
20240812-17:56:45 train_perplexity 67 model 0 1.1520917141693827
20240812-17:56:47 test_perplexity 67 model 0 1.1466793592648281
20240812-17:56:48 train_perplexity 67 model 4 1.1519075469611555
20240812-17:56:50 test_perplexity 67 model 4 1.1438771570661121
20240812-17:57:32 test_accuracy 67 model 0 val 754 / 805
20240812-17:57:35 test_accuracy 67 model 4 val 729 / 771
20240812-17:57:37 wrote gpt_000.pth
20240812-17:57:38 wrote gpt_004.pth
20240812-17:57:51 wrote non_validated_0067_00.png
20240812-17:58:04 wrote non_validated_0067_04.png
20240812-17:58:04 wrote state.pth
20240812-17:58:04 --- epoch 68 ----------------------------------------
20240812-17:58:04 current_test_accuracies 0.9366 0.9537 0.9581 0.9663 0.9455
20240812-17:58:04 training model 0
20240812-17:58:04 training model 4
20240812-18:01:48 train_perplexity 68 model 0 1.1520028791983734
20240812-18:01:50 test_perplexity 68 model 0 1.1485019643321248
20240812-18:01:50 train_perplexity 68 model 4 1.151756373467768
20240812-18:01:52 test_perplexity 68 model 4 1.1459962862057762
20240812-18:02:35 test_accuracy 68 model 0 val 782 / 811
20240812-18:02:38 test_accuracy 68 model 4 val 781 / 824
20240812-18:02:39 wrote gpt_000.pth
20240812-18:02:40 wrote gpt_004.pth
20240812-18:02:53 wrote non_validated_0068_00.png
20240812-18:03:06 wrote non_validated_0068_04.png
20240812-18:03:06 wrote state.pth
20240812-18:03:06 --- epoch 69 ----------------------------------------
20240812-18:03:06 current_test_accuracies 0.9642 0.9537 0.9581 0.9663 0.9478
20240812-18:03:06 training model 4
20240812-18:03:06 training model 1
20240812-18:06:50 train_perplexity 69 model 4 1.1506704326345742
20240812-18:06:52 test_perplexity 69 model 4 1.146399001687176
20240812-18:06:53 train_perplexity 69 model 1 1.155725957807268
20240812-18:06:55 test_perplexity 69 model 1 1.1459197154573109
20240812-18:07:39 test_accuracy 69 model 1 val 780 / 804
20240812-18:07:40 test_accuracy 69 model 4 val 764 / 794
20240812-18:07:42 wrote gpt_004.pth
20240812-18:07:43 wrote gpt_001.pth
20240812-18:07:56 wrote non_validated_0069_04.png
20240812-18:08:09 wrote non_validated_0069_01.png
20240812-18:08:09 wrote state.pth
20240812-18:08:09 --- epoch 70 ----------------------------------------
20240812-18:08:09 current_test_accuracies 0.9642 0.9701 0.9581 0.9663 0.9622
20240812-18:09:19 keep c_quizzes model 1 validated 13 / 410 (3.17%) nb_accumulated 13 / 410 (finishes Mon 18:45 -- 667/h)
20240812-18:10:08 keep c_quizzes model 4 validated 13 / 410 (3.17%) nb_accumulated 26 / 410 (finishes Mon 18:39 -- 789/h)
20240812-18:10:56 keep c_quizzes model 2 validated 11 / 410 (2.68%) nb_accumulated 37 / 410 (finishes Mon 18:39 -- 797/h)
20240812-18:11:45 keep c_quizzes model 2 validated 15 / 410 (3.66%) nb_accumulated 52 / 410 (finishes Mon 18:36 -- 867/h)
20240812-18:12:34 keep c_quizzes model 4 validated 19 / 410 (4.63%) nb_accumulated 71 / 410 (finishes Mon 18:33 -- 966/h)
20240812-18:13:22 keep c_quizzes model 1 validated 13 / 410 (3.17%) nb_accumulated 84 / 410 (finishes Mon 18:33 -- 965/h)
20240812-18:14:11 keep c_quizzes model 4 validated 10 / 410 (2.44%) nb_accumulated 94 / 410 (finishes Mon 18:34 -- 934/h)
20240812-18:15:00 keep c_quizzes model 3 validated 18 / 410 (4.39%) nb_accumulated 112 / 410 (finishes Mon 18:33 -- 982/h)
20240812-18:15:48 keep c_quizzes model 1 validated 14 / 410 (3.41%) nb_accumulated 126 / 410 (finishes Mon 18:33 -- 987/h)
20240812-18:16:37 keep c_quizzes model 1 validated 21 / 410 (5.12%) nb_accumulated 147 / 410 (finishes Mon 18:31 -- 1041/h)
20240812-18:17:26 keep c_quizzes model 2 validated 11 / 410 (2.68%) nb_accumulated 158 / 410 (finishes Mon 18:32 -- 1021/h)
20240812-18:18:14 keep c_quizzes model 3 validated 11 / 410 (2.68%) nb_accumulated 169 / 410 (finishes Mon 18:32 -- 1004/h)
20240812-18:19:03 keep c_quizzes model 1 validated 18 / 410 (4.39%) nb_accumulated 187 / 410 (finishes Mon 18:32 -- 1028/h)
20240812-18:19:52 keep c_quizzes model 1 validated 13 / 410 (3.17%) nb_accumulated 200 / 410 (finishes Mon 18:32 -- 1024/h)
20240812-18:20:41 keep c_quizzes model 4 validated 19 / 410 (4.63%) nb_accumulated 219 / 410 (finishes Mon 18:31 -- 1048/h)
20240812-18:21:29 keep c_quizzes model 2 validated 15 / 410 (3.66%) nb_accumulated 234 / 410 (finishes Mon 18:31 -- 1052/h)
20240812-18:22:18 keep c_quizzes model 1 validated 14 / 410 (3.41%) nb_accumulated 248 / 410 (finishes Mon 18:31 -- 1051/h)
20240812-18:23:07 keep c_quizzes model 0 validated 15 / 410 (3.66%) nb_accumulated 263 / 410 (finishes Mon 18:31 -- 1054/h)
20240812-18:23:56 keep c_quizzes model 4 validated 11 / 410 (2.68%) nb_accumulated 274 / 410 (finishes Mon 18:31 -- 1042/h)
20240812-18:24:44 keep c_quizzes model 4 validated 19 / 410 (4.63%) nb_accumulated 293 / 410 (finishes Mon 18:31 -- 1059/h)
20240812-18:25:34 keep c_quizzes model 0 validated 15 / 410 (3.66%) nb_accumulated 308 / 410 (finishes Mon 18:31 -- 1061/h)
20240812-18:26:22 keep c_quizzes model 2 validated 16 / 410 (3.90%) nb_accumulated 324 / 410 (finishes Mon 18:31 -- 1066/h)
20240812-18:27:11 keep c_quizzes model 0 validated 17 / 410 (4.15%) nb_accumulated 341 / 410 (finishes Mon 18:31 -- 1075/h)
20240812-18:28:00 keep c_quizzes model 3 validated 20 / 410 (4.88%) nb_accumulated 361 / 410 (finishes Mon 18:30 -- 1091/h)
20240812-18:28:48 keep c_quizzes model 0 validated 17 / 410 (4.15%) nb_accumulated 378 / 410 (finishes Mon 18:30 -- 1098/h)
20240812-18:29:37 keep c_quizzes model 2 validated 13 / 410 (3.17%) nb_accumulated 391 / 410 (finishes Mon 18:30 -- 1092/h)
20240812-18:30:26 keep c_quizzes model 2 validated 18 / 410 (4.39%) nb_accumulated 409 / 410 (finishes Mon 18:30 -- 1101/h)
20240812-18:31:14 keep c_quizzes model 0 validated 10 / 410 (2.44%) nb_accumulated 419 / 410 (finishes now! -- 1088/h)
20240812-18:31:18 wrote c_quizzes.pth
20240812-18:31:18 training model 0
20240812-18:31:18 training model 1
20240812-18:35:02 train_perplexity 70 model 0 1.152081412672053
20240812-18:35:03 train_perplexity 70 model 1 1.1550136742315085
20240812-18:35:05 test_perplexity 70 model 0 1.1479257429896699
20240812-18:35:06 test_perplexity 70 model 1 1.1468668457854903
20240812-18:35:48 test_accuracy 70 model 0 val 767 / 801
20240812-18:35:52 test_accuracy 70 model 1 val 759 / 793
20240812-18:35:53 wrote gpt_000.pth
20240812-18:35:54 wrote gpt_001.pth
20240812-18:36:07 wrote non_validated_0070_00.png
20240812-18:36:20 wrote non_validated_0070_01.png
20240812-18:36:20 wrote state.pth
20240812-18:36:20 --- epoch 71 ----------------------------------------
20240812-18:36:20 current_test_accuracies 0.9576 0.9571 0.0000 0.0000 0.0000
20240812-18:36:20 training model 2
20240812-18:36:20 training model 3
20240812-18:40:04 train_perplexity 71 model 2 1.1521867531657168
20240812-18:40:06 test_perplexity 71 model 2 1.1487347583923833
20240812-18:40:07 train_perplexity 71 model 3 1.1524948190436128
20240812-18:40:09 test_perplexity 71 model 3 1.1461477853273763
20240812-18:40:53 test_accuracy 71 model 3 val 754 / 810
20240812-18:40:55 test_accuracy 71 model 2 val 746 / 795
20240812-18:40:57 wrote gpt_002.pth
20240812-18:40:57 wrote gpt_003.pth
20240812-18:41:10 wrote non_validated_0071_02.png
20240812-18:41:23 wrote non_validated_0071_03.png
20240812-18:41:23 wrote state.pth
20240812-18:41:23 --- epoch 72 ----------------------------------------
20240812-18:41:23 current_test_accuracies 0.9576 0.9571 0.9384 0.9309 0.0000
20240812-18:41:23 training model 4
20240812-18:41:23 training model 3
20240812-18:45:08 train_perplexity 72 model 4 1.1515316006513212
20240812-18:45:09 test_perplexity 72 model 4 1.1492597520944001
20240812-18:45:10 train_perplexity 72 model 3 1.1518624083190199
20240812-18:45:13 test_perplexity 72 model 3 1.1497216584931025
20240812-18:45:54 test_accuracy 72 model 4 val 772 / 808
20240812-18:45:56 test_accuracy 72 model 3 val 758 / 812
20240812-18:45:58 wrote gpt_004.pth
20240812-18:45:59 wrote gpt_003.pth
20240812-18:46:12 wrote non_validated_0072_04.png
20240812-18:46:25 wrote non_validated_0072_03.png
20240812-18:46:25 wrote state.pth
20240812-18:46:25 --- epoch 73 ----------------------------------------
20240812-18:46:25 current_test_accuracies 0.9576 0.9571 0.9384 0.9335 0.9554
20240812-18:46:25 training model 3
20240812-18:46:25 training model 2
20240812-18:50:10 train_perplexity 73 model 3 1.1511299558256205
20240812-18:50:11 train_perplexity 73 model 2 1.1522264539631286
20240812-18:50:13 test_perplexity 73 model 3 1.1444471695048588
20240812-18:50:14 test_perplexity 73 model 2 1.1447094861488187
20240812-18:50:59 test_accuracy 73 model 3 val 718 / 752
20240812-18:51:02 test_accuracy 73 model 2 val 742 / 782
20240812-18:51:03 wrote gpt_003.pth
20240812-18:51:04 wrote gpt_002.pth
20240812-18:51:17 wrote non_validated_0073_03.png
20240812-18:51:30 wrote non_validated_0073_02.png
20240812-18:51:30 wrote state.pth
20240812-18:51:30 --- epoch 74 ----------------------------------------
20240812-18:51:30 current_test_accuracies 0.9576 0.9571 0.9488 0.9548 0.9554
20240812-18:51:30 training model 2
20240812-18:51:30 training model 3
20240812-18:55:15 train_perplexity 74 model 2 1.1512935983598072
20240812-18:55:17 train_perplexity 74 model 3 1.1513026638495005
20240812-18:55:17 test_perplexity 74 model 2 1.1485287992039248
20240812-18:55:19 test_perplexity 74 model 3 1.1485215606858528
20240812-18:56:02 test_accuracy 74 model 3 val 770 / 804
20240812-18:56:05 test_accuracy 74 model 2 val 741 / 799
20240812-18:56:07 wrote gpt_002.pth
20240812-18:56:08 wrote gpt_003.pth
20240812-18:56:21 wrote non_validated_0074_02.png
20240812-18:56:34 wrote non_validated_0074_03.png
20240812-18:56:34 wrote state.pth
20240812-18:56:34 --- epoch 75 ----------------------------------------
20240812-18:56:34 current_test_accuracies 0.9576 0.9571 0.9274 0.9577 0.9554
20240812-18:56:34 training model 2
20240812-18:56:34 training model 4
20240812-19:00:19 train_perplexity 75 model 2 1.1511029876548735
20240812-19:00:20 train_perplexity 75 model 4 1.1508935278638814
20240812-19:00:22 test_perplexity 75 model 2 1.1465410901002915
20240812-19:00:23 test_perplexity 75 model 4 1.146355944115405
20240812-19:01:06 test_accuracy 75 model 2 val 757 / 802
20240812-19:01:10 test_accuracy 75 model 4 val 761 / 786
20240812-19:01:11 wrote gpt_002.pth
20240812-19:01:12 wrote gpt_004.pth
20240812-19:01:25 wrote non_validated_0075_02.png
20240812-19:01:38 wrote non_validated_0075_04.png
20240812-19:01:38 wrote state.pth
20240812-19:01:38 --- epoch 76 ----------------------------------------
20240812-19:01:38 current_test_accuracies 0.9576 0.9571 0.9439 0.9577 0.9682
20240812-19:01:38 training model 2
20240812-19:01:38 training model 1
20240812-19:05:23 train_perplexity 76 model 2 1.150495287253063
20240812-19:05:24 train_perplexity 76 model 1 1.1536285255259837
20240812-19:05:26 test_perplexity 76 model 2 1.1492919230719718
20240812-19:05:27 test_perplexity 76 model 1 1.1471515277804096
20240812-19:06:14 test_accuracy 76 model 2 val 741 / 791
20240812-19:06:15 test_accuracy 76 model 1 val 767 / 788
20240812-19:06:17 wrote gpt_002.pth
20240812-19:06:18 wrote gpt_001.pth
20240812-19:06:31 wrote non_validated_0076_02.png
20240812-19:06:44 wrote non_validated_0076_01.png
20240812-19:06:44 wrote state.pth
20240812-19:06:44 --- epoch 77 ----------------------------------------
20240812-19:06:44 current_test_accuracies 0.9576 0.9734 0.9368 0.9577 0.9682
20240812-19:06:44 training model 2
20240812-19:06:44 training model 0
20240812-19:10:28 train_perplexity 77 model 2 1.1500884617526599
20240812-19:10:30 train_perplexity 77 model 0 1.151439541325128
20240812-19:10:30 test_perplexity 77 model 2 1.1451334271037008
20240812-19:10:33 test_perplexity 77 model 0 1.1482716884273783
20240812-19:11:17 test_accuracy 77 model 2 val 764 / 803
20240812-19:11:20 test_accuracy 77 model 0 val 751 / 789
20240812-19:11:22 wrote gpt_002.pth
20240812-19:11:22 wrote gpt_000.pth
20240812-19:11:35 wrote non_validated_0077_02.png
20240812-19:11:48 wrote non_validated_0077_00.png
20240812-19:11:48 wrote state.pth
20240812-19:11:48 --- epoch 78 ----------------------------------------
20240812-19:11:48 current_test_accuracies 0.9518 0.9734 0.9514 0.9577 0.9682
20240812-19:12:59 keep c_quizzes model 1 validated 16 / 410 (3.90%) nb_accumulated 16 / 410 (finishes Mon 19:42 -- 809/h)
20240812-19:13:48 keep c_quizzes model 2 validated 16 / 410 (3.90%) nb_accumulated 32 / 410 (finishes Mon 19:37 -- 961/h)
20240812-19:14:36 keep c_quizzes model 0 validated 11 / 410 (2.68%) nb_accumulated 43 / 410 (finishes Mon 19:38 -- 919/h)
20240812-19:15:25 keep c_quizzes model 3 validated 7 / 410 (1.71%) nb_accumulated 50 / 410 (finishes Mon 19:41 -- 829/h)
20240812-19:16:14 keep c_quizzes model 0 validated 13 / 410 (3.17%) nb_accumulated 63 / 410 (finishes Mon 19:40 -- 853/h)
20240812-19:17:03 keep c_quizzes model 0 validated 22 / 410 (5.37%) nb_accumulated 85 / 410 (finishes Mon 19:37 -- 972/h)
20240812-19:17:51 keep c_quizzes model 4 validated 19 / 410 (4.63%) nb_accumulated 104 / 410 (finishes Mon 19:35 -- 1030/h)
20240812-19:18:40 keep c_quizzes model 0 validated 15 / 410 (3.66%) nb_accumulated 119 / 410 (finishes Mon 19:35 -- 1040/h)
20240812-19:19:29 keep c_quizzes model 0 validated 16 / 410 (3.90%) nb_accumulated 135 / 410 (finishes Mon 19:35 -- 1055/h)
20240812-19:20:17 keep c_quizzes model 1 validated 11 / 410 (2.68%) nb_accumulated 146 / 410 (finishes Mon 19:35 -- 1032/h)
20240812-19:21:06 keep c_quizzes model 1 validated 13 / 410 (3.17%) nb_accumulated 159 / 410 (finishes Mon 19:35 -- 1026/h)
20240812-19:21:54 keep c_quizzes model 0 validated 7 / 410 (1.71%) nb_accumulated 166 / 410 (finishes Mon 19:36 -- 985/h)
20240812-19:22:43 keep c_quizzes model 0 validated 15 / 410 (3.66%) nb_accumulated 181 / 410 (finishes Mon 19:36 -- 994/h)
20240812-19:23:32 keep c_quizzes model 2 validated 15 / 410 (3.66%) nb_accumulated 196 / 410 (finishes Mon 19:36 -- 1002/h)
20240812-19:24:20 keep c_quizzes model 1 validated 23 / 410 (5.61%) nb_accumulated 219 / 410 (finishes Mon 19:35 -- 1047/h)
20240812-19:25:09 keep c_quizzes model 0 validated 14 / 410 (3.41%) nb_accumulated 233 / 410 (finishes Mon 19:35 -- 1047/h)
20240812-19:25:58 keep c_quizzes model 2 validated 21 / 410 (5.12%) nb_accumulated 254 / 410 (finishes Mon 19:34 -- 1075/h)
20240812-19:26:46 keep c_quizzes model 3 validated 17 / 410 (4.15%) nb_accumulated 271 / 410 (finishes Mon 19:34 -- 1085/h)
20240812-19:27:35 keep c_quizzes model 1 validated 13 / 410 (3.17%) nb_accumulated 284 / 410 (finishes Mon 19:34 -- 1079/h)
20240812-19:28:24 keep c_quizzes model 4 validated 12 / 410 (2.93%) nb_accumulated 296 / 410 (finishes Mon 19:34 -- 1069/h)
20240812-19:29:13 keep c_quizzes model 2 validated 16 / 410 (3.90%) nb_accumulated 312 / 410 (finishes Mon 19:34 -- 1075/h)
20240812-19:30:01 keep c_quizzes model 4 validated 20 / 410 (4.88%) nb_accumulated 332 / 410 (finishes Mon 19:34 -- 1093/h)
20240812-19:30:50 keep c_quizzes model 1 validated 18 / 410 (4.39%) nb_accumulated 350 / 410 (finishes Mon 19:34 -- 1103/h)
20240812-19:31:39 keep c_quizzes model 3 validated 12 / 410 (2.93%) nb_accumulated 362 / 410 (finishes Mon 19:34 -- 1094/h)
20240812-19:32:27 keep c_quizzes model 4 validated 12 / 410 (2.93%) nb_accumulated 374 / 410 (finishes Mon 19:34 -- 1086/h)
20240812-19:33:16 keep c_quizzes model 2 validated 10 / 410 (2.44%) nb_accumulated 384 / 410 (finishes Mon 19:34 -- 1073/h)
20240812-19:34:04 keep c_quizzes model 0 validated 15 / 410 (3.66%) nb_accumulated 399 / 410 (finishes Mon 19:34 -- 1075/h)
20240812-19:34:53 keep c_quizzes model 3 validated 18 / 410 (4.39%) nb_accumulated 417 / 410 (finishes now! -- 1084/h)
20240812-19:34:56 wrote c_quizzes.pth
20240812-19:34:56 training model 0
20240812-19:34:56 training model 1
20240812-19:38:40 train_perplexity 78 model 0 1.151759176655689
20240812-19:38:41 train_perplexity 78 model 1 1.1536959834355924
20240812-19:38:43 test_perplexity 78 model 0 1.148123187166166
20240812-19:38:44 test_perplexity 78 model 1 1.1465695468856483
20240812-19:39:31 test_accuracy 78 model 1 val 734 / 778
20240812-19:39:33 test_accuracy 78 model 0 val 759 / 796
20240812-19:39:35 wrote gpt_000.pth
20240812-19:39:35 wrote gpt_001.pth
20240812-19:39:48 wrote non_validated_0078_00.png
20240812-19:40:01 wrote non_validated_0078_01.png
20240812-19:40:01 wrote state.pth
20240812-19:40:01 --- epoch 79 ----------------------------------------
20240812-19:40:01 current_test_accuracies 0.9535 0.9434 0.0000 0.0000 0.0000
20240812-19:40:01 training model 2
20240812-19:40:01 training model 3
20240812-19:43:45 train_perplexity 79 model 2 1.1505250700872465
20240812-19:43:47 test_perplexity 79 model 2 1.1456882441112677
20240812-19:43:48 train_perplexity 79 model 3 1.1511674769125604
20240812-19:43:50 test_perplexity 79 model 3 1.1467397361848815
20240812-19:44:31 test_accuracy 79 model 2 val 771 / 805
20240812-19:44:34 test_accuracy 79 model 3 val 743 / 782
20240812-19:44:36 wrote gpt_002.pth
20240812-19:44:37 wrote gpt_003.pth
20240812-19:44:50 wrote non_validated_0079_02.png
20240812-19:45:03 wrote non_validated_0079_03.png
20240812-19:45:03 wrote state.pth
20240812-19:45:03 --- epoch 80 ----------------------------------------
20240812-19:45:03 current_test_accuracies 0.9535 0.9434 0.9578 0.9501 0.0000
20240812-19:45:03 training model 4
20240812-19:45:03 training model 1
20240812-19:48:47 train_perplexity 80 model 4 1.1510473618116097
20240812-19:48:49 test_perplexity 80 model 4 1.148735890500394
20240812-19:48:50 train_perplexity 80 model 1 1.1529495390323101
20240812-19:48:52 test_perplexity 80 model 1 1.1484144602949775
20240812-19:49:36 test_accuracy 80 model 1 val 773 / 808
20240812-19:49:37 test_accuracy 80 model 4 val 743 / 785
20240812-19:49:39 wrote gpt_004.pth
20240812-19:49:40 wrote gpt_001.pth
20240812-19:49:52 wrote non_validated_0080_04.png
20240812-19:50:05 wrote non_validated_0080_01.png
20240812-19:50:05 wrote state.pth
20240812-19:50:05 --- epoch 81 ----------------------------------------
20240812-19:50:05 current_test_accuracies 0.9535 0.9567 0.9578 0.9501 0.9465
20240812-19:50:05 training model 4
20240812-19:50:05 training model 3
20240812-19:53:50 train_perplexity 81 model 4 1.150641824796034
20240812-19:53:52 train_perplexity 81 model 3 1.1512719819454287
20240812-19:53:53 test_perplexity 81 model 4 1.1471308223521959
20240812-19:53:55 test_perplexity 81 model 3 1.1489904404988003
20240812-19:54:36 test_accuracy 81 model 4 val 763 / 800
20240812-19:54:38 test_accuracy 81 model 3 val 771 / 812
20240812-19:54:40 wrote gpt_004.pth
20240812-19:54:41 wrote gpt_003.pth
20240812-19:54:54 wrote non_validated_0081_04.png
20240812-19:55:07 wrote non_validated_0081_03.png
20240812-19:55:07 wrote state.pth
20240812-19:55:07 --- epoch 82 ----------------------------------------
20240812-19:55:07 current_test_accuracies 0.9535 0.9567 0.9578 0.9495 0.9538
20240812-19:55:07 training model 3
20240812-19:55:07 training model 0
20240812-19:58:52 train_perplexity 82 model 3 1.1512049809049338
20240812-19:58:53 train_perplexity 82 model 0 1.151407497519524
20240812-19:58:54 test_perplexity 82 model 3 1.1467936790063387
20240812-19:58:56 test_perplexity 82 model 0 1.1484670678925044
20240812-19:59:42 test_accuracy 82 model 0 val 779 / 818
20240812-19:59:43 test_accuracy 82 model 3 val 767 / 797
20240812-19:59:45 wrote gpt_003.pth
20240812-19:59:45 wrote gpt_000.pth
20240812-19:59:58 wrote non_validated_0082_03.png
20240812-20:00:11 wrote non_validated_0082_00.png
20240812-20:00:11 wrote state.pth
20240812-20:00:11 --- epoch 83 ----------------------------------------
20240812-20:00:11 current_test_accuracies 0.9523 0.9567 0.9578 0.9624 0.9538
20240812-20:01:22 keep c_quizzes model 2 validated 21 / 410 (5.12%) nb_accumulated 21 / 410 (finishes Mon 20:23 -- 1068/h)
20240812-20:02:11 keep c_quizzes model 2 validated 20 / 410 (4.88%) nb_accumulated 41 / 410 (finishes Mon 20:20 -- 1236/h)
20240812-20:02:59 keep c_quizzes model 4 validated 19 / 410 (4.63%) nb_accumulated 60 / 410 (finishes Mon 20:19 -- 1284/h)
20240812-20:03:48 keep c_quizzes model 3 validated 15 / 410 (3.66%) nb_accumulated 75 / 410 (finishes Mon 20:19 -- 1244/h)
20240812-20:04:37 keep c_quizzes model 1 validated 11 / 410 (2.68%) nb_accumulated 86 / 410 (finishes Mon 20:21 -- 1166/h)
20240812-20:05:25 keep c_quizzes model 1 validated 15 / 410 (3.66%) nb_accumulated 101 / 410 (finishes Mon 20:21 -- 1157/h)
20240812-20:06:14 keep c_quizzes model 0 validated 20 / 410 (4.88%) nb_accumulated 121 / 410 (finishes Mon 20:20 -- 1200/h)
20240812-20:07:03 keep c_quizzes model 4 validated 14 / 410 (3.41%) nb_accumulated 135 / 410 (finishes Mon 20:21 -- 1181/h)
20240812-20:07:51 keep c_quizzes model 3 validated 17 / 410 (4.15%) nb_accumulated 152 / 410 (finishes Mon 20:20 -- 1190/h)
20240812-20:08:39 keep c_quizzes model 0 validated 19 / 410 (4.63%) nb_accumulated 171 / 410 (finishes Mon 20:20 -- 1211/h)
20240812-20:09:28 keep c_quizzes model 0 validated 20 / 410 (4.88%) nb_accumulated 191 / 410 (finishes Mon 20:20 -- 1234/h)
20240812-20:10:16 keep c_quizzes model 0 validated 13 / 410 (3.17%) nb_accumulated 204 / 410 (finishes Mon 20:20 -- 1213/h)
20240812-20:11:05 keep c_quizzes model 3 validated 12 / 410 (2.93%) nb_accumulated 216 / 410 (finishes Mon 20:20 -- 1189/h)
20240812-20:11:54 keep c_quizzes model 4 validated 17 / 410 (4.15%) nb_accumulated 233 / 410 (finishes Mon 20:20 -- 1194/h)
20240812-20:12:42 keep c_quizzes model 0 validated 14 / 410 (3.41%) nb_accumulated 247 / 410 (finishes Mon 20:20 -- 1184/h)
20240812-20:13:31 keep c_quizzes model 3 validated 13 / 410 (3.17%) nb_accumulated 260 / 410 (finishes Mon 20:21 -- 1170/h)
20240812-20:14:19 keep c_quizzes model 4 validated 21 / 410 (5.12%) nb_accumulated 281 / 410 (finishes Mon 20:20 -- 1192/h)
20240812-20:15:08 keep c_quizzes model 3 validated 17 / 410 (4.15%) nb_accumulated 298 / 410 (finishes Mon 20:20 -- 1196/h)
20240812-20:15:56 keep c_quizzes model 0 validated 15 / 410 (3.66%) nb_accumulated 313 / 410 (finishes Mon 20:20 -- 1192/h)
20240812-20:16:45 keep c_quizzes model 4 validated 16 / 410 (3.90%) nb_accumulated 329 / 410 (finishes Mon 20:20 -- 1192/h)
20240812-20:17:33 keep c_quizzes model 2 validated 22 / 410 (5.37%) nb_accumulated 351 / 410 (finishes Mon 20:20 -- 1212/h)
20240812-20:18:22 keep c_quizzes model 0 validated 11 / 410 (2.68%) nb_accumulated 362 / 410 (finishes Mon 20:20 -- 1194/h)
20240812-20:19:11 keep c_quizzes model 2 validated 18 / 410 (4.39%) nb_accumulated 380 / 410 (finishes Mon 20:20 -- 1200/h)
20240812-20:19:59 keep c_quizzes model 1 validated 19 / 410 (4.63%) nb_accumulated 399 / 410 (finishes Mon 20:20 -- 1208/h)
20240812-20:20:48 keep c_quizzes model 3 validated 13 / 410 (3.17%) nb_accumulated 412 / 410 (finishes now! -- 1199/h)
20240812-20:20:52 wrote c_quizzes.pth
20240812-20:20:52 training model 0
20240812-20:20:52 training model 1
20240812-20:24:35 train_perplexity 83 model 0 1.151719436428997
20240812-20:24:36 train_perplexity 83 model 1 1.1530155559600481
20240812-20:24:38 test_perplexity 83 model 0 1.148197622744752
20240812-20:24:39 test_perplexity 83 model 1 1.147225551198706
20240812-20:25:22 test_accuracy 83 model 1 val 775 / 818
20240812-20:25:23 test_accuracy 83 model 0 val 794 / 820
20240812-20:25:25 wrote gpt_000.pth
20240812-20:25:26 wrote gpt_001.pth
20240812-20:25:38 wrote non_validated_0083_00.png
20240812-20:25:51 wrote non_validated_0083_01.png
20240812-20:25:51 wrote state.pth
20240812-20:25:51 --- epoch 84 ----------------------------------------
20240812-20:25:51 current_test_accuracies 0.9683 0.9474 0.0000 0.0000 0.0000
20240812-20:25:51 training model 2
20240812-20:25:51 training model 3
20240812-20:29:36 train_perplexity 84 model 2 1.1514025148923646
20240812-20:29:38 train_perplexity 84 model 3 1.1513219401916417
20240812-20:29:38 test_perplexity 84 model 2 1.1477159903984735
20240812-20:29:40 test_perplexity 84 model 3 1.1481657424556464
20240812-20:30:24 test_accuracy 84 model 2 val 774 / 802
20240812-20:30:26 test_accuracy 84 model 3 val 755 / 789
20240812-20:30:28 wrote gpt_002.pth
20240812-20:30:29 wrote gpt_003.pth
20240812-20:30:41 wrote non_validated_0084_02.png
20240812-20:30:54 wrote non_validated_0084_03.png
20240812-20:30:54 wrote state.pth
20240812-20:30:54 --- epoch 85 ----------------------------------------
20240812-20:30:54 current_test_accuracies 0.9683 0.9474 0.9651 0.9569 0.0000
20240812-20:30:54 training model 4
20240812-20:30:54 training model 1
20240812-20:34:40 train_perplexity 85 model 4 1.1516995028490369
20240812-20:34:41 train_perplexity 85 model 1 1.1528104849467935
20240812-20:34:42 test_perplexity 85 model 4 1.144436610609066
20240812-20:34:44 test_perplexity 85 model 1 1.1487408706334594
20240812-20:35:28 test_accuracy 85 model 1 val 787 / 818
20240812-20:35:29 test_accuracy 85 model 4 val 735 / 772
20240812-20:35:31 wrote gpt_004.pth
20240812-20:35:32 wrote gpt_001.pth
20240812-20:35:45 wrote non_validated_0085_04.png
20240812-20:35:58 wrote non_validated_0085_01.png
20240812-20:35:58 wrote state.pth
20240812-20:35:58 --- epoch 86 ----------------------------------------
20240812-20:35:58 current_test_accuracies 0.9683 0.9621 0.9651 0.9569 0.9521
20240812-20:37:06 keep c_quizzes model 2 validated 14 / 410 (3.41%) nb_accumulated 14 / 410 (finishes Mon 21:09 -- 736/h)
20240812-20:37:55 keep c_quizzes model 0 validated 12 / 410 (2.93%) nb_accumulated 26 / 410 (finishes Mon 21:06 -- 798/h)
20240812-20:38:43 keep c_quizzes model 3 validated 15 / 410 (3.66%) nb_accumulated 41 / 410 (finishes Mon 21:03 -- 890/h)
20240812-20:39:32 keep c_quizzes model 2 validated 16 / 410 (3.90%) nb_accumulated 57 / 410 (finishes Mon 21:01 -- 957/h)
20240812-20:40:21 keep c_quizzes model 0 validated 26 / 410 (6.34%) nb_accumulated 83 / 410 (finishes Mon 20:57 -- 1136/h)
20240812-20:41:09 keep c_quizzes model 2 validated 16 / 410 (3.90%) nb_accumulated 99 / 410 (finishes Mon 20:57 -- 1144/h)
20240812-20:41:58 keep c_quizzes model 3 validated 13 / 410 (3.17%) nb_accumulated 112 / 410 (finishes Mon 20:57 -- 1119/h)
20240812-20:42:46 keep c_quizzes model 0 validated 16 / 410 (3.90%) nb_accumulated 128 / 410 (finishes Mon 20:57 -- 1127/h)
20240812-20:43:35 keep c_quizzes model 1 validated 22 / 410 (5.37%) nb_accumulated 150 / 410 (finishes Mon 20:56 -- 1180/h)
20240812-20:44:24 keep c_quizzes model 2 validated 16 / 410 (3.90%) nb_accumulated 166 / 410 (finishes Mon 20:56 -- 1181/h)
20240812-20:45:12 keep c_quizzes model 0 validated 8 / 410 (1.95%) nb_accumulated 174 / 410 (finishes Mon 20:57 -- 1129/h)
20240812-20:46:01 keep c_quizzes model 1 validated 13 / 410 (3.17%) nb_accumulated 187 / 410 (finishes Mon 20:58 -- 1116/h)
20240812-20:46:50 keep c_quizzes model 2 validated 17 / 410 (4.15%) nb_accumulated 204 / 410 (finishes Mon 20:57 -- 1126/h)
20240812-20:47:38 keep c_quizzes model 1 validated 13 / 410 (3.17%) nb_accumulated 217 / 410 (finishes Mon 20:58 -- 1115/h)
20240812-20:48:27 keep c_quizzes model 3 validated 15 / 410 (3.66%) nb_accumulated 232 / 410 (finishes Mon 20:58 -- 1115/h)
20240812-20:49:15 keep c_quizzes model 2 validated 11 / 410 (2.68%) nb_accumulated 243 / 410 (finishes Mon 20:58 -- 1096/h)
20240812-20:50:04 keep c_quizzes model 1 validated 18 / 410 (4.39%) nb_accumulated 261 / 410 (finishes Mon 20:58 -- 1110/h)
20240812-20:50:53 keep c_quizzes model 1 validated 15 / 410 (3.66%) nb_accumulated 276 / 410 (finishes Mon 20:58 -- 1110/h)
20240812-20:51:41 keep c_quizzes model 4 validated 18 / 410 (4.39%) nb_accumulated 294 / 410 (finishes Mon 20:57 -- 1121/h)
20240812-20:52:30 keep c_quizzes model 1 validated 12 / 410 (2.93%) nb_accumulated 306 / 410 (finishes Mon 20:58 -- 1110/h)
20240812-20:53:19 keep c_quizzes model 0 validated 16 / 410 (3.90%) nb_accumulated 322 / 410 (finishes Mon 20:58 -- 1113/h)
20240812-20:54:07 keep c_quizzes model 3 validated 16 / 410 (3.90%) nb_accumulated 338 / 410 (finishes Mon 20:58 -- 1116/h)
20240812-20:54:56 keep c_quizzes model 0 validated 10 / 410 (2.44%) nb_accumulated 348 / 410 (finishes Mon 20:58 -- 1100/h)
20240812-20:55:45 keep c_quizzes model 1 validated 19 / 410 (4.63%) nb_accumulated 367 / 410 (finishes Mon 20:58 -- 1113/h)
20240812-20:56:33 keep c_quizzes model 1 validated 13 / 410 (3.17%) nb_accumulated 380 / 410 (finishes Mon 20:58 -- 1107/h)
20240812-20:57:22 keep c_quizzes model 4 validated 14 / 410 (3.41%) nb_accumulated 394 / 410 (finishes Mon 20:58 -- 1104/h)
20240812-20:58:10 keep c_quizzes model 1 validated 10 / 410 (2.44%) nb_accumulated 404 / 410 (finishes Mon 20:58 -- 1091/h)
20240812-20:58:59 keep c_quizzes model 0 validated 15 / 410 (3.66%) nb_accumulated 419 / 410 (finishes now! -- 1092/h)
20240812-20:59:03 wrote c_quizzes.pth
20240812-20:59:03 training model 0
20240812-20:59:03 training model 1
20240812-21:02:45 train_perplexity 86 model 0 1.1520677168126359
20240812-21:02:47 test_perplexity 86 model 0 1.1474607117956064
20240812-21:02:48 train_perplexity 86 model 1 1.1528374199132305
20240812-21:02:50 test_perplexity 86 model 1 1.1488753958864035
20240812-21:03:31 test_accuracy 86 model 0 val 761 / 804
20240812-21:03:34 test_accuracy 86 model 1 val 774 / 807
20240812-21:03:36 wrote gpt_000.pth
20240812-21:03:37 wrote gpt_001.pth
20240812-21:03:50 wrote non_validated_0086_00.png
20240812-21:04:02 wrote non_validated_0086_01.png
20240812-21:04:03 wrote state.pth
20240812-21:04:03 --- epoch 87 ----------------------------------------
20240812-21:04:03 current_test_accuracies 0.9465 0.9591 0.0000 0.0000 0.0000
20240812-21:04:03 training model 2
20240812-21:04:03 training model 3
20240812-21:07:48 train_perplexity 87 model 2 1.1513674978899682
20240812-21:07:49 train_perplexity 87 model 3 1.1512771157898043
20240812-21:07:50 test_perplexity 87 model 2 1.149118475729373
20240812-21:07:52 test_perplexity 87 model 3 1.1470694304747862
20240812-21:08:38 test_accuracy 87 model 3 val 741 / 787
20240812-21:08:39 test_accuracy 87 model 2 val 745 / 789
20240812-21:08:41 wrote gpt_002.pth
20240812-21:08:42 wrote gpt_003.pth
20240812-21:08:55 wrote non_validated_0087_02.png
20240812-21:09:08 wrote non_validated_0087_03.png
20240812-21:09:08 wrote state.pth
20240812-21:09:08 --- epoch 88 ----------------------------------------
20240812-21:09:08 current_test_accuracies 0.9465 0.9591 0.9442 0.9416 0.0000
20240812-21:09:08 training model 4
20240812-21:09:08 training model 3
20240812-21:12:53 train_perplexity 88 model 4 1.1515171215016464
20240812-21:12:54 train_perplexity 88 model 3 1.151305802813925
20240812-21:12:55 test_perplexity 88 model 4 1.1481855405227945
20240812-21:12:57 test_perplexity 88 model 3 1.14931956613269
20240812-21:13:41 test_accuracy 88 model 4 val 777 / 820
20240812-21:13:43 test_accuracy 88 model 3 val 748 / 780
20240812-21:13:45 wrote gpt_004.pth
20240812-21:13:46 wrote gpt_003.pth
20240812-21:13:59 wrote non_validated_0088_04.png
20240812-21:14:12 wrote non_validated_0088_03.png
20240812-21:14:12 wrote state.pth
20240812-21:14:12 --- epoch 89 ----------------------------------------
20240812-21:14:12 current_test_accuracies 0.9465 0.9591 0.9442 0.9590 0.9476
20240812-21:14:12 training model 2
20240812-21:14:12 training model 0
20240812-21:17:57 train_perplexity 89 model 2 1.1511571091577775
20240812-21:17:58 train_perplexity 89 model 0 1.1516925332143324
20240812-21:17:59 test_perplexity 89 model 2 1.149788729538028
20240812-21:18:01 test_perplexity 89 model 0 1.1502453000988677
20240812-21:18:44 test_accuracy 89 model 2 val 789 / 819
20240812-21:18:45 test_accuracy 89 model 0 val 772 / 806
20240812-21:18:47 wrote gpt_002.pth
20240812-21:18:48 wrote gpt_000.pth
20240812-21:19:00 wrote non_validated_0089_02.png
20240812-21:19:13 wrote non_validated_0089_00.png
20240812-21:19:13 wrote state.pth
20240812-21:19:13 --- epoch 90 ----------------------------------------
20240812-21:19:13 current_test_accuracies 0.9578 0.9591 0.9634 0.9590 0.9476
20240812-21:19:13 training model 4
20240812-21:19:13 training model 0
20240812-21:22:58 train_perplexity 90 model 4 1.1515144743517718
20240812-21:23:00 train_perplexity 90 model 0 1.1518749168497384
20240812-21:23:00 test_perplexity 90 model 4 1.1496528666795596
20240812-21:23:02 test_perplexity 90 model 0 1.1509109459090612
20240812-21:23:47 test_accuracy 90 model 4 val 787 / 818
20240812-21:23:49 test_accuracy 90 model 0 val 762 / 797
20240812-21:23:51 wrote gpt_004.pth
20240812-21:23:52 wrote gpt_000.pth
20240812-21:24:05 wrote non_validated_0090_04.png
20240812-21:24:18 wrote non_validated_0090_00.png
20240812-21:24:18 wrote state.pth
20240812-21:24:18 --- epoch 91 ----------------------------------------
20240812-21:24:18 current_test_accuracies 0.9561 0.9591 0.9634 0.9590 0.9621
20240812-21:25:30 keep c_quizzes model 0 validated 15 / 410 (3.66%) nb_accumulated 15 / 410 (finishes Mon 21:57 -- 747/h)
20240812-21:26:19 keep c_quizzes model 2 validated 14 / 410 (3.41%) nb_accumulated 29 / 410 (finishes Mon 21:52 -- 863/h)
20240812-21:27:07 keep c_quizzes model 1 validated 18 / 410 (4.39%) nb_accumulated 47 / 410 (finishes Mon 21:48 -- 998/h)
20240812-21:27:56 keep c_quizzes model 4 validated 11 / 410 (2.68%) nb_accumulated 58 / 410 (finishes Mon 21:49 -- 958/h)
20240812-21:28:45 keep c_quizzes model 3 validated 16 / 410 (3.90%) nb_accumulated 74 / 410 (finishes Mon 21:48 -- 999/h)
20240812-21:29:33 keep c_quizzes model 4 validated 10 / 410 (2.44%) nb_accumulated 84 / 410 (finishes Mon 21:49 -- 960/h)
20240812-21:30:21 keep c_quizzes model 3 validated 17 / 410 (4.15%) nb_accumulated 101 / 410 (finishes Mon 21:48 -- 1000/h)
20240812-21:31:10 keep c_quizzes model 1 validated 12 / 410 (2.93%) nb_accumulated 113 / 410 (finishes Mon 21:49 -- 987/h)
20240812-21:31:59 keep c_quizzes model 2 validated 12 / 410 (2.93%) nb_accumulated 125 / 410 (finishes Mon 21:49 -- 977/h)
20240812-21:32:47 keep c_quizzes model 0 validated 17 / 410 (4.15%) nb_accumulated 142 / 410 (finishes Mon 21:48 -- 1004/h)
20240812-21:33:36 keep c_quizzes model 1 validated 12 / 410 (2.93%) nb_accumulated 154 / 410 (finishes Mon 21:49 -- 994/h)
20240812-21:34:24 keep c_quizzes model 1 validated 17 / 410 (4.15%) nb_accumulated 171 / 410 (finishes Mon 21:48 -- 1015/h)
20240812-21:35:13 keep c_quizzes model 3 validated 15 / 410 (3.66%) nb_accumulated 186 / 410 (finishes Mon 21:48 -- 1022/h)
20240812-21:36:02 keep c_quizzes model 4 validated 7 / 410 (1.71%) nb_accumulated 193 / 410 (finishes Mon 21:49 -- 987/h)
20240812-21:36:50 keep c_quizzes model 2 validated 12 / 410 (2.93%) nb_accumulated 205 / 410 (finishes Mon 21:49 -- 981/h)
20240812-21:37:39 keep c_quizzes model 4 validated 11 / 410 (2.68%) nb_accumulated 216 / 410 (finishes Mon 21:49 -- 970/h)
20240812-21:38:28 keep c_quizzes model 1 validated 15 / 410 (3.66%) nb_accumulated 231 / 410 (finishes Mon 21:49 -- 978/h)
20240812-21:39:17 keep c_quizzes model 0 validated 13 / 410 (3.17%) nb_accumulated 244 / 410 (finishes Mon 21:49 -- 977/h)
20240812-21:40:05 keep c_quizzes model 3 validated 17 / 410 (4.15%) nb_accumulated 261 / 410 (finishes Mon 21:49 -- 991/h)
20240812-21:40:55 keep c_quizzes model 4 validated 9 / 410 (2.20%) nb_accumulated 270 / 410 (finishes Mon 21:49 -- 975/h)
20240812-21:41:43 keep c_quizzes model 0 validated 14 / 410 (3.41%) nb_accumulated 284 / 410 (finishes Mon 21:49 -- 978/h)
20240812-21:42:33 keep c_quizzes model 1 validated 14 / 410 (3.41%) nb_accumulated 298 / 410 (finishes Mon 21:49 -- 979/h)
20240812-21:43:22 keep c_quizzes model 0 validated 15 / 410 (3.66%) nb_accumulated 313 / 410 (finishes Mon 21:49 -- 985/h)
20240812-21:44:10 keep c_quizzes model 0 validated 12 / 410 (2.93%) nb_accumulated 325 / 410 (finishes Mon 21:49 -- 981/h)
20240812-21:44:59 keep c_quizzes model 0 validated 8 / 410 (1.95%) nb_accumulated 333 / 410 (finishes Mon 21:49 -- 966/h)
20240812-21:45:48 keep c_quizzes model 2 validated 17 / 410 (4.15%) nb_accumulated 350 / 410 (finishes Mon 21:49 -- 977/h)
20240812-21:46:36 keep c_quizzes model 2 validated 18 / 410 (4.39%) nb_accumulated 368 / 410 (finishes Mon 21:49 -- 989/h)
20240812-21:47:25 keep c_quizzes model 4 validated 18 / 410 (4.39%) nb_accumulated 386 / 410 (finishes Mon 21:48 -- 1001/h)
20240812-21:48:14 keep c_quizzes model 2 validated 19 / 410 (4.63%) nb_accumulated 405 / 410 (finishes Mon 21:48 -- 1015/h)
20240812-21:49:03 keep c_quizzes model 1 validated 16 / 410 (3.90%) nb_accumulated 421 / 410 (finishes now! -- 1020/h)
20240812-21:49:07 wrote c_quizzes.pth
20240812-21:49:07 training model 0
20240812-21:49:07 training model 1
20240812-21:52:52 train_perplexity 91 model 0 1.1514735406238703
20240812-21:52:52 train_perplexity 91 model 1 1.1534018702844826
20240812-21:52:55 test_perplexity 91 model 0 1.1496519576575992
20240812-21:52:55 test_perplexity 91 model 1 1.147719786046673
20240812-21:53:39 test_accuracy 91 model 0 val 764 / 802
20240812-21:53:42 test_accuracy 91 model 1 val 745 / 782
20240812-21:53:44 wrote gpt_000.pth
20240812-21:53:44 wrote gpt_001.pth
20240812-21:53:57 wrote non_validated_0091_00.png
20240812-21:54:10 wrote non_validated_0091_01.png
20240812-21:54:10 wrote state.pth
20240812-21:54:10 --- epoch 92 ----------------------------------------
20240812-21:54:10 current_test_accuracies 0.9526 0.9527 0.0000 0.0000 0.0000
20240812-21:54:10 training model 2
20240812-21:54:10 training model 3
20240812-21:57:55 train_perplexity 92 model 2 1.151176937958384
20240812-21:57:57 test_perplexity 92 model 2 1.148186428067962
20240812-21:57:57 train_perplexity 92 model 3 1.1517638712660443
20240812-21:57:59 test_perplexity 92 model 3 1.1487084272998445
20240812-21:58:43 test_accuracy 92 model 3 val 771 / 801
20240812-21:58:45 test_accuracy 92 model 2 val 725 / 778
20240812-21:58:47 wrote gpt_002.pth
20240812-21:58:47 wrote gpt_003.pth
20240812-21:59:00 wrote non_validated_0092_02.png
20240812-21:59:13 wrote non_validated_0092_03.png
20240812-21:59:13 wrote state.pth
20240812-21:59:13 --- epoch 93 ----------------------------------------
20240812-21:59:13 current_test_accuracies 0.9526 0.9527 0.9319 0.9625 0.0000
20240812-21:59:13 training model 4
20240812-21:59:13 training model 2
20240812-22:02:59 train_perplexity 93 model 4 1.1515039500940765
20240812-22:03:00 train_perplexity 93 model 2 1.1510572239473107
20240812-22:03:01 test_perplexity 93 model 4 1.1499683188527257
20240812-22:03:03 test_perplexity 93 model 2 1.1491878483998867
20240812-22:03:46 test_accuracy 93 model 4 val 762 / 804
20240812-22:03:47 test_accuracy 93 model 2 val 767 / 812
20240812-22:03:49 wrote gpt_004.pth
20240812-22:03:50 wrote gpt_002.pth
20240812-22:04:03 wrote non_validated_0093_04.png
20240812-22:04:16 wrote non_validated_0093_02.png
20240812-22:04:16 wrote state.pth
20240812-22:04:16 --- epoch 94 ----------------------------------------
20240812-22:04:16 current_test_accuracies 0.9526 0.9527 0.9446 0.9625 0.9478
20240812-22:04:16 training model 2
20240812-22:04:16 training model 4
20240812-22:08:02 train_perplexity 94 model 2 1.1512384608318063
20240812-22:08:03 train_perplexity 94 model 4 1.1514129352947273
20240812-22:08:04 test_perplexity 94 model 2 1.1466973065823458
20240812-22:08:06 test_perplexity 94 model 4 1.151871149067154
20240812-22:08:50 test_accuracy 94 model 4 val 772 / 808
20240812-22:08:53 test_accuracy 94 model 2 val 747 / 796
20240812-22:08:55 wrote gpt_002.pth
20240812-22:08:55 wrote gpt_004.pth
20240812-22:09:08 wrote non_validated_0094_02.png
20240812-22:09:21 wrote non_validated_0094_04.png
20240812-22:09:21 wrote state.pth
20240812-22:09:21 --- epoch 95 ----------------------------------------
20240812-22:09:21 current_test_accuracies 0.9526 0.9527 0.9384 0.9625 0.9554
20240812-22:09:21 training model 2
20240812-22:09:21 training model 0
20240812-22:13:06 train_perplexity 95 model 2 1.1510952153799188
20240812-22:13:08 train_perplexity 95 model 0 1.151643599202991
20240812-22:13:08 test_perplexity 95 model 2 1.148078743906213
20240812-22:13:10 test_perplexity 95 model 0 1.1502539958917333
20240812-22:13:54 test_accuracy 95 model 2 val 777 / 807
20240812-22:13:56 test_accuracy 95 model 0 val 789 / 814
20240812-22:13:58 wrote gpt_002.pth
20240812-22:13:58 wrote gpt_000.pth
20240812-22:14:11 wrote non_validated_0095_02.png
20240812-22:14:24 wrote non_validated_0095_00.png
20240812-22:14:24 wrote state.pth
20240812-22:14:24 --- epoch 96 ----------------------------------------
20240812-22:14:24 current_test_accuracies 0.9693 0.9527 0.9628 0.9625 0.9554
20240812-22:15:40 keep c_quizzes model 3 validated 25 / 410 (6.10%) nb_accumulated 25 / 410 (finishes Mon 22:34 -- 1195/h)
20240812-22:16:28 keep c_quizzes model 3 validated 19 / 410 (4.63%) nb_accumulated 44 / 410 (finishes Mon 22:33 -- 1280/h)
20240812-22:17:17 keep c_quizzes model 4 validated 13 / 410 (3.17%) nb_accumulated 57 / 410 (finishes Mon 22:35 -- 1191/h)
20240812-22:18:05 keep c_quizzes model 1 validated 16 / 410 (3.90%) nb_accumulated 73 / 410 (finishes Mon 22:35 -- 1189/h)
20240812-22:18:54 keep c_quizzes model 4 validated 15 / 410 (3.66%) nb_accumulated 88 / 410 (finishes Mon 22:35 -- 1176/h)
20240812-22:19:42 keep c_quizzes model 3 validated 17 / 410 (4.15%) nb_accumulated 105 / 410 (finishes Mon 22:35 -- 1189/h)
20240812-22:20:31 keep c_quizzes model 0 validated 17 / 410 (4.15%) nb_accumulated 122 / 410 (finishes Mon 22:34 -- 1199/h)
20240812-22:21:19 keep c_quizzes model 4 validated 15 / 410 (3.66%) nb_accumulated 137 / 410 (finishes Mon 22:35 -- 1189/h)
20240812-22:22:07 keep c_quizzes model 1 validated 14 / 410 (3.41%) nb_accumulated 151 / 410 (finishes Mon 22:35 -- 1174/h)
20240812-22:22:56 keep c_quizzes model 0 validated 21 / 410 (5.12%) nb_accumulated 172 / 410 (finishes Mon 22:34 -- 1210/h)
20240812-22:23:44 keep c_quizzes model 2 validated 25 / 410 (6.10%) nb_accumulated 197 / 410 (finishes Mon 22:33 -- 1266/h)
20240812-22:24:33 keep c_quizzes model 2 validated 23 / 410 (5.61%) nb_accumulated 220 / 410 (finishes Mon 22:33 -- 1300/h)
20240812-22:25:22 keep c_quizzes model 0 validated 19 / 410 (4.63%) nb_accumulated 239 / 410 (finishes Mon 22:33 -- 1308/h)
20240812-22:26:10 keep c_quizzes model 0 validated 19 / 410 (4.63%) nb_accumulated 258 / 410 (finishes Mon 22:33 -- 1316/h)
20240812-22:26:58 keep c_quizzes model 0 validated 19 / 410 (4.63%) nb_accumulated 277 / 410 (finishes Mon 22:33 -- 1322/h)
20240812-22:27:47 keep c_quizzes model 0 validated 23 / 410 (5.61%) nb_accumulated 300 / 410 (finishes Mon 22:32 -- 1345/h)
20240812-22:28:35 keep c_quizzes model 3 validated 29 / 410 (7.07%) nb_accumulated 329 / 410 (finishes Mon 22:32 -- 1391/h)
20240812-22:29:24 keep c_quizzes model 1 validated 16 / 410 (3.90%) nb_accumulated 345 / 410 (finishes Mon 22:32 -- 1380/h)
20240812-22:30:12 keep c_quizzes model 0 validated 10 / 410 (2.44%) nb_accumulated 355 / 410 (finishes Mon 22:32 -- 1347/h)
20240812-22:31:01 keep c_quizzes model 1 validated 30 / 410 (7.32%) nb_accumulated 385 / 410 (finishes Mon 22:32 -- 1390/h)
20240812-22:31:50 keep c_quizzes model 0 validated 20 / 410 (4.88%) nb_accumulated 405 / 410 (finishes Mon 22:32 -- 1394/h)
20240812-22:32:38 keep c_quizzes model 1 validated 14 / 410 (3.41%) nb_accumulated 419 / 410 (finishes now! -- 1378/h)
20240812-22:32:42 wrote c_quizzes.pth
20240812-22:32:42 training model 0
20240812-22:32:42 training model 1
20240812-22:36:26 train_perplexity 96 model 0 1.1516218538948642
20240812-22:36:27 train_perplexity 96 model 1 1.152962770935724
20240812-22:36:29 test_perplexity 96 model 0 1.149217943991951
20240812-22:36:30 test_perplexity 96 model 1 1.1493612503373174
20240812-22:37:14 test_accuracy 96 model 0 val 782 / 819
20240812-22:37:15 test_accuracy 96 model 1 val 772 / 810
20240812-22:37:17 wrote gpt_000.pth
20240812-22:37:17 wrote gpt_001.pth
20240812-22:37:30 wrote non_validated_0096_00.png
20240812-22:37:43 wrote non_validated_0096_01.png
20240812-22:37:43 wrote state.pth
20240812-22:37:43 --- epoch 97 ----------------------------------------
20240812-22:37:43 current_test_accuracies 0.9548 0.9531 0.0000 0.0000 0.0000
20240812-22:37:43 training model 2
20240812-22:37:43 training model 3
20240812-22:41:27 train_perplexity 97 model 2 1.1511754720214844
20240812-22:41:29 test_perplexity 97 model 2 1.1502124597028907
20240812-22:41:30 train_perplexity 97 model 3 1.1521487385245943
20240812-22:41:32 test_perplexity 97 model 3 1.1480812347909708
20240812-22:42:15 test_accuracy 97 model 2 val 778 / 812
20240812-22:42:17 test_accuracy 97 model 3 val 760 / 790
20240812-22:42:19 wrote gpt_002.pth
20240812-22:42:20 wrote gpt_003.pth
20240812-22:42:33 wrote non_validated_0097_02.png
20240812-22:42:47 wrote non_validated_0097_03.png
20240812-22:42:47 wrote state.pth
20240812-22:42:47 --- epoch 98 ----------------------------------------
20240812-22:42:47 current_test_accuracies 0.9548 0.9531 0.9581 0.9620 0.0000
20240812-22:42:47 training model 4
20240812-22:42:47 training model 1
20240812-22:46:32 train_perplexity 98 model 4 1.151576492977701
20240812-22:46:33 train_perplexity 98 model 1 1.1528266347291611
20240812-22:46:34 test_perplexity 98 model 4 1.1504347408746596
20240812-22:46:36 test_perplexity 98 model 1 1.1488486943637366
20240812-22:47:19 test_accuracy 98 model 4 val 759 / 812
20240812-22:47:20 test_accuracy 98 model 1 val 758 / 788
20240812-22:47:22 wrote gpt_004.pth
20240812-22:47:23 wrote gpt_001.pth
20240812-22:47:36 wrote non_validated_0098_04.png
20240812-22:47:49 wrote non_validated_0098_01.png
20240812-22:47:49 wrote state.pth
20240812-22:47:49 --- epoch 99 ----------------------------------------
20240812-22:47:49 current_test_accuracies 0.9548 0.9619 0.9581 0.9620 0.9347
20240812-22:47:49 training model 4
20240812-22:47:49 training model 0
20240812-22:51:34 train_perplexity 99 model 4 1.1518549079483362
20240812-22:51:36 test_perplexity 99 model 4 1.147638644428178
20240812-22:51:36 train_perplexity 99 model 0 1.1520877839978578
20240812-22:51:38 test_perplexity 99 model 0 1.149623242569892
20240812-22:52:21 test_accuracy 99 model 0 val 770 / 801
20240812-22:52:22 test_accuracy 99 model 4 val 745 / 775
20240812-22:52:24 wrote gpt_004.pth
20240812-22:52:25 wrote gpt_000.pth
20240812-22:52:38 wrote non_validated_0099_04.png
20240812-22:52:51 wrote non_validated_0099_00.png
20240812-22:52:51 wrote state.pth
20240812-22:52:51 --- epoch 100 ----------------------------------------
20240812-22:52:51 current_test_accuracies 0.9613 0.9619 0.9581 0.9620 0.9613
20240812-22:54:01 keep c_quizzes model 1 validated 15 / 410 (3.66%) nb_accumulated 15 / 410 (finishes Mon 23:24 -- 771/h)
20240812-22:54:49 keep c_quizzes model 3 validated 21 / 410 (5.12%) nb_accumulated 36 / 410 (finishes Mon 23:15 -- 1093/h)
20240812-22:55:38 keep c_quizzes model 2 validated 14 / 410 (3.41%) nb_accumulated 50 / 410 (finishes Mon 23:15 -- 1079/h)
20240812-22:56:26 keep c_quizzes model 0 validated 21 / 410 (5.12%) nb_accumulated 71 / 410 (finishes Mon 23:13 -- 1187/h)
20240812-22:57:14 keep c_quizzes model 0 validated 17 / 410 (4.15%) nb_accumulated 88 / 410 (finishes Mon 23:13 -- 1202/h)
20240812-22:58:03 keep c_quizzes model 3 validated 14 / 410 (3.41%) nb_accumulated 102 / 410 (finishes Mon 23:13 -- 1178/h)
20240812-22:58:51 keep c_quizzes model 2 validated 13 / 410 (3.17%) nb_accumulated 115 / 410 (finishes Mon 23:14 -- 1150/h)
20240812-22:59:39 keep c_quizzes model 2 validated 17 / 410 (4.15%) nb_accumulated 132 / 410 (finishes Mon 23:13 -- 1163/h)
20240812-23:00:27 keep c_quizzes model 4 validated 16 / 410 (3.90%) nb_accumulated 148 / 410 (finishes Mon 23:13 -- 1167/h)
20240812-23:01:16 keep c_quizzes model 0 validated 20 / 410 (4.88%) nb_accumulated 168 / 410 (finishes Mon 23:13 -- 1197/h)
20240812-23:02:04 keep c_quizzes model 1 validated 9 / 410 (2.20%) nb_accumulated 177 / 410 (finishes Mon 23:14 -- 1151/h)
20240812-23:02:52 keep c_quizzes model 2 validated 22 / 410 (5.37%) nb_accumulated 199 / 410 (finishes Mon 23:13 -- 1191/h)
20240812-23:03:41 keep c_quizzes model 0 validated 17 / 410 (4.15%) nb_accumulated 216 / 410 (finishes Mon 23:13 -- 1196/h)
20240812-23:04:29 keep c_quizzes model 0 validated 11 / 410 (2.68%) nb_accumulated 227 / 410 (finishes Mon 23:13 -- 1170/h)
20240812-23:05:18 keep c_quizzes model 1 validated 20 / 410 (4.88%) nb_accumulated 247 / 410 (finishes Mon 23:13 -- 1190/h)
20240812-23:06:06 keep c_quizzes model 2 validated 13 / 410 (3.17%) nb_accumulated 260 / 410 (finishes Mon 23:13 -- 1177/h)
20240812-23:06:54 keep c_quizzes model 2 validated 14 / 410 (3.41%) nb_accumulated 274 / 410 (finishes Mon 23:13 -- 1169/h)
20240812-23:07:42 keep c_quizzes model 3 validated 14 / 410 (3.41%) nb_accumulated 288 / 410 (finishes Mon 23:14 -- 1163/h)
20240812-23:08:31 keep c_quizzes model 4 validated 22 / 410 (5.37%) nb_accumulated 310 / 410 (finishes Mon 23:13 -- 1187/h)
20240812-23:09:19 keep c_quizzes model 2 validated 14 / 410 (3.41%) nb_accumulated 324 / 410 (finishes Mon 23:13 -- 1180/h)
20240812-23:10:07 keep c_quizzes model 3 validated 13 / 410 (3.17%) nb_accumulated 337 / 410 (finishes Mon 23:13 -- 1170/h)
20240812-23:10:56 keep c_quizzes model 3 validated 15 / 410 (3.66%) nb_accumulated 352 / 410 (finishes Mon 23:13 -- 1168/h)
20240812-23:11:44 keep c_quizzes model 3 validated 11 / 410 (2.68%) nb_accumulated 363 / 410 (finishes Mon 23:14 -- 1153/h)
20240812-23:12:32 keep c_quizzes model 1 validated 19 / 410 (4.63%) nb_accumulated 382 / 410 (finishes Mon 23:13 -- 1164/h)
20240812-23:13:20 keep c_quizzes model 4 validated 10 / 410 (2.44%) nb_accumulated 392 / 410 (finishes Mon 23:14 -- 1147/h)
20240812-23:14:08 keep c_quizzes model 3 validated 11 / 410 (2.68%) nb_accumulated 403 / 410 (finishes Mon 23:14 -- 1135/h)
20240812-23:14:57 keep c_quizzes model 4 validated 17 / 410 (4.15%) nb_accumulated 420 / 410 (finishes now! -- 1140/h)
20240812-23:15:00 wrote c_quizzes.pth
20240812-23:15:00 training model 0
20240812-23:15:00 training model 1
20240812-23:18:45 train_perplexity 100 model 0 1.1520588836628078
20240812-23:18:45 train_perplexity 100 model 1 1.1531986944989803
20240812-23:18:49 test_perplexity 100 model 0 1.151190406952795
20240812-23:18:49 test_perplexity 100 model 1 1.1494955579073698
20240812-23:19:33 test_accuracy 100 model 0 val 753 / 800
20240812-23:19:34 test_accuracy 100 model 1 val 779 / 814
20240812-23:19:36 wrote gpt_000.pth
20240812-23:19:37 wrote gpt_001.pth
20240812-23:19:50 wrote non_validated_0100_00.png
20240812-23:20:03 wrote non_validated_0100_01.png
20240812-23:20:03 wrote state.pth
20240812-23:20:03 --- epoch 101 ----------------------------------------
20240812-23:20:03 current_test_accuracies 0.9413 0.9570 0.0000 0.0000 0.0000
20240812-23:20:03 training model 2
20240812-23:20:03 training model 3
20240812-23:23:49 train_perplexity 101 model 2 1.1513435628088986
20240812-23:23:49 train_perplexity 101 model 3 1.1525487328020279
20240812-23:23:52 test_perplexity 101 model 2 1.148487071172886
20240812-23:23:53 test_perplexity 101 model 3 1.1502764573815625
20240812-23:24:39 test_accuracy 101 model 3 val 750 / 789
20240812-23:24:41 test_accuracy 101 model 2 val 762 / 793
20240812-23:24:42 wrote gpt_002.pth
20240812-23:24:43 wrote gpt_003.pth
20240812-23:24:56 wrote non_validated_0101_02.png
20240812-23:25:09 wrote non_validated_0101_03.png
20240812-23:25:09 wrote state.pth
20240812-23:25:09 --- epoch 102 ----------------------------------------
20240812-23:25:09 current_test_accuracies 0.9413 0.9570 0.9609 0.9506 0.0000
20240812-23:25:09 training model 4
20240812-23:25:09 training model 0
20240812-23:28:54 train_perplexity 102 model 4 1.1521147996832484
20240812-23:28:56 test_perplexity 102 model 4 1.1497012559517277
20240812-23:28:56 train_perplexity 102 model 0 1.1520871614259696
20240812-23:28:58 test_perplexity 102 model 0 1.148553450212902
20240812-23:29:41 test_accuracy 102 model 4 val 756 / 802
20240812-23:29:43 test_accuracy 102 model 0 val 756 / 804
20240812-23:29:45 wrote gpt_004.pth
20240812-23:29:45 wrote gpt_000.pth
20240812-23:29:58 wrote non_validated_0102_04.png
20240812-23:30:11 wrote non_validated_0102_00.png
20240812-23:30:11 wrote state.pth
20240812-23:30:11 --- epoch 103 ----------------------------------------
20240812-23:30:11 current_test_accuracies 0.9403 0.9570 0.9609 0.9506 0.9426
20240812-23:30:11 training model 0
20240812-23:30:11 training model 4
20240812-23:33:55 train_perplexity 103 model 0 1.1516369530162405
20240812-23:33:57 test_perplexity 103 model 0 1.1495497693272096
20240812-23:33:58 train_perplexity 103 model 4 1.152175516290789
20240812-23:34:01 test_perplexity 103 model 4 1.1515934848066038
20240812-23:34:45 test_accuracy 103 model 4 val 761 / 806
20240812-23:34:45 test_accuracy 103 model 0 val 745 / 779
20240812-23:34:47 wrote gpt_000.pth
20240812-23:34:48 wrote gpt_004.pth
20240812-23:35:01 wrote non_validated_0103_00.png
20240812-23:35:14 wrote non_validated_0103_04.png
20240812-23:35:14 wrote state.pth
20240812-23:35:14 --- epoch 104 ----------------------------------------
20240812-23:35:14 current_test_accuracies 0.9564 0.9570 0.9609 0.9506 0.9442
20240812-23:35:14 training model 4
20240812-23:35:14 training model 3
20240812-23:39:00 train_perplexity 104 model 4 1.1518073062009675
20240812-23:39:00 train_perplexity 104 model 3 1.1522560729594555
20240812-23:39:02 test_perplexity 104 model 4 1.1516726418286787
20240812-23:39:04 test_perplexity 104 model 3 1.1476275486154213
20240812-23:39:51 test_accuracy 104 model 4 val 769 / 798
20240812-23:39:51 test_accuracy 104 model 3 val 767 / 798
20240812-23:39:53 wrote gpt_004.pth
20240812-23:39:54 wrote gpt_003.pth
20240812-23:40:07 wrote non_validated_0104_04.png
20240812-23:40:20 wrote non_validated_0104_03.png
20240812-23:40:20 wrote state.pth
20240812-23:40:20 --- epoch 105 ----------------------------------------
20240812-23:40:20 current_test_accuracies 0.9564 0.9570 0.9609 0.9612 0.9637
20240812-23:41:30 keep c_quizzes model 0 validated 16 / 410 (3.90%) nb_accumulated 16 / 410 (finishes Tue 00:10 -- 828/h)
20240812-23:42:18 keep c_quizzes model 1 validated 14 / 410 (3.41%) nb_accumulated 30 / 410 (finishes Tue 00:07 -- 915/h)
20240812-23:43:06 keep c_quizzes model 3 validated 14 / 410 (3.41%) nb_accumulated 44 / 410 (finishes Tue 00:06 -- 954/h)
20240812-23:43:54 keep c_quizzes model 3 validated 17 / 410 (4.15%) nb_accumulated 61 / 410 (finishes Tue 00:04 -- 1025/h)
20240812-23:44:42 keep c_quizzes model 0 validated 15 / 410 (3.66%) nb_accumulated 76 / 410 (finishes Tue 00:03 -- 1043/h)
20240812-23:45:31 keep c_quizzes model 2 validated 11 / 410 (2.68%) nb_accumulated 87 / 410 (finishes Tue 00:04 -- 1009/h)
20240812-23:46:19 keep c_quizzes model 0 validated 15 / 410 (3.66%) nb_accumulated 102 / 410 (finishes Tue 00:04 -- 1022/h)
20240812-23:47:08 keep c_quizzes model 4 validated 11 / 410 (2.68%) nb_accumulated 113 / 410 (finishes Tue 00:04 -- 998/h)
20240812-23:47:56 keep c_quizzes model 4 validated 12 / 410 (2.93%) nb_accumulated 125 / 410 (finishes Tue 00:05 -- 986/h)
20240812-23:48:44 keep c_quizzes model 0 validated 13 / 410 (3.17%) nb_accumulated 138 / 410 (finishes Tue 00:05 -- 985/h)
20240812-23:49:32 keep c_quizzes model 1 validated 14 / 410 (3.41%) nb_accumulated 152 / 410 (finishes Tue 00:05 -- 990/h)
20240812-23:50:21 keep c_quizzes model 3 validated 9 / 410 (2.20%) nb_accumulated 161 / 410 (finishes Tue 00:05 -- 964/h)
20240812-23:51:10 keep c_quizzes model 3 validated 13 / 410 (3.17%) nb_accumulated 174 / 410 (finishes Tue 00:05 -- 964/h)
20240812-23:51:58 keep c_quizzes model 4 validated 19 / 410 (4.63%) nb_accumulated 193 / 410 (finishes Tue 00:05 -- 995/h)
20240812-23:52:46 keep c_quizzes model 4 validated 9 / 410 (2.20%) nb_accumulated 202 / 410 (finishes Tue 00:05 -- 974/h)
20240812-23:53:34 keep c_quizzes model 0 validated 7 / 410 (1.71%) nb_accumulated 209 / 410 (finishes Tue 00:06 -- 947/h)
20240812-23:54:23 keep c_quizzes model 1 validated 13 / 410 (3.17%) nb_accumulated 222 / 410 (finishes Tue 00:06 -- 948/h)
20240812-23:55:11 keep c_quizzes model 4 validated 12 / 410 (2.93%) nb_accumulated 234 / 410 (finishes Tue 00:06 -- 946/h)
20240812-23:55:59 keep c_quizzes model 3 validated 17 / 410 (4.15%) nb_accumulated 251 / 410 (finishes Tue 00:05 -- 962/h)
20240812-23:56:47 keep c_quizzes model 1 validated 14 / 410 (3.41%) nb_accumulated 265 / 410 (finishes Tue 00:05 -- 966/h)
20240812-23:57:35 keep c_quizzes model 1 validated 12 / 410 (2.93%) nb_accumulated 277 / 410 (finishes Tue 00:05 -- 963/h)
20240812-23:58:24 keep c_quizzes model 2 validated 14 / 410 (3.41%) nb_accumulated 291 / 410 (finishes Tue 00:05 -- 966/h)
20240812-23:59:12 keep c_quizzes model 2 validated 10 / 410 (2.44%) nb_accumulated 301 / 410 (finishes Tue 00:06 -- 957/h)
20240813-00:00:00 keep c_quizzes model 4 validated 11 / 410 (2.68%) nb_accumulated 312 / 410 (finishes Tue 00:06 -- 951/h)
20240813-00:00:49 keep c_quizzes model 4 validated 17 / 410 (4.15%) nb_accumulated 329 / 410 (finishes Tue 00:05 -- 964/h)
20240813-00:01:37 keep c_quizzes model 4 validated 17 / 410 (4.15%) nb_accumulated 346 / 410 (finishes Tue 00:05 -- 975/h)
20240813-00:02:25 keep c_quizzes model 1 validated 12 / 410 (2.93%) nb_accumulated 358 / 410 (finishes Tue 00:05 -- 972/h)
20240813-00:03:13 keep c_quizzes model 0 validated 8 / 410 (1.95%) nb_accumulated 366 / 410 (finishes Tue 00:05 -- 959/h)
20240813-00:04:03 keep c_quizzes model 1 validated 13 / 410 (3.17%) nb_accumulated 379 / 410 (finishes Tue 00:05 -- 959/h)
20240813-00:04:51 keep c_quizzes model 2 validated 19 / 410 (4.63%) nb_accumulated 398 / 410 (finishes Tue 00:05 -- 974/h)
20240813-00:05:39 keep c_quizzes model 2 validated 14 / 410 (3.41%) nb_accumulated 412 / 410 (finishes now! -- 976/h)
20240813-00:05:42 wrote c_quizzes.pth
20240813-00:05:42 training model 0
20240813-00:05:42 training model 1
20240813-00:09:27 train_perplexity 105 model 0 1.1525924297126486
20240813-00:09:27 train_perplexity 105 model 1 1.1531417149936436
20240813-00:09:30 test_perplexity 105 model 0 1.149082993582899
20240813-00:09:31 test_perplexity 105 model 1 1.1474979415983382
20240813-00:10:16 test_accuracy 105 model 0 val 769 / 810
20240813-00:10:18 test_accuracy 105 model 1 val 761 / 795
20240813-00:10:20 wrote gpt_000.pth
20240813-00:10:21 wrote gpt_001.pth
20240813-00:10:34 wrote non_validated_0105_00.png
20240813-00:10:46 wrote non_validated_0105_01.png
20240813-00:10:46 wrote state.pth
20240813-00:10:46 --- epoch 106 ----------------------------------------
20240813-00:10:46 current_test_accuracies 0.9494 0.9572 0.0000 0.0000 0.0000
20240813-00:10:46 training model 2
20240813-00:10:46 training model 3
20240813-00:14:31 train_perplexity 106 model 2 1.1522406888321282
20240813-00:14:33 test_perplexity 106 model 2 1.1534667446289435
20240813-00:14:33 train_perplexity 106 model 3 1.15290236455629
20240813-00:14:36 test_perplexity 106 model 3 1.1473384042159338
20240813-00:15:17 test_accuracy 106 model 2 val 766 / 815
20240813-00:15:20 test_accuracy 106 model 3 val 748 / 781
20240813-00:15:22 wrote gpt_002.pth
20240813-00:15:23 wrote gpt_003.pth
20240813-00:15:36 wrote non_validated_0106_02.png
20240813-00:15:49 wrote non_validated_0106_03.png
20240813-00:15:49 wrote state.pth
20240813-00:15:49 --- epoch 107 ----------------------------------------
20240813-00:15:49 current_test_accuracies 0.9494 0.9572 0.9399 0.9577 0.0000
20240813-00:15:49 training model 4
20240813-00:15:49 training model 2
20240813-00:19:34 train_perplexity 107 model 4 1.15209870983598
20240813-00:19:36 test_perplexity 107 model 4 1.1483343274832494
20240813-00:19:36 train_perplexity 107 model 2 1.151939961795292
20240813-00:19:38 test_perplexity 107 model 2 1.1488230248687126
20240813-00:20:22 test_accuracy 107 model 4 val 748 / 781
20240813-00:20:25 test_accuracy 107 model 2 val 768 / 797
20240813-00:20:27 wrote gpt_004.pth
20240813-00:20:28 wrote gpt_002.pth
20240813-00:20:41 wrote non_validated_0107_04.png
20240813-00:20:54 wrote non_validated_0107_02.png
20240813-00:20:54 wrote state.pth
20240813-00:20:54 --- epoch 108 ----------------------------------------
20240813-00:20:54 current_test_accuracies 0.9494 0.9572 0.9636 0.9577 0.9577
20240813-00:20:54 training model 0
20240813-00:20:54 training model 1
20240813-00:24:39 train_perplexity 108 model 0 1.1516435513940009
20240813-00:24:41 test_perplexity 108 model 0 1.1530247448945752
20240813-00:24:41 train_perplexity 108 model 1 1.1535984302420514
20240813-00:24:43 test_perplexity 108 model 1 1.1525812945170464
20240813-00:25:28 test_accuracy 108 model 1 val 767 / 808
20240813-00:25:30 test_accuracy 108 model 0 val 746 / 779
20240813-00:25:32 wrote gpt_000.pth
20240813-00:25:33 wrote gpt_001.pth
20240813-00:25:46 wrote non_validated_0108_00.png
20240813-00:25:59 wrote non_validated_0108_01.png
20240813-00:25:59 wrote state.pth
20240813-00:25:59 --- epoch 109 ----------------------------------------
20240813-00:25:59 current_test_accuracies 0.9576 0.9493 0.9636 0.9577 0.9577
20240813-00:25:59 training model 1
20240813-00:25:59 training model 0
20240813-00:29:44 train_perplexity 109 model 1 1.152990067268367
20240813-00:29:45 train_perplexity 109 model 0 1.1519995957043079
20240813-00:29:47 test_perplexity 109 model 1 1.1491443307674494
20240813-00:29:48 test_perplexity 109 model 0 1.1501229527830368
20240813-00:30:32 test_accuracy 109 model 1 val 772 / 806
20240813-00:30:33 test_accuracy 109 model 0 val 770 / 801
20240813-00:30:35 wrote gpt_001.pth
20240813-00:30:36 wrote gpt_000.pth
20240813-00:30:49 wrote non_validated_0109_01.png
20240813-00:31:02 wrote non_validated_0109_00.png
20240813-00:31:02 wrote state.pth
20240813-00:31:02 --- epoch 110 ----------------------------------------
20240813-00:31:02 current_test_accuracies 0.9613 0.9578 0.9636 0.9577 0.9577
20240813-00:32:15 keep c_quizzes model 0 validated 16 / 410 (3.90%) nb_accumulated 16 / 410 (finishes Tue 01:01 -- 794/h)
20240813-00:33:03 keep c_quizzes model 4 validated 17 / 410 (4.15%) nb_accumulated 33 / 410 (finishes Tue 00:56 -- 981/h)
20240813-00:33:52 keep c_quizzes model 3 validated 15 / 410 (3.66%) nb_accumulated 48 / 410 (finishes Tue 00:55 -- 1016/h)
20240813-00:34:41 keep c_quizzes model 4 validated 9 / 410 (2.20%) nb_accumulated 57 / 410 (finishes Tue 00:57 -- 939/h)
20240813-00:35:29 keep c_quizzes model 0 validated 13 / 410 (3.17%) nb_accumulated 70 / 410 (finishes Tue 00:57 -- 944/h)
20240813-00:36:18 keep c_quizzes model 2 validated 17 / 410 (4.15%) nb_accumulated 87 / 410 (finishes Tue 00:55 -- 991/h)
20240813-00:37:07 keep c_quizzes model 2 validated 18 / 410 (4.39%) nb_accumulated 105 / 410 (finishes Tue 00:54 -- 1036/h)
20240813-00:37:56 keep c_quizzes model 2 validated 15 / 410 (3.66%) nb_accumulated 120 / 410 (finishes Tue 00:54 -- 1045/h)
20240813-00:38:44 keep c_quizzes model 4 validated 18 / 410 (4.39%) nb_accumulated 138 / 410 (finishes Tue 00:53 -- 1075/h)
20240813-00:39:33 keep c_quizzes model 2 validated 9 / 410 (2.20%) nb_accumulated 147 / 410 (finishes Tue 00:54 -- 1036/h)
20240813-00:40:21 keep c_quizzes model 2 validated 14 / 410 (3.41%) nb_accumulated 161 / 410 (finishes Tue 00:54 -- 1036/h)
20240813-00:41:11 keep c_quizzes model 2 validated 21 / 410 (5.12%) nb_accumulated 182 / 410 (finishes Tue 00:53 -- 1076/h)
20240813-00:42:00 keep c_quizzes model 4 validated 7 / 410 (1.71%) nb_accumulated 189 / 410 (finishes Tue 00:54 -- 1035/h)
20240813-00:42:48 keep c_quizzes model 4 validated 25 / 410 (6.10%) nb_accumulated 214 / 410 (finishes Tue 00:53 -- 1090/h)
20240813-00:43:37 keep c_quizzes model 3 validated 5 / 410 (1.22%) nb_accumulated 219 / 410 (finishes Tue 00:54 -- 1044/h)
20240813-00:44:25 keep c_quizzes model 0 validated 12 / 410 (2.93%) nb_accumulated 231 / 410 (finishes Tue 00:54 -- 1035/h)
20240813-00:45:15 keep c_quizzes model 3 validated 12 / 410 (2.93%) nb_accumulated 243 / 410 (finishes Tue 00:55 -- 1026/h)
20240813-00:46:04 keep c_quizzes model 2 validated 17 / 410 (4.15%) nb_accumulated 260 / 410 (finishes Tue 00:54 -- 1038/h)
20240813-00:46:53 keep c_quizzes model 1 validated 21 / 410 (5.12%) nb_accumulated 281 / 410 (finishes Tue 00:54 -- 1064/h)
20240813-00:47:42 keep c_quizzes model 3 validated 23 / 410 (5.61%) nb_accumulated 304 / 410 (finishes Tue 00:53 -- 1094/h)
20240813-00:48:30 keep c_quizzes model 0 validated 22 / 410 (5.37%) nb_accumulated 326 / 410 (finishes Tue 00:53 -- 1119/h)
20240813-00:49:19 keep c_quizzes model 0 validated 18 / 410 (4.39%) nb_accumulated 344 / 410 (finishes Tue 00:52 -- 1129/h)
20240813-00:50:08 keep c_quizzes model 0 validated 16 / 410 (3.90%) nb_accumulated 360 / 410 (finishes Tue 00:52 -- 1131/h)
20240813-00:50:57 keep c_quizzes model 1 validated 10 / 410 (2.44%) nb_accumulated 370 / 410 (finishes Tue 00:53 -- 1114/h)
20240813-00:51:46 keep c_quizzes model 2 validated 17 / 410 (4.15%) nb_accumulated 387 / 410 (finishes Tue 00:53 -- 1119/h)
20240813-00:52:35 keep c_quizzes model 1 validated 16 / 410 (3.90%) nb_accumulated 403 / 410 (finishes Tue 00:52 -- 1121/h)
20240813-00:53:24 keep c_quizzes model 3 validated 17 / 410 (4.15%) nb_accumulated 420 / 410 (finishes now! -- 1126/h)
20240813-00:53:28 wrote c_quizzes.pth
20240813-00:53:28 training model 0
20240813-00:53:28 training model 1
20240813-00:57:11 train_perplexity 110 model 0 1.152548955912495
20240813-00:57:13 train_perplexity 110 model 1 1.1533048563192696
20240813-00:57:14 test_perplexity 110 model 0 1.151188350824458
20240813-00:57:15 test_perplexity 110 model 1 1.1481752360666895
20240813-00:58:02 test_accuracy 110 model 1 val 751 / 780
20240813-00:58:04 test_accuracy 110 model 0 val 758 / 797
20240813-00:58:06 wrote gpt_000.pth
20240813-00:58:06 wrote gpt_001.pth
20240813-00:58:19 wrote non_validated_0110_00.png
20240813-00:58:32 wrote non_validated_0110_01.png
20240813-00:58:32 wrote state.pth
20240813-00:58:32 --- epoch 111 ----------------------------------------
20240813-00:58:32 current_test_accuracies 0.9511 0.9628 0.0000 0.0000 0.0000
20240813-00:58:32 training model 2
20240813-00:58:32 training model 3
20240813-01:02:17 train_perplexity 111 model 2 1.1519243970856468
20240813-01:02:19 train_perplexity 111 model 3 1.152884048774223
20240813-01:02:20 test_perplexity 111 model 2 1.1497778701469346
20240813-01:02:21 test_perplexity 111 model 3 1.149625891410717
20240813-01:03:05 test_accuracy 111 model 2 val 770 / 817
20240813-01:03:06 test_accuracy 111 model 3 val 765 / 807
20240813-01:03:08 wrote gpt_002.pth
20240813-01:03:09 wrote gpt_003.pth
20240813-01:03:22 wrote non_validated_0111_02.png
20240813-01:03:35 wrote non_validated_0111_03.png
20240813-01:03:35 wrote state.pth
20240813-01:03:35 --- epoch 112 ----------------------------------------
20240813-01:03:35 current_test_accuracies 0.9511 0.9628 0.9425 0.9480 0.0000
20240813-01:03:35 training model 4
20240813-01:03:35 training model 2
20240813-01:07:19 train_perplexity 112 model 4 1.1523849191689925
20240813-01:07:21 test_perplexity 112 model 4 1.1515073259804156
20240813-01:07:22 train_perplexity 112 model 2 1.1523123482981403
20240813-01:07:24 test_perplexity 112 model 2 1.1481730510171808
20240813-01:08:07 test_accuracy 112 model 4 val 757 / 804
20240813-01:08:10 test_accuracy 112 model 2 val 751 / 787
20240813-01:08:12 wrote gpt_004.pth
20240813-01:08:13 wrote gpt_002.pth
20240813-01:08:26 wrote non_validated_0112_04.png
20240813-01:08:39 wrote non_validated_0112_02.png
20240813-01:08:39 wrote state.pth
20240813-01:08:39 --- epoch 113 ----------------------------------------
20240813-01:08:39 current_test_accuracies 0.9511 0.9628 0.9543 0.9480 0.9415
20240813-01:08:39 training model 4
20240813-01:08:39 training model 3
20240813-01:12:24 train_perplexity 113 model 4 1.1524456488044061
20240813-01:12:26 train_perplexity 113 model 3 1.1526746680722804
20240813-01:12:26 test_perplexity 113 model 4 1.151061335144282
20240813-01:12:28 test_perplexity 113 model 3 1.1514941867071273
20240813-01:13:11 test_accuracy 113 model 4 val 763 / 803
20240813-01:13:14 test_accuracy 113 model 3 val 745 / 792
20240813-01:13:16 wrote gpt_004.pth
20240813-01:13:17 wrote gpt_003.pth
20240813-01:13:30 wrote non_validated_0113_04.png
20240813-01:13:43 wrote non_validated_0113_03.png
20240813-01:13:43 wrote state.pth
20240813-01:13:43 --- epoch 114 ----------------------------------------
20240813-01:13:43 current_test_accuracies 0.9511 0.9628 0.9543 0.9407 0.9502
20240813-01:13:43 training model 3
20240813-01:13:43 training model 4
20240813-01:17:28 train_perplexity 114 model 3 1.1523775216408847
20240813-01:17:29 train_perplexity 114 model 4 1.152047641372064
20240813-01:17:31 test_perplexity 114 model 3 1.1496703153294423
20240813-01:17:32 test_perplexity 114 model 4 1.1511826915050982
20240813-01:18:15 test_accuracy 114 model 4 val 777 / 816
20240813-01:18:16 test_accuracy 114 model 3 val 781 / 822
20240813-01:18:18 wrote gpt_003.pth
20240813-01:18:19 wrote gpt_004.pth
20240813-01:18:32 wrote non_validated_0114_03.png
20240813-01:18:45 wrote non_validated_0114_04.png
20240813-01:18:45 wrote state.pth
20240813-01:18:45 --- epoch 115 ----------------------------------------
20240813-01:18:45 current_test_accuracies 0.9511 0.9628 0.9543 0.9501 0.9522
20240813-01:19:55 keep c_quizzes model 3 validated 14 / 410 (3.41%) nb_accumulated 14 / 410 (finishes Tue 01:52 -- 722/h)
20240813-01:20:43 keep c_quizzes model 3 validated 9 / 410 (2.20%) nb_accumulated 23 / 410 (finishes Tue 01:53 -- 701/h)
20240813-01:21:32 keep c_quizzes model 4 validated 4 / 410 (0.98%) nb_accumulated 27 / 410 (finishes Tue 02:00 -- 583/h)
20240813-01:22:20 keep c_quizzes model 0 validated 12 / 410 (2.93%) nb_accumulated 39 / 410 (finishes Tue 01:56 -- 653/h)
20240813-01:23:09 keep c_quizzes model 1 validated 13 / 410 (3.17%) nb_accumulated 52 / 410 (finishes Tue 01:53 -- 710/h)
20240813-01:23:57 keep c_quizzes model 4 validated 10 / 410 (2.44%) nb_accumulated 62 / 410 (finishes Tue 01:53 -- 716/h)
20240813-01:24:45 keep c_quizzes model 4 validated 15 / 410 (3.66%) nb_accumulated 77 / 410 (finishes Tue 01:50 -- 769/h)
20240813-01:25:34 keep c_quizzes model 1 validated 11 / 410 (2.68%) nb_accumulated 88 / 410 (finishes Tue 01:50 -- 775/h)
20240813-01:26:22 keep c_quizzes model 1 validated 16 / 410 (3.90%) nb_accumulated 104 / 410 (finishes Tue 01:48 -- 819/h)
20240813-01:27:10 keep c_quizzes model 2 validated 17 / 410 (4.15%) nb_accumulated 121 / 410 (finishes Tue 01:47 -- 862/h)
20240813-01:27:59 keep c_quizzes model 3 validated 12 / 410 (2.93%) nb_accumulated 133 / 410 (finishes Tue 01:47 -- 864/h)
20240813-01:28:48 keep c_quizzes model 0 validated 6 / 410 (1.46%) nb_accumulated 139 / 410 (finishes Tue 01:48 -- 830/h)
20240813-01:29:36 keep c_quizzes model 0 validated 10 / 410 (2.44%) nb_accumulated 149 / 410 (finishes Tue 01:48 -- 824/h)
20240813-01:30:25 keep c_quizzes model 1 validated 10 / 410 (2.44%) nb_accumulated 159 / 410 (finishes Tue 01:48 -- 818/h)
20240813-01:31:13 keep c_quizzes model 4 validated 12 / 410 (2.93%) nb_accumulated 171 / 410 (finishes Tue 01:48 -- 823/h)
20240813-01:32:02 keep c_quizzes model 0 validated 9 / 410 (2.20%) nb_accumulated 180 / 410 (finishes Tue 01:48 -- 813/h)
20240813-01:32:50 keep c_quizzes model 3 validated 11 / 410 (2.68%) nb_accumulated 191 / 410 (finishes Tue 01:48 -- 814/h)
20240813-01:33:38 keep c_quizzes model 0 validated 8 / 410 (1.95%) nb_accumulated 199 / 410 (finishes Tue 01:49 -- 802/h)
20240813-01:34:27 keep c_quizzes model 2 validated 7 / 410 (1.71%) nb_accumulated 206 / 410 (finishes Tue 01:50 -- 787/h)
20240813-01:35:16 keep c_quizzes model 0 validated 15 / 410 (3.66%) nb_accumulated 221 / 410 (finishes Tue 01:49 -- 803/h)
20240813-01:36:04 keep c_quizzes model 1 validated 9 / 410 (2.20%) nb_accumulated 230 / 410 (finishes Tue 01:49 -- 796/h)
20240813-01:36:53 keep c_quizzes model 3 validated 7 / 410 (1.71%) nb_accumulated 237 / 410 (finishes Tue 01:50 -- 784/h)
20240813-01:37:42 keep c_quizzes model 4 validated 6 / 410 (1.46%) nb_accumulated 243 / 410 (finishes Tue 01:50 -- 769/h)
20240813-01:38:31 keep c_quizzes model 2 validated 14 / 410 (3.41%) nb_accumulated 257 / 410 (finishes Tue 01:50 -- 780/h)
20240813-01:39:20 keep c_quizzes model 3 validated 11 / 410 (2.68%) nb_accumulated 268 / 410 (finishes Tue 01:50 -- 781/h)
20240813-01:40:09 keep c_quizzes model 1 validated 13 / 410 (3.17%) nb_accumulated 281 / 410 (finishes Tue 01:49 -- 788/h)
20240813-01:40:57 keep c_quizzes model 3 validated 14 / 410 (3.41%) nb_accumulated 295 / 410 (finishes Tue 01:49 -- 797/h)
20240813-01:41:46 keep c_quizzes model 0 validated 10 / 410 (2.44%) nb_accumulated 305 / 410 (finishes Tue 01:49 -- 795/h)
20240813-01:42:34 keep c_quizzes model 1 validated 11 / 410 (2.68%) nb_accumulated 316 / 410 (finishes Tue 01:49 -- 796/h)
20240813-01:43:23 keep c_quizzes model 4 validated 8 / 410 (1.95%) nb_accumulated 324 / 410 (finishes Tue 01:49 -- 789/h)
20240813-01:44:11 keep c_quizzes model 3 validated 7 / 410 (1.71%) nb_accumulated 331 / 410 (finishes Tue 01:50 -- 780/h)
20240813-01:45:00 keep c_quizzes model 3 validated 9 / 410 (2.20%) nb_accumulated 340 / 410 (finishes Tue 01:50 -- 777/h)
20240813-01:45:49 keep c_quizzes model 2 validated 10 / 410 (2.44%) nb_accumulated 350 / 410 (finishes Tue 01:50 -- 776/h)
20240813-01:46:37 keep c_quizzes model 4 validated 7 / 410 (1.71%) nb_accumulated 357 / 410 (finishes Tue 01:50 -- 768/h)
20240813-01:47:27 keep c_quizzes model 3 validated 12 / 410 (2.93%) nb_accumulated 369 / 410 (finishes Tue 01:50 -- 771/h)
20240813-01:48:16 keep c_quizzes model 3 validated 12 / 410 (2.93%) nb_accumulated 381 / 410 (finishes Tue 01:50 -- 774/h)
20240813-01:49:04 keep c_quizzes model 2 validated 10 / 410 (2.44%) nb_accumulated 391 / 410 (finishes Tue 01:50 -- 773/h)
20240813-01:49:53 keep c_quizzes model 0 validated 17 / 410 (4.15%) nb_accumulated 408 / 410 (finishes Tue 01:50 -- 786/h)
20240813-01:50:41 keep c_quizzes model 2 validated 10 / 410 (2.44%) nb_accumulated 418 / 410 (finishes now! -- 785/h)
20240813-01:50:44 wrote c_quizzes.pth
20240813-01:50:44 training model 0
20240813-01:50:44 training model 1
20240813-01:54:29 train_perplexity 115 model 0 1.1531382102269232
20240813-01:54:29 train_perplexity 115 model 1 1.153970858569956
20240813-01:54:33 test_perplexity 115 model 0 1.1514090059857334
20240813-01:54:33 test_perplexity 115 model 1 1.1522623858696417
20240813-01:55:17 test_accuracy 115 model 0 val 775 / 805
20240813-01:55:17 test_accuracy 115 model 1 val 770 / 811
20240813-01:55:20 wrote gpt_000.pth
20240813-01:55:20 wrote gpt_001.pth
20240813-01:55:33 wrote non_validated_0115_00.png
20240813-01:55:46 wrote non_validated_0115_01.png
20240813-01:55:46 wrote state.pth
20240813-01:55:46 --- epoch 116 ----------------------------------------
20240813-01:55:46 current_test_accuracies 0.9627 0.9494 0.0000 0.0000 0.0000
20240813-01:55:46 training model 2
20240813-01:55:46 training model 3
20240813-01:59:31 train_perplexity 116 model 2 1.1525739591190491
20240813-01:59:32 train_perplexity 116 model 3 1.1530809160962772
20240813-01:59:33 test_perplexity 116 model 2 1.149624669773992
20240813-01:59:35 test_perplexity 116 model 3 1.1512475483763716
20240813-02:00:19 test_accuracy 116 model 3 val 762 / 800
20240813-02:00:21 test_accuracy 116 model 2 val 769 / 797
20240813-02:00:23 wrote gpt_002.pth
20240813-02:00:24 wrote gpt_003.pth
20240813-02:00:37 wrote non_validated_0116_02.png
20240813-02:00:49 wrote non_validated_0116_03.png
20240813-02:00:50 wrote state.pth
20240813-02:00:50 --- epoch 117 ----------------------------------------
20240813-02:00:50 current_test_accuracies 0.9627 0.9494 0.9649 0.9525 0.0000
20240813-02:00:50 training model 4
20240813-02:00:50 training model 1
20240813-02:04:36 train_perplexity 117 model 4 1.152438674568455
20240813-02:04:37 train_perplexity 117 model 1 1.1533926579350542
20240813-02:04:39 test_perplexity 117 model 4 1.1514770411032371
20240813-02:04:40 test_perplexity 117 model 1 1.1503680621910464
20240813-02:05:22 test_accuracy 117 model 1 val 779 / 808
20240813-02:05:23 test_accuracy 117 model 4 val 761 / 805
20240813-02:05:25 wrote gpt_004.pth
20240813-02:05:26 wrote gpt_001.pth
20240813-02:05:39 wrote non_validated_0117_04.png
20240813-02:05:52 wrote non_validated_0117_01.png
20240813-02:05:52 wrote state.pth
20240813-02:05:52 --- epoch 118 ----------------------------------------
20240813-02:05:52 current_test_accuracies 0.9627 0.9641 0.9649 0.9525 0.9453
20240813-02:05:52 training model 4
20240813-02:05:52 training model 3
20240813-02:09:37 train_perplexity 118 model 4 1.152171895148921
20240813-02:09:39 train_perplexity 118 model 3 1.1533823946038269
20240813-02:09:39 test_perplexity 118 model 4 1.1497938806422976
20240813-02:09:41 test_perplexity 118 model 3 1.151131832855992
20240813-02:10:25 test_accuracy 118 model 3 val 770 / 812
20240813-02:10:26 test_accuracy 118 model 4 val 781 / 821
20240813-02:10:28 wrote gpt_004.pth
20240813-02:10:28 wrote gpt_003.pth
20240813-02:10:41 wrote non_validated_0118_04.png
20240813-02:10:54 wrote non_validated_0118_03.png
20240813-02:10:54 wrote state.pth
20240813-02:10:54 --- epoch 119 ----------------------------------------
20240813-02:10:54 current_test_accuracies 0.9627 0.9641 0.9649 0.9483 0.9513
20240813-02:10:54 training model 3
20240813-02:10:54 training model 4
20240813-02:14:39 train_perplexity 119 model 3 1.1533042985720956
20240813-02:14:41 test_perplexity 119 model 3 1.1496144106463433
20240813-02:14:42 train_perplexity 119 model 4 1.1525398007064729
20240813-02:14:44 test_perplexity 119 model 4 1.1510253552117196
20240813-02:15:27 test_accuracy 119 model 3 val 752 / 781
20240813-02:15:29 test_accuracy 119 model 4 val 785 / 816
20240813-02:15:31 wrote gpt_003.pth
20240813-02:15:31 wrote gpt_004.pth
20240813-02:15:44 wrote non_validated_0119_03.png
20240813-02:15:57 wrote non_validated_0119_04.png
20240813-02:15:57 wrote state.pth
20240813-02:15:57 --- epoch 120 ----------------------------------------
20240813-02:15:57 current_test_accuracies 0.9627 0.9641 0.9649 0.9629 0.9620
20240813-02:17:09 keep c_quizzes model 3 validated 10 / 410 (2.44%) nb_accumulated 10 / 410 (finishes Tue 03:05 -- 501/h)
20240813-02:17:57 keep c_quizzes model 4 validated 17 / 410 (4.15%) nb_accumulated 27 / 410 (finishes Tue 02:46 -- 811/h)
20240813-02:18:45 keep c_quizzes model 2 validated 16 / 410 (3.90%) nb_accumulated 43 / 410 (finishes Tue 02:42 -- 922/h)
20240813-02:19:33 keep c_quizzes model 4 validated 8 / 410 (1.95%) nb_accumulated 51 / 410 (finishes Tue 02:44 -- 850/h)
20240813-02:20:22 keep c_quizzes model 0 validated 11 / 410 (2.68%) nb_accumulated 62 / 410 (finishes Tue 02:45 -- 845/h)
20240813-02:21:10 keep c_quizzes model 3 validated 18 / 410 (4.39%) nb_accumulated 80 / 410 (finishes Tue 02:42 -- 922/h)
20240813-02:21:58 keep c_quizzes model 1 validated 13 / 410 (3.17%) nb_accumulated 93 / 410 (finishes Tue 02:42 -- 929/h)
20240813-02:22:46 keep c_quizzes model 4 validated 17 / 410 (4.15%) nb_accumulated 110 / 410 (finishes Tue 02:41 -- 968/h)
20240813-02:23:35 keep c_quizzes model 1 validated 14 / 410 (3.41%) nb_accumulated 124 / 410 (finishes Tue 02:41 -- 976/h)
20240813-02:24:23 keep c_quizzes model 3 validated 13 / 410 (3.17%) nb_accumulated 137 / 410 (finishes Tue 02:41 -- 976/h)
20240813-02:25:11 keep c_quizzes model 1 validated 18 / 410 (4.39%) nb_accumulated 155 / 410 (finishes Tue 02:40 -- 1008/h)
20240813-02:25:59 keep c_quizzes model 0 validated 14 / 410 (3.41%) nb_accumulated 169 / 410 (finishes Tue 02:40 -- 1011/h)
20240813-02:26:48 keep c_quizzes model 4 validated 10 / 410 (2.44%) nb_accumulated 179 / 410 (finishes Tue 02:40 -- 990/h)
20240813-02:27:36 keep c_quizzes model 3 validated 15 / 410 (3.66%) nb_accumulated 194 / 410 (finishes Tue 02:40 -- 999/h)
20240813-02:28:25 keep c_quizzes model 4 validated 9 / 410 (2.20%) nb_accumulated 203 / 410 (finishes Tue 02:41 -- 978/h)
20240813-02:29:13 keep c_quizzes model 1 validated 10 / 410 (2.44%) nb_accumulated 213 / 410 (finishes Tue 02:41 -- 964/h)
20240813-02:30:01 keep c_quizzes model 0 validated 15 / 410 (3.66%) nb_accumulated 228 / 410 (finishes Tue 02:41 -- 973/h)
20240813-02:30:51 keep c_quizzes model 1 validated 10 / 410 (2.44%) nb_accumulated 238 / 410 (finishes Tue 02:41 -- 959/h)
20240813-02:31:39 keep c_quizzes model 2 validated 16 / 410 (3.90%) nb_accumulated 254 / 410 (finishes Tue 02:41 -- 970/h)
20240813-02:32:28 keep c_quizzes model 2 validated 20 / 410 (4.88%) nb_accumulated 274 / 410 (finishes Tue 02:40 -- 996/h)
20240813-02:33:16 keep c_quizzes model 4 validated 16 / 410 (3.90%) nb_accumulated 290 / 410 (finishes Tue 02:40 -- 1005/h)
20240813-02:34:04 keep c_quizzes model 3 validated 10 / 410 (2.44%) nb_accumulated 300 / 410 (finishes Tue 02:40 -- 994/h)
20240813-02:34:52 keep c_quizzes model 1 validated 18 / 410 (4.39%) nb_accumulated 318 / 410 (finishes Tue 02:40 -- 1008/h)
20240813-02:35:40 keep c_quizzes model 1 validated 14 / 410 (3.41%) nb_accumulated 332 / 410 (finishes Tue 02:40 -- 1010/h)
20240813-02:36:29 keep c_quizzes model 1 validated 17 / 410 (4.15%) nb_accumulated 349 / 410 (finishes Tue 02:40 -- 1020/h)
20240813-02:37:18 keep c_quizzes model 1 validated 17 / 410 (4.15%) nb_accumulated 366 / 410 (finishes Tue 02:39 -- 1029/h)
20240813-02:38:06 keep c_quizzes model 1 validated 9 / 410 (2.20%) nb_accumulated 375 / 410 (finishes Tue 02:40 -- 1016/h)
20240813-02:38:54 keep c_quizzes model 4 validated 13 / 410 (3.17%) nb_accumulated 388 / 410 (finishes Tue 02:40 -- 1014/h)
20240813-02:39:42 keep c_quizzes model 4 validated 9 / 410 (2.20%) nb_accumulated 397 / 410 (finishes Tue 02:40 -- 1003/h)
20240813-02:40:30 keep c_quizzes model 3 validated 12 / 410 (2.93%) nb_accumulated 409 / 410 (finishes Tue 02:40 -- 1000/h)
20240813-02:41:18 keep c_quizzes model 0 validated 19 / 410 (4.63%) nb_accumulated 428 / 410 (finishes now! -- 1013/h)
20240813-02:41:22 wrote c_quizzes.pth
20240813-02:41:22 training model 0
20240813-02:41:22 training model 1
20240813-02:45:05 train_perplexity 120 model 0 1.1536078343789562
20240813-02:45:07 train_perplexity 120 model 1 1.1543572440310388
20240813-02:45:07 test_perplexity 120 model 0 1.1506496418256145
20240813-02:45:09 test_perplexity 120 model 1 1.1499792333784435
20240813-02:45:53 test_accuracy 120 model 1 val 771 / 804
20240813-02:45:55 test_accuracy 120 model 0 val 771 / 809
20240813-02:45:57 wrote gpt_000.pth
20240813-02:45:57 wrote gpt_001.pth
20240813-02:46:10 wrote non_validated_0120_00.png
20240813-02:46:23 wrote non_validated_0120_01.png
20240813-02:46:23 wrote state.pth
20240813-02:46:23 --- epoch 121 ----------------------------------------
20240813-02:46:23 current_test_accuracies 0.9530 0.9590 0.0000 0.0000 0.0000
20240813-02:46:23 training model 2
20240813-02:46:23 training model 3
20240813-02:50:08 train_perplexity 121 model 2 1.1535144444628602
20240813-02:50:10 train_perplexity 121 model 3 1.153208022972942
20240813-02:50:10 test_perplexity 121 model 2 1.1520141727820228
20240813-02:50:12 test_perplexity 121 model 3 1.1523518203914211
20240813-02:50:55 test_accuracy 121 model 2 val 788 / 816
20240813-02:50:57 test_accuracy 121 model 3 val 784 / 813
20240813-02:50:59 wrote gpt_002.pth
20240813-02:51:00 wrote gpt_003.pth
20240813-02:51:13 wrote non_validated_0121_02.png
20240813-02:51:26 wrote non_validated_0121_03.png
20240813-02:51:26 wrote state.pth
20240813-02:51:26 --- epoch 122 ----------------------------------------
20240813-02:51:26 current_test_accuracies 0.9530 0.9590 0.9657 0.9643 0.0000
20240813-02:51:26 training model 4
20240813-02:51:26 training model 0
20240813-02:55:11 train_perplexity 122 model 4 1.153205287180765
20240813-02:55:13 test_perplexity 122 model 4 1.1519354894320804
20240813-02:55:13 train_perplexity 122 model 0 1.153535504422591
20240813-02:55:15 test_perplexity 122 model 0 1.1496760899182472
20240813-02:55:58 test_accuracy 122 model 4 val 772 / 807
20240813-02:56:02 test_accuracy 122 model 0 val 770 / 798
20240813-02:56:04 wrote gpt_004.pth
20240813-02:56:05 wrote gpt_000.pth
20240813-02:56:18 wrote non_validated_0122_04.png
20240813-02:56:31 wrote non_validated_0122_00.png
20240813-02:56:31 wrote state.pth
20240813-02:56:31 --- epoch 123 ----------------------------------------
20240813-02:56:31 current_test_accuracies 0.9649 0.9590 0.9657 0.9643 0.9566
20240813-02:57:42 keep c_quizzes model 2 validated 18 / 410 (4.39%) nb_accumulated 18 / 410 (finishes Tue 03:23 -- 909/h)
20240813-02:58:31 keep c_quizzes model 2 validated 9 / 410 (2.20%) nb_accumulated 27 / 410 (finishes Tue 03:26 -- 810/h)
20240813-02:59:19 keep c_quizzes model 1 validated 10 / 410 (2.44%) nb_accumulated 37 / 410 (finishes Tue 03:27 -- 791/h)
20240813-03:00:08 keep c_quizzes model 2 validated 16 / 410 (3.90%) nb_accumulated 53 / 410 (finishes Tue 03:24 -- 878/h)
20240813-03:00:56 keep c_quizzes model 0 validated 12 / 410 (2.93%) nb_accumulated 65 / 410 (finishes Tue 03:24 -- 881/h)
20240813-03:01:45 keep c_quizzes model 2 validated 13 / 410 (3.17%) nb_accumulated 78 / 410 (finishes Tue 03:24 -- 893/h)
20240813-03:02:33 keep c_quizzes model 2 validated 17 / 410 (4.15%) nb_accumulated 95 / 410 (finishes Tue 03:22 -- 943/h)
20240813-03:03:22 keep c_quizzes model 4 validated 14 / 410 (3.41%) nb_accumulated 109 / 410 (finishes Tue 03:22 -- 954/h)
20240813-03:04:10 keep c_quizzes model 0 validated 13 / 410 (3.17%) nb_accumulated 122 / 410 (finishes Tue 03:22 -- 956/h)
20240813-03:05:00 keep c_quizzes model 2 validated 9 / 410 (2.20%) nb_accumulated 131 / 410 (finishes Tue 03:23 -- 926/h)
20240813-03:05:50 keep c_quizzes model 2 validated 11 / 410 (2.68%) nb_accumulated 142 / 410 (finishes Tue 03:23 -- 914/h)
20240813-03:06:39 keep c_quizzes model 4 validated 8 / 410 (1.95%) nb_accumulated 150 / 410 (finishes Tue 03:24 -- 888/h)
20240813-03:07:28 keep c_quizzes model 0 validated 20 / 410 (4.88%) nb_accumulated 170 / 410 (finishes Tue 03:22 -- 931/h)
20240813-03:08:17 keep c_quizzes model 3 validated 15 / 410 (3.66%) nb_accumulated 185 / 410 (finishes Tue 03:22 -- 943/h)
20240813-03:09:07 keep c_quizzes model 1 validated 12 / 410 (2.93%) nb_accumulated 197 / 410 (finishes Tue 03:22 -- 938/h)
20240813-03:09:55 keep c_quizzes model 2 validated 7 / 410 (1.71%) nb_accumulated 204 / 410 (finishes Tue 03:23 -- 912/h)
20240813-03:10:44 keep c_quizzes model 4 validated 10 / 410 (2.44%) nb_accumulated 214 / 410 (finishes Tue 03:23 -- 902/h)
20240813-03:11:32 keep c_quizzes model 4 validated 12 / 410 (2.93%) nb_accumulated 226 / 410 (finishes Tue 03:23 -- 902/h)
20240813-03:12:21 keep c_quizzes model 3 validated 12 / 410 (2.93%) nb_accumulated 238 / 410 (finishes Tue 03:23 -- 901/h)
20240813-03:13:11 keep c_quizzes model 4 validated 9 / 410 (2.20%) nb_accumulated 247 / 410 (finishes Tue 03:24 -- 889/h)
20240813-03:13:59 keep c_quizzes model 0 validated 12 / 410 (2.93%) nb_accumulated 259 / 410 (finishes Tue 03:24 -- 889/h)
20240813-03:14:48 keep c_quizzes model 0 validated 12 / 410 (2.93%) nb_accumulated 271 / 410 (finishes Tue 03:24 -- 889/h)
20240813-03:15:36 keep c_quizzes model 1 validated 18 / 410 (4.39%) nb_accumulated 289 / 410 (finishes Tue 03:23 -- 908/h)
20240813-03:16:24 keep c_quizzes model 2 validated 17 / 410 (4.15%) nb_accumulated 306 / 410 (finishes Tue 03:23 -- 922/h)
20240813-03:17:13 keep c_quizzes model 3 validated 17 / 410 (4.15%) nb_accumulated 323 / 410 (finishes Tue 03:22 -- 935/h)
20240813-03:18:02 keep c_quizzes model 4 validated 13 / 410 (3.17%) nb_accumulated 336 / 410 (finishes Tue 03:22 -- 936/h)
20240813-03:18:50 keep c_quizzes model 2 validated 8 / 410 (1.95%) nb_accumulated 344 / 410 (finishes Tue 03:23 -- 924/h)
20240813-03:19:39 keep c_quizzes model 3 validated 12 / 410 (2.93%) nb_accumulated 356 / 410 (finishes Tue 03:23 -- 923/h)
20240813-03:20:27 keep c_quizzes model 1 validated 14 / 410 (3.41%) nb_accumulated 370 / 410 (finishes Tue 03:23 -- 927/h)
20240813-03:21:16 keep c_quizzes model 3 validated 10 / 410 (2.44%) nb_accumulated 380 / 410 (finishes Tue 03:23 -- 921/h)
20240813-03:22:04 keep c_quizzes model 1 validated 14 / 410 (3.41%) nb_accumulated 394 / 410 (finishes Tue 03:23 -- 924/h)
20240813-03:22:53 keep c_quizzes model 4 validated 13 / 410 (3.17%) nb_accumulated 407 / 410 (finishes Tue 03:23 -- 926/h)
20240813-03:23:43 keep c_quizzes model 4 validated 11 / 410 (2.68%) nb_accumulated 418 / 410 (finishes now! -- 922/h)
20240813-03:23:46 wrote c_quizzes.pth
20240813-03:23:46 training model 0
20240813-03:23:46 training model 1
20240813-03:27:31 train_perplexity 123 model 0 1.1542337914515781
20240813-03:27:31 train_perplexity 123 model 1 1.154460571704312
20240813-03:27:34 test_perplexity 123 model 0 1.152858363558385
20240813-03:27:35 test_perplexity 123 model 1 1.152850104603447
20240813-03:28:18 test_accuracy 123 model 0 val 773 / 812
20240813-03:28:18 test_accuracy 123 model 1 val 769 / 811
20240813-03:28:21 wrote gpt_000.pth
20240813-03:28:21 wrote gpt_001.pth
20240813-03:28:34 wrote non_validated_0123_00.png
20240813-03:28:47 wrote non_validated_0123_01.png
20240813-03:28:47 wrote state.pth
20240813-03:28:47 --- epoch 124 ----------------------------------------
20240813-03:28:47 current_test_accuracies 0.9520 0.9482 0.0000 0.0000 0.0000
20240813-03:28:47 training model 2
20240813-03:28:47 training model 3
20240813-03:32:32 train_perplexity 124 model 2 1.153951908859041
20240813-03:32:33 train_perplexity 124 model 3 1.154268236633436
20240813-03:32:36 test_perplexity 124 model 2 1.1513869075552148
20240813-03:32:36 test_perplexity 124 model 3 1.1506071462102179
20240813-03:33:25 test_accuracy 124 model 3 val 760 / 795
20240813-03:33:25 test_accuracy 124 model 2 val 745 / 783
20240813-03:33:27 wrote gpt_002.pth
20240813-03:33:28 wrote gpt_003.pth
20240813-03:33:41 wrote non_validated_0124_02.png
20240813-03:33:54 wrote non_validated_0124_03.png
20240813-03:33:54 wrote state.pth
20240813-03:33:54 --- epoch 125 ----------------------------------------
20240813-03:33:54 current_test_accuracies 0.9520 0.9482 0.9515 0.9560 0.0000
20240813-03:33:54 training model 4
20240813-03:33:54 training model 1
20240813-03:37:40 train_perplexity 125 model 4 1.1537419262871342
20240813-03:37:40 train_perplexity 125 model 1 1.1538334908569088
20240813-03:37:43 test_perplexity 125 model 4 1.1517780897256025
20240813-03:37:44 test_perplexity 125 model 1 1.1513746360749968
20240813-03:38:32 test_accuracy 125 model 1 val 770 / 794
20240813-03:38:33 test_accuracy 125 model 4 val 768 / 798
20240813-03:38:35 wrote gpt_004.pth
20240813-03:38:36 wrote gpt_001.pth
20240813-03:38:49 wrote non_validated_0125_04.png
20240813-03:39:02 wrote non_validated_0125_01.png
20240813-03:39:02 wrote state.pth
20240813-03:39:02 --- epoch 126 ----------------------------------------
20240813-03:39:02 current_test_accuracies 0.9520 0.9698 0.9515 0.9560 0.9624
20240813-03:40:16 keep c_quizzes model 2 validated 10 / 410 (2.44%) nb_accumulated 10 / 410 (finishes Tue 04:29 -- 485/h)
20240813-03:41:05 keep c_quizzes model 3 validated 9 / 410 (2.20%) nb_accumulated 19 / 410 (finishes Tue 04:23 -- 556/h)
20240813-03:41:53 keep c_quizzes model 4 validated 10 / 410 (2.44%) nb_accumulated 29 / 410 (finishes Tue 04:19 -- 611/h)
20240813-03:42:41 keep c_quizzes model 2 validated 12 / 410 (2.93%) nb_accumulated 41 / 410 (finishes Tue 04:15 -- 672/h)
20240813-03:43:29 keep c_quizzes model 3 validated 12 / 410 (2.93%) nb_accumulated 53 / 410 (finishes Tue 04:13 -- 713/h)
20240813-03:44:17 keep c_quizzes model 2 validated 13 / 410 (3.17%) nb_accumulated 66 / 410 (finishes Tue 04:11 -- 752/h)
20240813-03:45:06 keep c_quizzes model 0 validated 8 / 410 (1.95%) nb_accumulated 74 / 410 (finishes Tue 04:12 -- 732/h)
20240813-03:45:54 keep c_quizzes model 2 validated 12 / 410 (2.93%) nb_accumulated 86 / 410 (finishes Tue 04:11 -- 751/h)
20240813-03:46:42 keep c_quizzes model 2 validated 10 / 410 (2.44%) nb_accumulated 96 / 410 (finishes Tue 04:11 -- 750/h)
20240813-03:47:30 keep c_quizzes model 4 validated 12 / 410 (2.93%) nb_accumulated 108 / 410 (finishes Tue 04:11 -- 764/h)
20240813-03:48:19 keep c_quizzes model 0 validated 7 / 410 (1.71%) nb_accumulated 115 / 410 (finishes Tue 04:12 -- 743/h)
20240813-03:49:07 keep c_quizzes model 0 validated 15 / 410 (3.66%) nb_accumulated 130 / 410 (finishes Tue 04:10 -- 773/h)
20240813-03:49:55 keep c_quizzes model 3 validated 10 / 410 (2.44%) nb_accumulated 140 / 410 (finishes Tue 04:10 -- 771/h)
20240813-03:50:43 keep c_quizzes model 2 validated 7 / 410 (1.71%) nb_accumulated 147 / 410 (finishes Tue 04:11 -- 754/h)
20240813-03:51:31 keep c_quizzes model 3 validated 13 / 410 (3.17%) nb_accumulated 160 / 410 (finishes Tue 04:11 -- 768/h)
20240813-03:52:19 keep c_quizzes model 1 validated 11 / 410 (2.68%) nb_accumulated 171 / 410 (finishes Tue 04:10 -- 771/h)
20240813-03:53:09 keep c_quizzes model 3 validated 15 / 410 (3.66%) nb_accumulated 186 / 410 (finishes Tue 04:10 -- 790/h)
20240813-03:53:57 keep c_quizzes model 3 validated 13 / 410 (3.17%) nb_accumulated 199 / 410 (finishes Tue 04:09 -- 799/h)
20240813-03:54:45 keep c_quizzes model 2 validated 15 / 410 (3.66%) nb_accumulated 214 / 410 (finishes Tue 04:09 -- 816/h)
20240813-03:55:34 keep c_quizzes model 3 validated 14 / 410 (3.41%) nb_accumulated 228 / 410 (finishes Tue 04:08 -- 827/h)
20240813-03:56:23 keep c_quizzes model 3 validated 11 / 410 (2.68%) nb_accumulated 239 / 410 (finishes Tue 04:08 -- 826/h)
20240813-03:57:11 keep c_quizzes model 1 validated 16 / 410 (3.90%) nb_accumulated 255 / 410 (finishes Tue 04:08 -- 842/h)
20240813-03:57:59 keep c_quizzes model 4 validated 9 / 410 (2.20%) nb_accumulated 264 / 410 (finishes Tue 04:08 -- 835/h)
20240813-03:58:48 keep c_quizzes model 0 validated 13 / 410 (3.17%) nb_accumulated 277 / 410 (finishes Tue 04:08 -- 840/h)
20240813-03:59:36 keep c_quizzes model 2 validated 10 / 410 (2.44%) nb_accumulated 287 / 410 (finishes Tue 04:08 -- 837/h)
20240813-04:00:24 keep c_quizzes model 0 validated 7 / 410 (1.71%) nb_accumulated 294 / 410 (finishes Tue 04:08 -- 825/h)
20240813-04:01:12 keep c_quizzes model 1 validated 8 / 410 (1.95%) nb_accumulated 302 / 410 (finishes Tue 04:09 -- 817/h)
20240813-04:02:01 keep c_quizzes model 1 validated 6 / 410 (1.46%) nb_accumulated 308 / 410 (finishes Tue 04:09 -- 804/h)
20240813-04:02:48 keep c_quizzes model 4 validated 14 / 410 (3.41%) nb_accumulated 322 / 410 (finishes Tue 04:09 -- 812/h)
20240813-04:03:37 keep c_quizzes model 1 validated 13 / 410 (3.17%) nb_accumulated 335 / 410 (finishes Tue 04:09 -- 817/h)
20240813-04:04:25 keep c_quizzes model 1 validated 10 / 410 (2.44%) nb_accumulated 345 / 410 (finishes Tue 04:09 -- 815/h)
20240813-04:05:13 keep c_quizzes model 2 validated 6 / 410 (1.46%) nb_accumulated 351 / 410 (finishes Tue 04:09 -- 804/h)
20240813-04:06:02 keep c_quizzes model 0 validated 8 / 410 (1.95%) nb_accumulated 359 / 410 (finishes Tue 04:09 -- 797/h)
20240813-04:06:50 keep c_quizzes model 3 validated 15 / 410 (3.66%) nb_accumulated 374 / 410 (finishes Tue 04:09 -- 807/h)
20240813-04:07:38 keep c_quizzes model 3 validated 11 / 410 (2.68%) nb_accumulated 385 / 410 (finishes Tue 04:09 -- 807/h)
20240813-04:08:27 keep c_quizzes model 3 validated 13 / 410 (3.17%) nb_accumulated 398 / 410 (finishes Tue 04:09 -- 811/h)
20240813-04:09:16 keep c_quizzes model 1 validated 9 / 410 (2.20%) nb_accumulated 407 / 410 (finishes Tue 04:09 -- 807/h)
20240813-04:10:04 keep c_quizzes model 4 validated 10 / 410 (2.44%) nb_accumulated 417 / 410 (finishes now! -- 806/h)
20240813-04:10:07 wrote c_quizzes.pth
20240813-04:10:07 training model 0
20240813-04:10:07 training model 1
20240813-04:13:52 train_perplexity 126 model 0 1.1548258413795103
20240813-04:13:52 train_perplexity 126 model 1 1.15481877169442
20240813-04:13:56 test_perplexity 126 model 0 1.1536420537876093
20240813-04:13:56 test_perplexity 126 model 1 1.1497740730464547
20240813-04:14:40 test_accuracy 126 model 0 val 772 / 811
20240813-04:14:42 test_accuracy 126 model 1 val 747 / 793
20240813-04:14:44 wrote gpt_000.pth
20240813-04:14:45 wrote gpt_001.pth
20240813-04:14:58 wrote non_validated_0126_00.png
20240813-04:15:11 wrote non_validated_0126_01.png
20240813-04:15:11 wrote state.pth
20240813-04:15:11 --- epoch 127 ----------------------------------------
20240813-04:15:11 current_test_accuracies 0.9519 0.9420 0.0000 0.0000 0.0000
20240813-04:15:11 training model 2
20240813-04:15:11 training model 3
20240813-04:18:56 train_perplexity 127 model 2 1.1544187304663363
20240813-04:18:57 train_perplexity 127 model 3 1.1541694683503418
20240813-04:18:59 test_perplexity 127 model 2 1.1497564489248508
20240813-04:19:00 test_perplexity 127 model 3 1.1504255320063808
20240813-04:19:46 test_accuracy 127 model 2 val 740 / 780
20240813-04:19:47 test_accuracy 127 model 3 val 764 / 793
20240813-04:19:49 wrote gpt_002.pth
20240813-04:19:50 wrote gpt_003.pth
20240813-04:20:03 wrote non_validated_0127_02.png
20240813-04:20:16 wrote non_validated_0127_03.png
20240813-04:20:16 wrote state.pth
20240813-04:20:16 --- epoch 128 ----------------------------------------
20240813-04:20:16 current_test_accuracies 0.9519 0.9420 0.9487 0.9634 0.0000
20240813-04:20:16 training model 4
20240813-04:20:16 training model 1
20240813-04:24:02 train_perplexity 128 model 4 1.1540854750374228
20240813-04:24:03 train_perplexity 128 model 1 1.154837618128576
20240813-04:24:05 test_perplexity 128 model 4 1.1516929163193208
20240813-04:24:06 test_perplexity 128 model 1 1.153125420096187
20240813-04:24:51 test_accuracy 128 model 4 val 769 / 807
20240813-04:24:52 test_accuracy 128 model 1 val 768 / 808
20240813-04:24:54 wrote gpt_004.pth
20240813-04:24:55 wrote gpt_001.pth
20240813-04:25:08 wrote non_validated_0128_04.png
20240813-04:25:21 wrote non_validated_0128_01.png
20240813-04:25:21 wrote state.pth
20240813-04:25:21 --- epoch 129 ----------------------------------------
20240813-04:25:21 current_test_accuracies 0.9519 0.9505 0.9487 0.9634 0.9529
20240813-04:25:21 training model 2
20240813-04:25:21 training model 1
20240813-04:29:06 train_perplexity 129 model 2 1.1540005091292447
20240813-04:29:07 train_perplexity 129 model 1 1.1543165005475746
20240813-04:29:08 test_perplexity 129 model 2 1.1517192413833726
20240813-04:29:10 test_perplexity 129 model 1 1.1531240957243316
20240813-04:29:57 test_accuracy 129 model 1 val 761 / 788
20240813-04:29:58 test_accuracy 129 model 2 val 750 / 785
20240813-04:30:00 wrote gpt_002.pth
20240813-04:30:01 wrote gpt_001.pth
20240813-04:30:14 wrote non_validated_0129_02.png
20240813-04:30:27 wrote non_validated_0129_01.png
20240813-04:30:27 wrote state.pth
20240813-04:30:27 --- epoch 130 ----------------------------------------
20240813-04:30:27 current_test_accuracies 0.9519 0.9657 0.9554 0.9634 0.9529
20240813-04:31:37 keep c_quizzes model 4 validated 10 / 410 (2.44%) nb_accumulated 10 / 410 (finishes Tue 05:18 -- 516/h)
20240813-04:32:27 keep c_quizzes model 2 validated 11 / 410 (2.68%) nb_accumulated 21 / 410 (finishes Tue 05:09 -- 629/h)
20240813-04:33:15 keep c_quizzes model 3 validated 20 / 410 (4.88%) nb_accumulated 41 / 410 (finishes Tue 04:58 -- 877/h)
20240813-04:34:03 keep c_quizzes model 3 validated 16 / 410 (3.90%) nb_accumulated 57 / 410 (finishes Tue 04:56 -- 949/h)
20240813-04:34:52 keep c_quizzes model 0 validated 13 / 410 (3.17%) nb_accumulated 70 / 410 (finishes Tue 04:56 -- 952/h)
20240813-04:35:40 keep c_quizzes model 0 validated 17 / 410 (4.15%) nb_accumulated 87 / 410 (finishes Tue 04:55 -- 1001/h)
20240813-04:36:29 keep c_quizzes model 1 validated 21 / 410 (5.12%) nb_accumulated 108 / 410 (finishes Tue 04:53 -- 1074/h)
20240813-04:37:18 keep c_quizzes model 1 validated 14 / 410 (3.41%) nb_accumulated 122 / 410 (finishes Tue 04:53 -- 1069/h)
20240813-04:38:06 keep c_quizzes model 0 validated 9 / 410 (2.20%) nb_accumulated 131 / 410 (finishes Tue 04:54 -- 1027/h)
20240813-04:38:55 keep c_quizzes model 3 validated 19 / 410 (4.63%) nb_accumulated 150 / 410 (finishes Tue 04:53 -- 1064/h)
20240813-04:39:43 keep c_quizzes model 3 validated 25 / 410 (6.10%) nb_accumulated 175 / 410 (finishes Tue 04:52 -- 1133/h)
20240813-04:40:32 keep c_quizzes model 2 validated 10 / 410 (2.44%) nb_accumulated 185 / 410 (finishes Tue 04:52 -- 1100/h)
20240813-04:41:22 keep c_quizzes model 4 validated 16 / 410 (3.90%) nb_accumulated 201 / 410 (finishes Tue 04:52 -- 1105/h)
20240813-04:42:10 keep c_quizzes model 2 validated 15 / 410 (3.66%) nb_accumulated 216 / 410 (finishes Tue 04:52 -- 1106/h)
20240813-04:42:59 keep c_quizzes model 1 validated 16 / 410 (3.90%) nb_accumulated 232 / 410 (finishes Tue 04:52 -- 1110/h)
20240813-04:43:48 keep c_quizzes model 1 validated 13 / 410 (3.17%) nb_accumulated 245 / 410 (finishes Tue 04:52 -- 1102/h)
20240813-04:44:38 keep c_quizzes model 3 validated 12 / 410 (2.93%) nb_accumulated 257 / 410 (finishes Tue 04:53 -- 1087/h)
20240813-04:45:27 keep c_quizzes model 4 validated 10 / 410 (2.44%) nb_accumulated 267 / 410 (finishes Tue 04:53 -- 1068/h)
20240813-04:46:15 keep c_quizzes model 4 validated 17 / 410 (4.15%) nb_accumulated 284 / 410 (finishes Tue 04:53 -- 1078/h)
20240813-04:47:04 keep c_quizzes model 2 validated 11 / 410 (2.68%) nb_accumulated 295 / 410 (finishes Tue 04:53 -- 1065/h)
20240813-04:47:53 keep c_quizzes model 4 validated 15 / 410 (3.66%) nb_accumulated 310 / 410 (finishes Tue 04:53 -- 1067/h)
20240813-04:48:42 keep c_quizzes model 0 validated 18 / 410 (4.39%) nb_accumulated 328 / 410 (finishes Tue 04:53 -- 1078/h)
20240813-04:49:30 keep c_quizzes model 4 validated 8 / 410 (1.95%) nb_accumulated 336 / 410 (finishes Tue 04:53 -- 1058/h)
20240813-04:50:18 keep c_quizzes model 2 validated 13 / 410 (3.17%) nb_accumulated 349 / 410 (finishes Tue 04:53 -- 1054/h)
20240813-04:51:07 keep c_quizzes model 1 validated 8 / 410 (1.95%) nb_accumulated 357 / 410 (finishes Tue 04:54 -- 1036/h)
20240813-04:51:56 keep c_quizzes model 1 validated 7 / 410 (1.71%) nb_accumulated 364 / 410 (finishes Tue 04:54 -- 1017/h)
20240813-04:52:45 keep c_quizzes model 1 validated 15 / 410 (3.66%) nb_accumulated 379 / 410 (finishes Tue 04:54 -- 1020/h)
20240813-04:53:34 keep c_quizzes model 2 validated 19 / 410 (4.63%) nb_accumulated 398 / 410 (finishes Tue 04:54 -- 1033/h)
20240813-04:54:22 keep c_quizzes model 2 validated 11 / 410 (2.68%) nb_accumulated 409 / 410 (finishes Tue 04:54 -- 1026/h)
20240813-04:55:10 keep c_quizzes model 4 validated 15 / 410 (3.66%) nb_accumulated 424 / 410 (finishes now! -- 1029/h)
20240813-04:55:14 wrote c_quizzes.pth
20240813-04:55:14 training model 0
20240813-04:55:14 training model 1
20240813-04:58:57 train_perplexity 130 model 0 1.1555284625034588
20240813-04:58:59 test_perplexity 130 model 0 1.1521110257457075
20240813-04:59:00 train_perplexity 130 model 1 1.1551063325542228
20240813-04:59:02 test_perplexity 130 model 1 1.1534497922351414
20240813-04:59:47 test_accuracy 130 model 0 val 759 / 788
20240813-04:59:48 test_accuracy 130 model 1 val 757 / 793
20240813-04:59:50 wrote gpt_000.pth
20240813-04:59:51 wrote gpt_001.pth
20240813-05:00:04 wrote non_validated_0130_00.png
20240813-05:00:17 wrote non_validated_0130_01.png
20240813-05:00:17 wrote state.pth
20240813-05:00:17 --- epoch 131 ----------------------------------------
20240813-05:00:17 current_test_accuracies 0.9632 0.9546 0.0000 0.0000 0.0000
20240813-05:00:17 training model 2
20240813-05:00:17 training model 3
20240813-05:04:02 train_perplexity 131 model 2 1.154834113300065
20240813-05:04:04 train_perplexity 131 model 3 1.1551008270761765
20240813-05:04:04 test_perplexity 131 model 2 1.152363079720442
20240813-05:04:06 test_perplexity 131 model 3 1.157283201602073
20240813-05:04:52 test_accuracy 131 model 3 val 796 / 828
20240813-05:04:53 test_accuracy 131 model 2 val 767 / 793
20240813-05:04:55 wrote gpt_002.pth
20240813-05:04:56 wrote gpt_003.pth
20240813-05:05:09 wrote non_validated_0131_02.png
20240813-05:05:22 wrote non_validated_0131_03.png
20240813-05:05:22 wrote state.pth
20240813-05:05:22 --- epoch 132 ----------------------------------------
20240813-05:05:22 current_test_accuracies 0.9632 0.9546 0.9672 0.9614 0.0000
20240813-05:05:22 training model 4
20240813-05:05:22 training model 1
20240813-05:09:08 train_perplexity 132 model 4 1.1544758392231051
20240813-05:09:09 train_perplexity 132 model 1 1.1547013105714259
20240813-05:09:10 test_perplexity 132 model 4 1.1528018344597002
20240813-05:09:12 test_perplexity 132 model 1 1.1518789734023516
20240813-05:09:56 test_accuracy 132 model 1 val 770 / 806
20240813-05:09:58 test_accuracy 132 model 4 val 768 / 797
20240813-05:10:00 wrote gpt_004.pth
20240813-05:10:01 wrote gpt_001.pth
20240813-05:10:14 wrote non_validated_0132_04.png
20240813-05:10:27 wrote non_validated_0132_01.png
20240813-05:10:28 wrote state.pth
20240813-05:10:28 --- epoch 133 ----------------------------------------
20240813-05:10:28 current_test_accuracies 0.9632 0.9553 0.9672 0.9614 0.9636
20240813-05:11:41 keep c_quizzes model 4 validated 12 / 410 (2.93%) nb_accumulated 12 / 410 (finishes Tue 05:52 -- 591/h)
20240813-05:12:29 keep c_quizzes model 0 validated 6 / 410 (1.46%) nb_accumulated 18 / 410 (finishes Tue 05:56 -- 531/h)
20240813-05:13:19 keep c_quizzes model 4 validated 9 / 410 (2.20%) nb_accumulated 27 / 410 (finishes Tue 05:53 -- 566/h)
20240813-05:14:08 keep c_quizzes model 2 validated 8 / 410 (1.95%) nb_accumulated 35 / 410 (finishes Tue 05:53 -- 572/h)
20240813-05:14:57 keep c_quizzes model 2 validated 12 / 410 (2.93%) nb_accumulated 47 / 410 (finishes Tue 05:49 -- 628/h)
20240813-05:15:45 keep c_quizzes model 2 validated 12 / 410 (2.93%) nb_accumulated 59 / 410 (finishes Tue 05:47 -- 668/h)
20240813-05:16:33 keep c_quizzes model 2 validated 9 / 410 (2.20%) nb_accumulated 68 / 410 (finishes Tue 05:47 -- 669/h)
20240813-05:17:22 keep c_quizzes model 1 validated 7 / 410 (1.71%) nb_accumulated 75 / 410 (finishes Tue 05:48 -- 651/h)
20240813-05:18:10 keep c_quizzes model 3 validated 8 / 410 (1.95%) nb_accumulated 83 / 410 (finishes Tue 05:48 -- 646/h)
20240813-05:18:58 keep c_quizzes model 1 validated 6 / 410 (1.46%) nb_accumulated 89 / 410 (finishes Tue 05:49 -- 627/h)
20240813-05:19:46 keep c_quizzes model 0 validated 6 / 410 (1.46%) nb_accumulated 95 / 410 (finishes Tue 05:50 -- 612/h)
20240813-05:20:34 keep c_quizzes model 2 validated 8 / 410 (1.95%) nb_accumulated 103 / 410 (finishes Tue 05:50 -- 611/h)
20240813-05:21:22 keep c_quizzes model 2 validated 8 / 410 (1.95%) nb_accumulated 111 / 410 (finishes Tue 05:50 -- 610/h)
20240813-05:22:11 keep c_quizzes model 4 validated 12 / 410 (2.93%) nb_accumulated 123 / 410 (finishes Tue 05:49 -- 629/h)
20240813-05:23:00 keep c_quizzes model 4 validated 6 / 410 (1.46%) nb_accumulated 129 / 410 (finishes Tue 05:50 -- 617/h)
20240813-05:23:49 keep c_quizzes model 4 validated 7 / 410 (1.71%) nb_accumulated 136 / 410 (finishes Tue 05:50 -- 610/h)
20240813-05:24:38 keep c_quizzes model 4 validated 8 / 410 (1.95%) nb_accumulated 144 / 410 (finishes Tue 05:50 -- 609/h)
20240813-05:25:26 keep c_quizzes model 3 validated 11 / 410 (2.68%) nb_accumulated 155 / 410 (finishes Tue 05:50 -- 620/h)
20240813-05:26:15 keep c_quizzes model 4 validated 12 / 410 (2.93%) nb_accumulated 167 / 410 (finishes Tue 05:49 -- 634/h)
20240813-05:27:03 keep c_quizzes model 0 validated 12 / 410 (2.93%) nb_accumulated 179 / 410 (finishes Tue 05:48 -- 647/h)
20240813-05:27:51 keep c_quizzes model 1 validated 4 / 410 (0.98%) nb_accumulated 183 / 410 (finishes Tue 05:49 -- 631/h)
20240813-05:28:40 keep c_quizzes model 3 validated 7 / 410 (1.71%) nb_accumulated 190 / 410 (finishes Tue 05:49 -- 626/h)
20240813-05:29:29 keep c_quizzes model 2 validated 10 / 410 (2.44%) nb_accumulated 200 / 410 (finishes Tue 05:49 -- 630/h)
20240813-05:30:18 keep c_quizzes model 4 validated 5 / 410 (1.22%) nb_accumulated 205 / 410 (finishes Tue 05:50 -- 620/h)
20240813-05:31:08 keep c_quizzes model 2 validated 8 / 410 (1.95%) nb_accumulated 213 / 410 (finishes Tue 05:50 -- 617/h)
20240813-05:31:58 keep c_quizzes model 0 validated 4 / 410 (0.98%) nb_accumulated 217 / 410 (finishes Tue 05:51 -- 605/h)
20240813-05:32:46 keep c_quizzes model 1 validated 9 / 410 (2.20%) nb_accumulated 226 / 410 (finishes Tue 05:50 -- 607/h)
20240813-05:33:34 keep c_quizzes model 0 validated 7 / 410 (1.71%) nb_accumulated 233 / 410 (finishes Tue 05:51 -- 604/h)
20240813-05:34:23 keep c_quizzes model 4 validated 7 / 410 (1.71%) nb_accumulated 240 / 410 (finishes Tue 05:51 -- 602/h)
20240813-05:35:12 keep c_quizzes model 4 validated 7 / 410 (1.71%) nb_accumulated 247 / 410 (finishes Tue 05:51 -- 599/h)
20240813-05:36:00 keep c_quizzes model 3 validated 6 / 410 (1.46%) nb_accumulated 253 / 410 (finishes Tue 05:51 -- 594/h)
20240813-05:36:49 keep c_quizzes model 3 validated 6 / 410 (1.46%) nb_accumulated 259 / 410 (finishes Tue 05:52 -- 589/h)
20240813-05:37:37 keep c_quizzes model 0 validated 8 / 410 (1.95%) nb_accumulated 267 / 410 (finishes Tue 05:52 -- 589/h)
20240813-05:38:25 keep c_quizzes model 2 validated 7 / 410 (1.71%) nb_accumulated 274 / 410 (finishes Tue 05:52 -- 587/h)
20240813-05:39:15 keep c_quizzes model 3 validated 7 / 410 (1.71%) nb_accumulated 281 / 410 (finishes Tue 05:52 -- 585/h)
20240813-05:40:03 keep c_quizzes model 4 validated 7 / 410 (1.71%) nb_accumulated 288 / 410 (finishes Tue 05:52 -- 583/h)
20240813-05:40:52 keep c_quizzes model 4 validated 4 / 410 (0.98%) nb_accumulated 292 / 410 (finishes Tue 05:53 -- 576/h)
20240813-05:41:41 keep c_quizzes model 3 validated 9 / 410 (2.20%) nb_accumulated 301 / 410 (finishes Tue 05:53 -- 578/h)
20240813-05:42:33 keep c_quizzes model 2 validated 10 / 410 (2.44%) nb_accumulated 311 / 410 (finishes Tue 05:52 -- 581/h)
20240813-05:43:22 keep c_quizzes model 2 validated 3 / 410 (0.73%) nb_accumulated 314 / 410 (finishes Tue 05:53 -- 572/h)
20240813-05:44:10 keep c_quizzes model 3 validated 9 / 410 (2.20%) nb_accumulated 323 / 410 (finishes Tue 05:53 -- 574/h)
20240813-05:45:00 keep c_quizzes model 4 validated 4 / 410 (0.98%) nb_accumulated 327 / 410 (finishes Tue 05:53 -- 568/h)
20240813-05:45:50 keep c_quizzes model 0 validated 8 / 410 (1.95%) nb_accumulated 335 / 410 (finishes Tue 05:53 -- 568/h)
20240813-05:46:39 keep c_quizzes model 0 validated 9 / 410 (2.20%) nb_accumulated 344 / 410 (finishes Tue 05:53 -- 570/h)
20240813-05:47:27 keep c_quizzes model 3 validated 7 / 410 (1.71%) nb_accumulated 351 / 410 (finishes Tue 05:53 -- 569/h)
20240813-05:48:15 keep c_quizzes model 3 validated 6 / 410 (1.46%) nb_accumulated 357 / 410 (finishes Tue 05:53 -- 566/h)
20240813-05:49:04 keep c_quizzes model 2 validated 15 / 410 (3.66%) nb_accumulated 372 / 410 (finishes Tue 05:53 -- 578/h)
20240813-05:49:52 keep c_quizzes model 2 validated 9 / 410 (2.20%) nb_accumulated 381 / 410 (finishes Tue 05:52 -- 580/h)
20240813-05:50:40 keep c_quizzes model 4 validated 10 / 410 (2.44%) nb_accumulated 391 / 410 (finishes Tue 05:52 -- 583/h)
20240813-05:51:29 keep c_quizzes model 1 validated 5 / 410 (1.22%) nb_accumulated 396 / 410 (finishes Tue 05:52 -- 579/h)
20240813-05:52:17 keep c_quizzes model 1 validated 7 / 410 (1.71%) nb_accumulated 403 / 410 (finishes Tue 05:53 -- 578/h)
20240813-05:53:06 keep c_quizzes model 0 validated 6 / 410 (1.46%) nb_accumulated 409 / 410 (finishes Tue 05:53 -- 575/h)
20240813-05:53:54 keep c_quizzes model 1 validated 10 / 410 (2.44%) nb_accumulated 419 / 410 (finishes now! -- 578/h)
20240813-05:53:57 wrote c_quizzes.pth
20240813-05:53:57 training model 0
20240813-05:53:57 training model 1
20240813-05:57:42 train_perplexity 133 model 0 1.1561712540080722
20240813-05:57:42 train_perplexity 133 model 1 1.1560038663555563
20240813-05:57:44 test_perplexity 133 model 0 1.1561637855989508
20240813-05:57:46 test_perplexity 133 model 1 1.1524315399936451
20240813-05:58:28 test_accuracy 133 model 1 val 788 / 823
20240813-05:58:31 test_accuracy 133 model 0 val 757 / 799
20240813-05:58:33 wrote gpt_000.pth
20240813-05:58:34 wrote gpt_001.pth
20240813-05:58:47 wrote non_validated_0133_00.png
20240813-05:59:00 wrote non_validated_0133_01.png
20240813-05:59:00 wrote state.pth
20240813-05:59:00 --- epoch 134 ----------------------------------------
20240813-05:59:00 current_test_accuracies 0.9474 0.9575 0.0000 0.0000 0.0000
20240813-05:59:00 training model 2
20240813-05:59:00 training model 3
20240813-06:02:45 train_perplexity 134 model 2 1.155456559910408
20240813-06:02:47 train_perplexity 134 model 3 1.1561974816162135
20240813-06:02:47 test_perplexity 134 model 2 1.1521067363808342
20240813-06:02:49 test_perplexity 134 model 3 1.151837848606166
20240813-06:03:31 test_accuracy 134 model 2 val 769 / 800
20240813-06:03:34 test_accuracy 134 model 3 val 765 / 793
20240813-06:03:36 wrote gpt_002.pth
20240813-06:03:37 wrote gpt_003.pth
20240813-06:03:50 wrote non_validated_0134_02.png
20240813-06:04:03 wrote non_validated_0134_03.png
20240813-06:04:03 wrote state.pth
20240813-06:04:03 --- epoch 135 ----------------------------------------
20240813-06:04:03 current_test_accuracies 0.9474 0.9575 0.9613 0.9647 0.0000
20240813-06:04:03 training model 4
20240813-06:04:03 training model 0
20240813-06:07:48 train_perplexity 135 model 4 1.1554175344270303
20240813-06:07:49 train_perplexity 135 model 0 1.1552326848597168
20240813-06:07:50 test_perplexity 135 model 4 1.1535254261475782
20240813-06:07:52 test_perplexity 135 model 0 1.1541645013152646
20240813-06:08:35 test_accuracy 135 model 4 val 767 / 803
20240813-06:08:36 test_accuracy 135 model 0 val 773 / 808
20240813-06:08:38 wrote gpt_004.pth
20240813-06:08:39 wrote gpt_000.pth
20240813-06:08:52 wrote non_validated_0135_04.png
20240813-06:09:05 wrote non_validated_0135_00.png
20240813-06:09:05 wrote state.pth
20240813-06:09:05 --- epoch 136 ----------------------------------------
20240813-06:09:05 current_test_accuracies 0.9567 0.9575 0.9613 0.9647 0.9552
20240813-06:10:15 keep c_quizzes model 4 validated 5 / 410 (1.22%) nb_accumulated 5 / 410 (finishes Tue 07:44 -- 259/h)
20240813-06:11:03 keep c_quizzes model 1 validated 4 / 410 (0.98%) nb_accumulated 9 / 410 (finishes Tue 07:38 -- 274/h)
20240813-06:11:51 keep c_quizzes model 0 validated 4 / 410 (0.98%) nb_accumulated 13 / 410 (finishes Tue 07:36 -- 281/h)
20240813-06:12:40 keep c_quizzes model 4 validated 16 / 410 (3.90%) nb_accumulated 29 / 410 (finishes Tue 06:59 -- 486/h)
20240813-06:13:28 keep c_quizzes model 3 validated 3 / 410 (0.73%) nb_accumulated 32 / 410 (finishes Tue 07:05 -- 437/h)
20240813-06:14:17 keep c_quizzes model 3 validated 11 / 410 (2.68%) nb_accumulated 43 / 410 (finishes Tue 06:58 -- 496/h)
20240813-06:15:05 keep c_quizzes model 1 validated 10 / 410 (2.44%) nb_accumulated 53 / 410 (finishes Tue 06:55 -- 530/h)
20240813-06:15:53 keep c_quizzes model 0 validated 9 / 410 (2.20%) nb_accumulated 62 / 410 (finishes Tue 06:54 -- 546/h)
20240813-06:16:41 keep c_quizzes model 2 validated 11 / 410 (2.68%) nb_accumulated 73 / 410 (finishes Tue 06:51 -- 576/h)
20240813-06:17:29 keep c_quizzes model 2 validated 9 / 410 (2.20%) nb_accumulated 82 / 410 (finishes Tue 06:51 -- 585/h)
20240813-06:18:18 keep c_quizzes model 1 validated 14 / 410 (3.41%) nb_accumulated 96 / 410 (finishes Tue 06:48 -- 624/h)
20240813-06:19:06 keep c_quizzes model 2 validated 17 / 410 (4.15%) nb_accumulated 113 / 410 (finishes Tue 06:45 -- 676/h)
20240813-06:19:55 keep c_quizzes model 3 validated 10 / 410 (2.44%) nb_accumulated 123 / 410 (finishes Tue 06:45 -- 681/h)
20240813-06:20:43 keep c_quizzes model 1 validated 10 / 410 (2.44%) nb_accumulated 133 / 410 (finishes Tue 06:44 -- 685/h)
20240813-06:21:32 keep c_quizzes model 2 validated 11 / 410 (2.68%) nb_accumulated 144 / 410 (finishes Tue 06:44 -- 694/h)
20240813-06:22:20 keep c_quizzes model 1 validated 9 / 410 (2.20%) nb_accumulated 153 / 410 (finishes Tue 06:44 -- 692/h)
20240813-06:23:08 keep c_quizzes model 1 validated 7 / 410 (1.71%) nb_accumulated 160 / 410 (finishes Tue 06:45 -- 682/h)
20240813-06:23:57 keep c_quizzes model 4 validated 5 / 410 (1.22%) nb_accumulated 165 / 410 (finishes Tue 06:46 -- 666/h)
20240813-06:24:45 keep c_quizzes model 0 validated 9 / 410 (2.20%) nb_accumulated 174 / 410 (finishes Tue 06:46 -- 666/h)
20240813-06:25:33 keep c_quizzes model 3 validated 3 / 410 (0.73%) nb_accumulated 177 / 410 (finishes Tue 06:47 -- 644/h)
20240813-06:26:22 keep c_quizzes model 3 validated 10 / 410 (2.44%) nb_accumulated 187 / 410 (finishes Tue 06:46 -- 649/h)
20240813-06:27:10 keep c_quizzes model 0 validated 1 / 410 (0.24%) nb_accumulated 188 / 410 (finishes Tue 06:48 -- 623/h)
20240813-06:27:58 keep c_quizzes model 0 validated 9 / 410 (2.20%) nb_accumulated 197 / 410 (finishes Tue 06:48 -- 625/h)
20240813-06:28:47 keep c_quizzes model 4 validated 8 / 410 (1.95%) nb_accumulated 205 / 410 (finishes Tue 06:48 -- 624/h)
20240813-06:29:35 keep c_quizzes model 3 validated 12 / 410 (2.93%) nb_accumulated 217 / 410 (finishes Tue 06:47 -- 635/h)
20240813-06:30:23 keep c_quizzes model 4 validated 8 / 410 (1.95%) nb_accumulated 225 / 410 (finishes Tue 06:47 -- 633/h)
20240813-06:31:11 keep c_quizzes model 1 validated 11 / 410 (2.68%) nb_accumulated 236 / 410 (finishes Tue 06:47 -- 640/h)
20240813-06:32:00 keep c_quizzes model 4 validated 4 / 410 (0.98%) nb_accumulated 240 / 410 (finishes Tue 06:48 -- 628/h)
20240813-06:32:48 keep c_quizzes model 0 validated 6 / 410 (1.46%) nb_accumulated 246 / 410 (finishes Tue 06:48 -- 622/h)
20240813-06:33:36 keep c_quizzes model 3 validated 5 / 410 (1.22%) nb_accumulated 251 / 410 (finishes Tue 06:49 -- 614/h)
20240813-06:34:25 keep c_quizzes model 4 validated 5 / 410 (1.22%) nb_accumulated 256 / 410 (finishes Tue 06:49 -- 606/h)
20240813-06:35:13 keep c_quizzes model 2 validated 3 / 410 (0.73%) nb_accumulated 259 / 410 (finishes Tue 06:50 -- 594/h)
20240813-06:36:01 keep c_quizzes model 0 validated 12 / 410 (2.93%) nb_accumulated 271 / 410 (finishes Tue 06:49 -- 603/h)
20240813-06:36:50 keep c_quizzes model 4 validated 11 / 410 (2.68%) nb_accumulated 282 / 410 (finishes Tue 06:49 -- 609/h)
20240813-06:37:38 keep c_quizzes model 1 validated 5 / 410 (1.22%) nb_accumulated 287 / 410 (finishes Tue 06:49 -- 603/h)
20240813-06:38:26 keep c_quizzes model 1 validated 8 / 410 (1.95%) nb_accumulated 295 / 410 (finishes Tue 06:49 -- 603/h)
20240813-06:39:15 keep c_quizzes model 2 validated 13 / 410 (3.17%) nb_accumulated 308 / 410 (finishes Tue 06:49 -- 612/h)
20240813-06:40:03 keep c_quizzes model 3 validated 13 / 410 (3.17%) nb_accumulated 321 / 410 (finishes Tue 06:48 -- 622/h)
20240813-06:40:51 keep c_quizzes model 2 validated 7 / 410 (1.71%) nb_accumulated 328 / 410 (finishes Tue 06:48 -- 619/h)
20240813-06:41:39 keep c_quizzes model 1 validated 7 / 410 (1.71%) nb_accumulated 335 / 410 (finishes Tue 06:48 -- 617/h)
20240813-06:42:27 keep c_quizzes model 0 validated 6 / 410 (1.46%) nb_accumulated 341 / 410 (finishes Tue 06:49 -- 613/h)
20240813-06:43:16 keep c_quizzes model 0 validated 4 / 410 (0.98%) nb_accumulated 345 / 410 (finishes Tue 06:49 -- 605/h)
20240813-06:44:04 keep c_quizzes model 2 validated 8 / 410 (1.95%) nb_accumulated 353 / 410 (finishes Tue 06:49 -- 605/h)
20240813-06:44:53 keep c_quizzes model 4 validated 8 / 410 (1.95%) nb_accumulated 361 / 410 (finishes Tue 06:49 -- 605/h)
20240813-06:45:41 keep c_quizzes model 2 validated 10 / 410 (2.44%) nb_accumulated 371 / 410 (finishes Tue 06:49 -- 608/h)
20240813-06:46:29 keep c_quizzes model 2 validated 13 / 410 (3.17%) nb_accumulated 384 / 410 (finishes Tue 06:49 -- 615/h)
20240813-06:47:18 keep c_quizzes model 4 validated 15 / 410 (3.66%) nb_accumulated 399 / 410 (finishes Tue 06:48 -- 626/h)
20240813-06:48:06 keep c_quizzes model 0 validated 9 / 410 (2.20%) nb_accumulated 408 / 410 (finishes Tue 06:48 -- 627/h)
20240813-06:48:54 keep c_quizzes model 4 validated 6 / 410 (1.46%) nb_accumulated 414 / 410 (finishes now! -- 623/h)
20240813-06:48:58 wrote c_quizzes.pth
20240813-06:48:58 training model 0
20240813-06:48:58 training model 1
20240813-06:52:42 train_perplexity 136 model 0 1.1561054466074
20240813-06:52:43 train_perplexity 136 model 1 1.1563936608945884
20240813-06:52:46 test_perplexity 136 model 0 1.1500468044273817
20240813-06:52:46 test_perplexity 136 model 1 1.154107655367673
20240813-06:53:30 test_accuracy 136 model 1 val 786 / 815
20240813-06:53:33 test_accuracy 136 model 0 val 747 / 780
20240813-06:53:35 wrote gpt_000.pth
20240813-06:53:36 wrote gpt_001.pth
20240813-06:53:49 wrote non_validated_0136_00.png
20240813-06:54:02 wrote non_validated_0136_01.png
20240813-06:54:02 wrote state.pth
20240813-06:54:02 --- epoch 137 ----------------------------------------
20240813-06:54:02 current_test_accuracies 0.9577 0.9644 0.0000 0.0000 0.0000
20240813-06:54:02 training model 2
20240813-06:54:02 training model 3
20240813-06:57:46 train_perplexity 137 model 2 1.1562810237445516
20240813-06:57:48 train_perplexity 137 model 3 1.1566726023128167
20240813-06:57:49 test_perplexity 137 model 2 1.1526368106030094
20240813-06:57:50 test_perplexity 137 model 3 1.1554500339250608
20240813-06:58:35 test_accuracy 137 model 3 val 775 / 807
20240813-06:58:36 test_accuracy 137 model 2 val 754 / 786
20240813-06:58:38 wrote gpt_002.pth
20240813-06:58:39 wrote gpt_003.pth
20240813-06:58:52 wrote non_validated_0137_02.png
20240813-06:59:05 wrote non_validated_0137_03.png
20240813-06:59:05 wrote state.pth
20240813-06:59:05 --- epoch 138 ----------------------------------------
20240813-06:59:05 current_test_accuracies 0.9577 0.9644 0.9593 0.9603 0.0000
20240813-06:59:05 training model 4
20240813-06:59:05 training model 0
20240813-07:02:49 train_perplexity 138 model 4 1.1556310840959019
20240813-07:02:51 test_perplexity 138 model 4 1.1539088589914632
20240813-07:02:51 train_perplexity 138 model 0 1.1562352796323894
20240813-07:02:54 test_perplexity 138 model 0 1.154738833312465
20240813-07:03:37 test_accuracy 138 model 4 val 781 / 815
20240813-07:03:40 test_accuracy 138 model 0 val 762 / 791
20240813-07:03:42 wrote gpt_004.pth
20240813-07:03:43 wrote gpt_000.pth
20240813-07:03:56 wrote non_validated_0138_04.png
20240813-07:04:09 wrote non_validated_0138_00.png
20240813-07:04:09 wrote state.pth
20240813-07:04:09 --- epoch 139 ----------------------------------------
20240813-07:04:09 current_test_accuracies 0.9633 0.9644 0.9593 0.9603 0.9583
20240813-07:05:19 keep c_quizzes model 2 validated 10 / 410 (2.44%) nb_accumulated 10 / 410 (finishes Tue 07:52 -- 512/h)
20240813-07:06:07 keep c_quizzes model 4 validated 10 / 410 (2.44%) nb_accumulated 20 / 410 (finishes Tue 07:44 -- 607/h)
20240813-07:06:55 keep c_quizzes model 4 validated 14 / 410 (3.41%) nb_accumulated 34 / 410 (finishes Tue 07:37 -- 734/h)
20240813-07:07:43 keep c_quizzes model 3 validated 2 / 410 (0.49%) nb_accumulated 36 / 410 (finishes Tue 07:44 -- 603/h)
20240813-07:08:32 keep c_quizzes model 4 validated 5 / 410 (1.22%) nb_accumulated 41 / 410 (finishes Tue 07:47 -- 561/h)
20240813-07:09:20 keep c_quizzes model 3 validated 8 / 410 (1.95%) nb_accumulated 49 / 410 (finishes Tue 07:47 -- 567/h)
20240813-07:10:08 keep c_quizzes model 4 validated 8 / 410 (1.95%) nb_accumulated 57 / 410 (finishes Tue 07:47 -- 571/h)
20240813-07:10:56 keep c_quizzes model 2 validated 14 / 410 (3.41%) nb_accumulated 71 / 410 (finishes Tue 07:43 -- 627/h)
20240813-07:11:44 keep c_quizzes model 1 validated 9 / 410 (2.20%) nb_accumulated 80 / 410 (finishes Tue 07:43 -- 632/h)
20240813-07:12:32 keep c_quizzes model 0 validated 6 / 410 (1.46%) nb_accumulated 86 / 410 (finishes Tue 07:44 -- 615/h)
20240813-07:13:20 keep c_quizzes model 4 validated 12 / 410 (2.93%) nb_accumulated 98 / 410 (finishes Tue 07:42 -- 639/h)
20240813-07:14:08 keep c_quizzes model 0 validated 7 / 410 (1.71%) nb_accumulated 105 / 410 (finishes Tue 07:43 -- 630/h)
20240813-07:14:57 keep c_quizzes model 4 validated 14 / 410 (3.41%) nb_accumulated 119 / 410 (finishes Tue 07:41 -- 661/h)
20240813-07:15:45 keep c_quizzes model 3 validated 14 / 410 (3.41%) nb_accumulated 133 / 410 (finishes Tue 07:39 -- 687/h)
20240813-07:16:33 keep c_quizzes model 0 validated 15 / 410 (3.66%) nb_accumulated 148 / 410 (finishes Tue 07:38 -- 715/h)
20240813-07:17:21 keep c_quizzes model 3 validated 6 / 410 (1.46%) nb_accumulated 154 / 410 (finishes Tue 07:39 -- 699/h)
20240813-07:18:09 keep c_quizzes model 3 validated 9 / 410 (2.20%) nb_accumulated 163 / 410 (finishes Tue 07:39 -- 697/h)
20240813-07:18:58 keep c_quizzes model 1 validated 13 / 410 (3.17%) nb_accumulated 176 / 410 (finishes Tue 07:38 -- 712/h)
20240813-07:19:46 keep c_quizzes model 2 validated 11 / 410 (2.68%) nb_accumulated 187 / 410 (finishes Tue 07:38 -- 718/h)
20240813-07:20:34 keep c_quizzes model 4 validated 3 / 410 (0.73%) nb_accumulated 190 / 410 (finishes Tue 07:39 -- 694/h)
20240813-07:21:22 keep c_quizzes model 1 validated 3 / 410 (0.73%) nb_accumulated 193 / 410 (finishes Tue 07:40 -- 672/h)
20240813-07:22:11 keep c_quizzes model 3 validated 14 / 410 (3.41%) nb_accumulated 207 / 410 (finishes Tue 07:39 -- 688/h)
20240813-07:22:59 keep c_quizzes model 2 validated 4 / 410 (0.98%) nb_accumulated 211 / 410 (finishes Tue 07:40 -- 671/h)
20240813-07:23:47 keep c_quizzes model 4 validated 8 / 410 (1.95%) nb_accumulated 219 / 410 (finishes Tue 07:40 -- 668/h)
20240813-07:24:35 keep c_quizzes model 0 validated 6 / 410 (1.46%) nb_accumulated 225 / 410 (finishes Tue 07:41 -- 660/h)
20240813-07:25:23 keep c_quizzes model 0 validated 4 / 410 (0.98%) nb_accumulated 229 / 410 (finishes Tue 07:42 -- 646/h)
20240813-07:26:11 keep c_quizzes model 0 validated 10 / 410 (2.44%) nb_accumulated 239 / 410 (finishes Tue 07:41 -- 650/h)
20240813-07:27:00 keep c_quizzes model 4 validated 14 / 410 (3.41%) nb_accumulated 253 / 410 (finishes Tue 07:41 -- 664/h)
20240813-07:27:48 keep c_quizzes model 3 validated 14 / 410 (3.41%) nb_accumulated 267 / 410 (finishes Tue 07:40 -- 677/h)
20240813-07:28:36 keep c_quizzes model 1 validated 9 / 410 (2.20%) nb_accumulated 276 / 410 (finishes Tue 07:40 -- 677/h)
20240813-07:29:24 keep c_quizzes model 4 validated 10 / 410 (2.44%) nb_accumulated 286 / 410 (finishes Tue 07:40 -- 679/h)
20240813-07:30:13 keep c_quizzes model 0 validated 8 / 410 (1.95%) nb_accumulated 294 / 410 (finishes Tue 07:40 -- 676/h)
20240813-07:31:01 keep c_quizzes model 0 validated 9 / 410 (2.20%) nb_accumulated 303 / 410 (finishes Tue 07:40 -- 676/h)
20240813-07:31:49 keep c_quizzes model 1 validated 8 / 410 (1.95%) nb_accumulated 311 / 410 (finishes Tue 07:40 -- 674/h)
20240813-07:32:37 keep c_quizzes model 0 validated 8 / 410 (1.95%) nb_accumulated 319 / 410 (finishes Tue 07:40 -- 672/h)
20240813-07:33:26 keep c_quizzes model 1 validated 16 / 410 (3.90%) nb_accumulated 335 / 410 (finishes Tue 07:39 -- 686/h)
20240813-07:34:14 keep c_quizzes model 4 validated 6 / 410 (1.46%) nb_accumulated 341 / 410 (finishes Tue 07:40 -- 680/h)
20240813-07:35:02 keep c_quizzes model 2 validated 9 / 410 (2.20%) nb_accumulated 350 / 410 (finishes Tue 07:40 -- 679/h)
20240813-07:35:50 keep c_quizzes model 4 validated 11 / 410 (2.68%) nb_accumulated 361 / 410 (finishes Tue 07:40 -- 683/h)
20240813-07:36:39 keep c_quizzes model 3 validated 8 / 410 (1.95%) nb_accumulated 369 / 410 (finishes Tue 07:40 -- 681/h)
20240813-07:37:27 keep c_quizzes model 1 validated 5 / 410 (1.22%) nb_accumulated 374 / 410 (finishes Tue 07:40 -- 673/h)
20240813-07:38:15 keep c_quizzes model 0 validated 9 / 410 (2.20%) nb_accumulated 383 / 410 (finishes Tue 07:40 -- 673/h)
20240813-07:39:03 keep c_quizzes model 1 validated 7 / 410 (1.71%) nb_accumulated 390 / 410 (finishes Tue 07:40 -- 670/h)
20240813-07:39:51 keep c_quizzes model 4 validated 8 / 410 (1.95%) nb_accumulated 398 / 410 (finishes Tue 07:40 -- 668/h)
20240813-07:40:39 keep c_quizzes model 4 validated 9 / 410 (2.20%) nb_accumulated 407 / 410 (finishes Tue 07:40 -- 668/h)
20240813-07:41:28 keep c_quizzes model 3 validated 9 / 410 (2.20%) nb_accumulated 416 / 410 (finishes now! -- 668/h)
20240813-07:41:31 wrote c_quizzes.pth
20240813-07:41:31 training model 0
20240813-07:41:31 training model 1
20240813-07:45:15 train_perplexity 139 model 0 1.1567838553741265
20240813-07:45:16 train_perplexity 139 model 1 1.1571296125659047
20240813-07:45:17 test_perplexity 139 model 0 1.1562978441390765
20240813-07:45:19 test_perplexity 139 model 1 1.1570318268193038
20240813-07:46:02 test_accuracy 139 model 1 val 778 / 814
20240813-07:46:03 test_accuracy 139 model 0 val 767 / 803
20240813-07:46:05 wrote gpt_000.pth
20240813-07:46:06 wrote gpt_001.pth
20240813-07:46:18 wrote non_validated_0139_00.png
20240813-07:46:31 wrote non_validated_0139_01.png
20240813-07:46:31 wrote state.pth
20240813-07:46:31 --- epoch 140 ----------------------------------------
20240813-07:46:31 current_test_accuracies 0.9552 0.9558 0.0000 0.0000 0.0000
20240813-07:46:31 training model 2
20240813-07:46:31 training model 3
20240813-07:50:15 train_perplexity 140 model 2 1.157352200729754
20240813-07:50:17 test_perplexity 140 model 2 1.1549457901586915
20240813-07:50:18 train_perplexity 140 model 3 1.1569258038137251
20240813-07:50:20 test_perplexity 140 model 3 1.156111767562921
20240813-07:51:05 test_accuracy 140 model 2 val 753 / 798
20240813-07:51:05 test_accuracy 140 model 3 val 776 / 820
20240813-07:51:08 wrote gpt_002.pth
20240813-07:51:08 wrote gpt_003.pth
20240813-07:51:21 wrote non_validated_0140_02.png
20240813-07:51:34 wrote non_validated_0140_03.png
20240813-07:51:34 wrote state.pth
20240813-07:51:34 --- epoch 141 ----------------------------------------
20240813-07:51:34 current_test_accuracies 0.9552 0.9558 0.9436 0.9463 0.0000
20240813-07:51:34 training model 4
20240813-07:51:34 training model 2
20240813-07:55:20 train_perplexity 141 model 4 1.1565816487341898
20240813-07:55:21 train_perplexity 141 model 2 1.1568263665322598
20240813-07:55:23 test_perplexity 141 model 4 1.1535031091962826
20240813-07:55:24 test_perplexity 141 model 2 1.1567818080603114
20240813-07:56:10 test_accuracy 141 model 2 val 748 / 790
20240813-07:56:12 test_accuracy 141 model 4 val 757 / 794
20240813-07:56:14 wrote gpt_004.pth
20240813-07:56:14 wrote gpt_002.pth
20240813-07:56:27 wrote non_validated_0141_04.png
20240813-07:56:41 wrote non_validated_0141_02.png
20240813-07:56:41 wrote state.pth
20240813-07:56:41 --- epoch 142 ----------------------------------------
20240813-07:56:41 current_test_accuracies 0.9552 0.9558 0.9468 0.9463 0.9534
20240813-07:56:41 training model 3
20240813-07:56:41 training model 2
20240813-08:00:25 train_perplexity 142 model 3 1.1569181094079497
20240813-08:00:27 train_perplexity 142 model 2 1.15669853012755
20240813-08:00:27 test_perplexity 142 model 3 1.1548369897955018
20240813-08:00:29 test_perplexity 142 model 2 1.1520009612065185
20240813-08:01:16 test_accuracy 142 model 3 val 745 / 779
20240813-08:01:17 test_accuracy 142 model 2 val 755 / 792
20240813-08:01:19 wrote gpt_003.pth
20240813-08:01:19 wrote gpt_002.pth
20240813-08:01:32 wrote non_validated_0142_03.png
20240813-08:01:45 wrote non_validated_0142_02.png
20240813-08:01:45 wrote state.pth
20240813-08:01:45 --- epoch 143 ----------------------------------------
20240813-08:01:45 current_test_accuracies 0.9552 0.9558 0.9533 0.9564 0.9534
20240813-08:02:52 keep c_quizzes model 2 validated 10 / 410 (2.44%) nb_accumulated 10 / 410 (finishes Tue 08:47 -- 536/h)
20240813-08:03:41 keep c_quizzes model 1 validated 11 / 410 (2.68%) nb_accumulated 21 / 410 (finishes Tue 08:39 -- 655/h)
20240813-08:04:29 keep c_quizzes model 1 validated 8 / 410 (1.95%) nb_accumulated 29 / 410 (finishes Tue 08:40 -- 638/h)
20240813-08:05:17 keep c_quizzes model 0 validated 7 / 410 (1.71%) nb_accumulated 36 / 410 (finishes Tue 08:41 -- 612/h)
20240813-08:06:05 keep c_quizzes model 0 validated 7 / 410 (1.71%) nb_accumulated 43 / 410 (finishes Tue 08:43 -- 595/h)
20240813-08:06:53 keep c_quizzes model 2 validated 11 / 410 (2.68%) nb_accumulated 54 / 410 (finishes Tue 08:40 -- 631/h)
20240813-08:07:41 keep c_quizzes model 1 validated 12 / 410 (2.93%) nb_accumulated 66 / 410 (finishes Tue 08:38 -- 667/h)
20240813-08:08:29 keep c_quizzes model 0 validated 8 / 410 (1.95%) nb_accumulated 74 / 410 (finishes Tue 08:39 -- 659/h)
20240813-08:09:17 keep c_quizzes model 4 validated 6 / 410 (1.46%) nb_accumulated 80 / 410 (finishes Tue 08:40 -- 637/h)
20240813-08:10:05 keep c_quizzes model 4 validated 4 / 410 (0.98%) nb_accumulated 84 / 410 (finishes Tue 08:42 -- 604/h)
20240813-08:10:54 keep c_quizzes model 0 validated 15 / 410 (3.66%) nb_accumulated 99 / 410 (finishes Tue 08:39 -- 649/h)
20240813-08:11:42 keep c_quizzes model 0 validated 9 / 410 (2.20%) nb_accumulated 108 / 410 (finishes Tue 08:39 -- 651/h)
20240813-08:12:29 keep c_quizzes model 4 validated 5 / 410 (1.22%) nb_accumulated 113 / 410 (finishes Tue 08:40 -- 631/h)
20240813-08:13:18 keep c_quizzes model 2 validated 10 / 410 (2.44%) nb_accumulated 123 / 410 (finishes Tue 08:40 -- 639/h)
20240813-08:14:06 keep c_quizzes model 2 validated 6 / 410 (1.46%) nb_accumulated 129 / 410 (finishes Tue 08:40 -- 627/h)
20240813-08:14:54 keep c_quizzes model 3 validated 6 / 410 (1.46%) nb_accumulated 135 / 410 (finishes Tue 08:41 -- 616/h)
20240813-08:15:42 keep c_quizzes model 2 validated 11 / 410 (2.68%) nb_accumulated 146 / 410 (finishes Tue 08:40 -- 628/h)
20240813-08:16:30 keep c_quizzes model 3 validated 11 / 410 (2.68%) nb_accumulated 157 / 410 (finishes Tue 08:40 -- 638/h)
20240813-08:17:18 keep c_quizzes model 0 validated 13 / 410 (3.17%) nb_accumulated 170 / 410 (finishes Tue 08:39 -- 656/h)
20240813-08:18:06 keep c_quizzes model 0 validated 12 / 410 (2.93%) nb_accumulated 182 / 410 (finishes Tue 08:38 -- 667/h)
20240813-08:18:55 keep c_quizzes model 0 validated 12 / 410 (2.93%) nb_accumulated 194 / 410 (finishes Tue 08:38 -- 678/h)
20240813-08:19:43 keep c_quizzes model 2 validated 8 / 410 (1.95%) nb_accumulated 202 / 410 (finishes Tue 08:38 -- 675/h)
20240813-08:20:31 keep c_quizzes model 2 validated 8 / 410 (1.95%) nb_accumulated 210 / 410 (finishes Tue 08:38 -- 671/h)
20240813-08:21:19 keep c_quizzes model 3 validated 5 / 410 (1.22%) nb_accumulated 215 / 410 (finishes Tue 08:39 -- 659/h)
20240813-08:22:07 keep c_quizzes model 4 validated 10 / 410 (2.44%) nb_accumulated 225 / 410 (finishes Tue 08:38 -- 663/h)
20240813-08:22:55 keep c_quizzes model 0 validated 9 / 410 (2.20%) nb_accumulated 234 / 410 (finishes Tue 08:38 -- 663/h)
20240813-08:23:43 keep c_quizzes model 3 validated 17 / 410 (4.15%) nb_accumulated 251 / 410 (finishes Tue 08:37 -- 685/h)
20240813-08:24:31 keep c_quizzes model 2 validated 7 / 410 (1.71%) nb_accumulated 258 / 410 (finishes Tue 08:37 -- 680/h)
20240813-08:25:19 keep c_quizzes model 4 validated 8 / 410 (1.95%) nb_accumulated 266 / 410 (finishes Tue 08:38 -- 677/h)
20240813-08:26:07 keep c_quizzes model 0 validated 13 / 410 (3.17%) nb_accumulated 279 / 410 (finishes Tue 08:37 -- 687/h)
20240813-08:26:55 keep c_quizzes model 1 validated 6 / 410 (1.46%) nb_accumulated 285 / 410 (finishes Tue 08:37 -- 679/h)
20240813-08:27:43 keep c_quizzes model 3 validated 9 / 410 (2.20%) nb_accumulated 294 / 410 (finishes Tue 08:37 -- 679/h)
20240813-08:28:31 keep c_quizzes model 2 validated 6 / 410 (1.46%) nb_accumulated 300 / 410 (finishes Tue 08:38 -- 672/h)
20240813-08:29:19 keep c_quizzes model 4 validated 10 / 410 (2.44%) nb_accumulated 310 / 410 (finishes Tue 08:38 -- 674/h)
20240813-08:30:08 keep c_quizzes model 2 validated 9 / 410 (2.20%) nb_accumulated 319 / 410 (finishes Tue 08:38 -- 674/h)
20240813-08:30:56 keep c_quizzes model 2 validated 9 / 410 (2.20%) nb_accumulated 328 / 410 (finishes Tue 08:38 -- 674/h)
20240813-08:31:44 keep c_quizzes model 2 validated 7 / 410 (1.71%) nb_accumulated 335 / 410 (finishes Tue 08:38 -- 670/h)
20240813-08:32:33 keep c_quizzes model 0 validated 7 / 410 (1.71%) nb_accumulated 342 / 410 (finishes Tue 08:38 -- 666/h)
20240813-08:33:21 keep c_quizzes model 4 validated 5 / 410 (1.22%) nb_accumulated 347 / 410 (finishes Tue 08:39 -- 659/h)
20240813-08:34:09 keep c_quizzes model 2 validated 19 / 410 (4.63%) nb_accumulated 366 / 410 (finishes Tue 08:38 -- 677/h)
20240813-08:34:57 keep c_quizzes model 2 validated 4 / 410 (0.98%) nb_accumulated 370 / 410 (finishes Tue 08:38 -- 668/h)
20240813-08:35:45 keep c_quizzes model 3 validated 11 / 410 (2.68%) nb_accumulated 381 / 410 (finishes Tue 08:38 -- 672/h)
20240813-08:36:34 keep c_quizzes model 0 validated 7 / 410 (1.71%) nb_accumulated 388 / 410 (finishes Tue 08:38 -- 668/h)
20240813-08:37:22 keep c_quizzes model 4 validated 8 / 410 (1.95%) nb_accumulated 396 / 410 (finishes Tue 08:38 -- 667/h)
20240813-08:38:10 keep c_quizzes model 4 validated 7 / 410 (1.71%) nb_accumulated 403 / 410 (finishes Tue 08:38 -- 664/h)
20240813-08:38:58 keep c_quizzes model 2 validated 9 / 410 (2.20%) nb_accumulated 412 / 410 (finishes now! -- 664/h)
20240813-08:39:02 wrote c_quizzes.pth
20240813-08:39:02 training model 0
20240813-08:39:02 training model 1
20240813-08:42:46 train_perplexity 143 model 0 1.157599883795727
20240813-08:42:46 train_perplexity 143 model 1 1.1580040684063018
20240813-08:42:50 test_perplexity 143 model 0 1.156194838092874
20240813-08:42:50 test_perplexity 143 model 1 1.1564237833714295
20240813-08:43:36 test_accuracy 143 model 1 val 795 / 838
20240813-08:43:38 test_accuracy 143 model 0 val 747 / 795
20240813-08:43:40 wrote gpt_000.pth
20240813-08:43:40 wrote gpt_001.pth
20240813-08:43:53 wrote non_validated_0143_00.png
20240813-08:44:06 wrote non_validated_0143_01.png
20240813-08:44:06 wrote state.pth
20240813-08:44:06 --- epoch 144 ----------------------------------------
20240813-08:44:06 current_test_accuracies 0.9396 0.9487 0.0000 0.0000 0.0000
20240813-08:44:06 training model 2
20240813-08:44:06 training model 3
20240813-08:47:52 train_perplexity 144 model 2 1.1574580264939094
20240813-08:47:52 train_perplexity 144 model 3 1.1574729226786544
20240813-08:47:55 test_perplexity 144 model 2 1.1562289566986201
20240813-08:47:56 test_perplexity 144 model 3 1.1552540567504574
20240813-08:48:40 test_accuracy 144 model 3 val 766 / 802
20240813-08:48:41 test_accuracy 144 model 2 val 774 / 812
20240813-08:48:43 wrote gpt_002.pth
20240813-08:48:44 wrote gpt_003.pth
20240813-08:48:57 wrote non_validated_0144_02.png
20240813-08:49:10 wrote non_validated_0144_03.png
20240813-08:49:10 wrote state.pth
20240813-08:49:10 --- epoch 145 ----------------------------------------
20240813-08:49:10 current_test_accuracies 0.9396 0.9487 0.9532 0.9551 0.0000
20240813-08:49:10 training model 4
20240813-08:49:10 training model 0
20240813-08:52:56 train_perplexity 145 model 4 1.1576008205400725
20240813-08:52:56 train_perplexity 145 model 0 1.1572462821884097
20240813-08:52:59 test_perplexity 145 model 4 1.154016544870203
20240813-08:53:00 test_perplexity 145 model 0 1.1560120632869082
20240813-08:53:47 test_accuracy 145 model 0 val 743 / 781
20240813-08:53:48 test_accuracy 145 model 4 val 760 / 797
20240813-08:53:50 wrote gpt_004.pth
20240813-08:53:50 wrote gpt_000.pth
20240813-08:54:03 wrote non_validated_0145_04.png
20240813-08:54:16 wrote non_validated_0145_00.png
20240813-08:54:17 wrote state.pth
20240813-08:54:17 --- epoch 146 ----------------------------------------
20240813-08:54:17 current_test_accuracies 0.9513 0.9487 0.9532 0.9551 0.9536
20240813-08:54:17 training model 1
20240813-08:54:17 training model 0
20240813-08:58:02 train_perplexity 146 model 1 1.1577797051122625
20240813-08:58:03 train_perplexity 146 model 0 1.1569333544165576
20240813-08:58:04 test_perplexity 146 model 1 1.1576775928566478
20240813-08:58:06 test_perplexity 146 model 0 1.157492157506149
20240813-08:58:50 test_accuracy 146 model 0 val 753 / 802
20240813-08:58:51 test_accuracy 146 model 1 val 764 / 803
20240813-08:58:53 wrote gpt_001.pth
20240813-08:58:54 wrote gpt_000.pth
20240813-08:59:07 wrote non_validated_0146_01.png
20240813-08:59:20 wrote non_validated_0146_00.png
20240813-08:59:20 wrote state.pth
20240813-08:59:20 --- epoch 147 ----------------------------------------
20240813-08:59:20 current_test_accuracies 0.9389 0.9514 0.9532 0.9551 0.9536
20240813-08:59:20 training model 0
20240813-08:59:20 training model 1
20240813-09:03:05 train_perplexity 147 model 0 1.156851993131254
20240813-09:03:06 train_perplexity 147 model 1 1.1574701738150597
20240813-09:03:06 test_perplexity 147 model 0 1.155649094955142
20240813-09:03:09 test_perplexity 147 model 1 1.1544674561199757
20240813-09:03:52 test_accuracy 147 model 0 val 772 / 811
20240813-09:03:55 test_accuracy 147 model 1 val 761 / 795
20240813-09:03:57 wrote gpt_000.pth
20240813-09:03:58 wrote gpt_001.pth
20240813-09:04:11 wrote non_validated_0147_00.png
20240813-09:04:24 wrote non_validated_0147_01.png
20240813-09:04:24 wrote state.pth
20240813-09:04:24 --- epoch 148 ----------------------------------------
20240813-09:04:24 current_test_accuracies 0.9519 0.9572 0.9532 0.9551 0.9536
20240813-09:05:36 keep c_quizzes model 2 validated 11 / 410 (2.68%) nb_accumulated 11 / 410 (finishes Tue 09:48 -- 553/h)
20240813-09:06:24 keep c_quizzes model 0 validated 10 / 410 (2.44%) nb_accumulated 21 / 410 (finishes Tue 09:43 -- 628/h)
20240813-09:07:13 keep c_quizzes model 0 validated 10 / 410 (2.44%) nb_accumulated 31 / 410 (finishes Tue 09:41 -- 662/h)
20240813-09:08:01 keep c_quizzes model 1 validated 10 / 410 (2.44%) nb_accumulated 41 / 410 (finishes Tue 09:40 -- 679/h)
20240813-09:08:50 keep c_quizzes model 3 validated 9 / 410 (2.20%) nb_accumulated 50 / 410 (finishes Tue 09:40 -- 677/h)
20240813-09:09:38 keep c_quizzes model 3 validated 10 / 410 (2.44%) nb_accumulated 60 / 410 (finishes Tue 09:40 -- 687/h)
20240813-09:10:27 keep c_quizzes model 0 validated 13 / 410 (3.17%) nb_accumulated 73 / 410 (finishes Tue 09:38 -- 724/h)
20240813-09:11:15 keep c_quizzes model 4 validated 9 / 410 (2.20%) nb_accumulated 82 / 410 (finishes Tue 09:38 -- 718/h)
20240813-09:12:04 keep c_quizzes model 1 validated 8 / 410 (1.95%) nb_accumulated 90 / 410 (finishes Tue 09:39 -- 705/h)
20240813-09:12:52 keep c_quizzes model 4 validated 11 / 410 (2.68%) nb_accumulated 101 / 410 (finishes Tue 09:38 -- 715/h)
20240813-09:13:40 keep c_quizzes model 2 validated 10 / 410 (2.44%) nb_accumulated 111 / 410 (finishes Tue 09:38 -- 718/h)
20240813-09:14:29 keep c_quizzes model 3 validated 13 / 410 (3.17%) nb_accumulated 124 / 410 (finishes Tue 09:37 -- 737/h)
20240813-09:15:18 keep c_quizzes model 3 validated 12 / 410 (2.93%) nb_accumulated 136 / 410 (finishes Tue 09:37 -- 748/h)
20240813-09:16:06 keep c_quizzes model 0 validated 15 / 410 (3.66%) nb_accumulated 151 / 410 (finishes Tue 09:36 -- 774/h)
20240813-09:16:55 keep c_quizzes model 1 validated 13 / 410 (3.17%) nb_accumulated 164 / 410 (finishes Tue 09:35 -- 786/h)
20240813-09:17:43 keep c_quizzes model 3 validated 16 / 410 (3.90%) nb_accumulated 180 / 410 (finishes Tue 09:34 -- 811/h)
20240813-09:18:31 keep c_quizzes model 3 validated 16 / 410 (3.90%) nb_accumulated 196 / 410 (finishes Tue 09:33 -- 832/h)
20240813-09:19:20 keep c_quizzes model 2 validated 7 / 410 (1.71%) nb_accumulated 203 / 410 (finishes Tue 09:34 -- 815/h)
20240813-09:20:08 keep c_quizzes model 0 validated 12 / 410 (2.93%) nb_accumulated 215 / 410 (finishes Tue 09:34 -- 819/h)
20240813-09:20:57 keep c_quizzes model 2 validated 15 / 410 (3.66%) nb_accumulated 230 / 410 (finishes Tue 09:33 -- 833/h)
20240813-09:21:45 keep c_quizzes model 1 validated 13 / 410 (3.17%) nb_accumulated 243 / 410 (finishes Tue 09:33 -- 840/h)
20240813-09:22:34 keep c_quizzes model 0 validated 16 / 410 (3.90%) nb_accumulated 259 / 410 (finishes Tue 09:33 -- 855/h)
20240813-09:23:23 keep c_quizzes model 1 validated 16 / 410 (3.90%) nb_accumulated 275 / 410 (finishes Tue 09:32 -- 869/h)
20240813-09:24:11 keep c_quizzes model 1 validated 14 / 410 (3.41%) nb_accumulated 289 / 410 (finishes Tue 09:32 -- 876/h)
20240813-09:24:59 keep c_quizzes model 0 validated 17 / 410 (4.15%) nb_accumulated 306 / 410 (finishes Tue 09:31 -- 891/h)
20240813-09:25:48 keep c_quizzes model 4 validated 10 / 410 (2.44%) nb_accumulated 316 / 410 (finishes Tue 09:32 -- 885/h)
20240813-09:26:36 keep c_quizzes model 0 validated 11 / 410 (2.68%) nb_accumulated 327 / 410 (finishes Tue 09:32 -- 883/h)
20240813-09:27:25 keep c_quizzes model 0 validated 11 / 410 (2.68%) nb_accumulated 338 / 410 (finishes Tue 09:32 -- 881/h)
20240813-09:28:13 keep c_quizzes model 4 validated 10 / 410 (2.44%) nb_accumulated 348 / 410 (finishes Tue 09:32 -- 876/h)
20240813-09:29:02 keep c_quizzes model 0 validated 11 / 410 (2.68%) nb_accumulated 359 / 410 (finishes Tue 09:32 -- 874/h)
20240813-09:29:50 keep c_quizzes model 2 validated 14 / 410 (3.41%) nb_accumulated 373 / 410 (finishes Tue 09:32 -- 879/h)
20240813-09:30:39 keep c_quizzes model 3 validated 9 / 410 (2.20%) nb_accumulated 382 / 410 (finishes Tue 09:32 -- 873/h)
20240813-09:31:28 keep c_quizzes model 1 validated 10 / 410 (2.44%) nb_accumulated 392 / 410 (finishes Tue 09:32 -- 869/h)
20240813-09:32:16 keep c_quizzes model 4 validated 20 / 410 (4.88%) nb_accumulated 412 / 410 (finishes now! -- 886/h)
20240813-09:32:20 wrote c_quizzes.pth
20240813-09:32:20 training model 0
20240813-09:32:20 training model 1
20240813-09:36:04 train_perplexity 148 model 0 1.1579426530326271
20240813-09:36:05 train_perplexity 148 model 1 1.1582012002659907
20240813-09:36:06 test_perplexity 148 model 0 1.1553715540602014
20240813-09:36:08 test_perplexity 148 model 1 1.1550393220873534
20240813-09:36:51 test_accuracy 148 model 0 val 772 / 812
20240813-09:36:55 test_accuracy 148 model 1 val 759 / 799
20240813-09:36:57 wrote gpt_000.pth
20240813-09:36:57 wrote gpt_001.pth
20240813-09:37:10 wrote non_validated_0148_00.png
20240813-09:37:23 wrote non_validated_0148_01.png
20240813-09:37:23 wrote state.pth
20240813-09:37:23 --- epoch 149 ----------------------------------------
20240813-09:37:23 current_test_accuracies 0.9507 0.9499 0.0000 0.0000 0.0000
20240813-09:37:23 training model 2
20240813-09:37:23 training model 3
20240813-09:41:09 train_perplexity 149 model 2 1.1583294843637744
20240813-09:41:09 train_perplexity 149 model 3 1.1584825852285776
20240813-09:41:11 test_perplexity 149 model 2 1.1546755524030516
20240813-09:41:13 test_perplexity 149 model 3 1.1558443985365279
20240813-09:41:57 test_accuracy 149 model 3 val 749 / 806
20240813-09:42:00 test_accuracy 149 model 2 val 768 / 796
20240813-09:42:01 wrote gpt_002.pth
20240813-09:42:02 wrote gpt_003.pth
20240813-09:42:15 wrote non_validated_0149_02.png
20240813-09:42:28 wrote non_validated_0149_03.png
20240813-09:42:28 wrote state.pth
20240813-09:42:28 --- epoch 150 ----------------------------------------
20240813-09:42:28 current_test_accuracies 0.9507 0.9499 0.9648 0.9293 0.0000
20240813-09:42:28 training model 4
20240813-09:42:28 training model 3
20240813-09:46:14 train_perplexity 150 model 4 1.1580673456523782
20240813-09:46:14 train_perplexity 150 model 3 1.1584024411108547
20240813-09:46:17 test_perplexity 150 model 4 1.1546975397379886
20240813-09:46:18 test_perplexity 150 model 3 1.1562903165130685
20240813-09:47:01 test_accuracy 150 model 4 val 764 / 804
20240813-09:47:04 test_accuracy 150 model 3 val 786 / 833
20240813-09:47:06 wrote gpt_004.pth
20240813-09:47:07 wrote gpt_003.pth
20240813-09:47:19 wrote non_validated_0150_04.png
20240813-09:47:32 wrote non_validated_0150_03.png
20240813-09:47:33 wrote state.pth
20240813-09:47:33 --- epoch 151 ----------------------------------------
20240813-09:47:33 current_test_accuracies 0.9507 0.9499 0.9648 0.9436 0.9502
20240813-09:47:33 training model 3
20240813-09:47:33 training model 1
20240813-09:51:18 train_perplexity 151 model 3 1.1582786342557845
20240813-09:51:19 train_perplexity 151 model 1 1.157947604222623
20240813-09:51:20 test_perplexity 151 model 3 1.1572561783541815
20240813-09:51:22 test_perplexity 151 model 1 1.154331874005225
20240813-09:52:07 test_accuracy 151 model 1 val 766 / 807
20240813-09:52:08 test_accuracy 151 model 3 val 746 / 788
20240813-09:52:10 wrote gpt_003.pth
20240813-09:52:11 wrote gpt_001.pth
20240813-09:52:24 wrote non_validated_0151_03.png
20240813-09:52:37 wrote non_validated_0151_01.png
20240813-09:52:37 wrote state.pth
20240813-09:52:37 --- epoch 152 ----------------------------------------
20240813-09:52:37 current_test_accuracies 0.9507 0.9492 0.9648 0.9467 0.9502
20240813-09:52:37 training model 3
20240813-09:52:37 training model 1
20240813-09:56:22 train_perplexity 152 model 3 1.1585274942806743
20240813-09:56:23 train_perplexity 152 model 1 1.1579925416600232
20240813-09:56:24 test_perplexity 152 model 3 1.155735161980988
20240813-09:56:26 test_perplexity 152 model 1 1.1543761905718137
20240813-09:57:08 test_accuracy 152 model 3 val 767 / 802
20240813-09:57:12 test_accuracy 152 model 1 val 753 / 782
20240813-09:57:13 wrote gpt_003.pth
20240813-09:57:14 wrote gpt_001.pth
20240813-09:57:27 wrote non_validated_0152_03.png
20240813-09:57:40 wrote non_validated_0152_01.png
20240813-09:57:40 wrote state.pth
20240813-09:57:40 --- epoch 153 ----------------------------------------
20240813-09:57:40 current_test_accuracies 0.9507 0.9629 0.9648 0.9564 0.9502
20240813-09:58:53 keep c_quizzes model 3 validated 7 / 410 (1.71%) nb_accumulated 7 / 410 (finishes Tue 11:08 -- 345/h)
20240813-09:59:42 keep c_quizzes model 0 validated 13 / 410 (3.17%) nb_accumulated 20 / 410 (finishes Tue 10:39 -- 592/h)
20240813-10:00:30 keep c_quizzes model 4 validated 12 / 410 (2.93%) nb_accumulated 32 / 410 (finishes Tue 10:33 -- 678/h)
20240813-10:01:18 keep c_quizzes model 4 validated 7 / 410 (1.71%) nb_accumulated 39 / 410 (finishes Tue 10:35 -- 643/h)
20240813-10:02:07 keep c_quizzes model 0 validated 7 / 410 (1.71%) nb_accumulated 46 / 410 (finishes Tue 10:37 -- 621/h)
20240813-10:02:55 keep c_quizzes model 4 validated 10 / 410 (2.44%) nb_accumulated 56 / 410 (finishes Tue 10:36 -- 640/h)
20240813-10:03:43 keep c_quizzes model 1 validated 11 / 410 (2.68%) nb_accumulated 67 / 410 (finishes Tue 10:34 -- 664/h)
20240813-10:04:32 keep c_quizzes model 1 validated 11 / 410 (2.68%) nb_accumulated 78 / 410 (finishes Tue 10:33 -- 682/h)
20240813-10:05:20 keep c_quizzes model 2 validated 14 / 410 (3.41%) nb_accumulated 92 / 410 (finishes Tue 10:31 -- 720/h)
20240813-10:06:08 keep c_quizzes model 1 validated 14 / 410 (3.41%) nb_accumulated 106 / 410 (finishes Tue 10:30 -- 751/h)
20240813-10:06:56 keep c_quizzes model 2 validated 7 / 410 (1.71%) nb_accumulated 113 / 410 (finishes Tue 10:31 -- 731/h)
20240813-10:07:45 keep c_quizzes model 2 validated 12 / 410 (2.93%) nb_accumulated 125 / 410 (finishes Tue 10:30 -- 744/h)
20240813-10:08:33 keep c_quizzes model 2 validated 5 / 410 (1.22%) nb_accumulated 130 / 410 (finishes Tue 10:31 -- 717/h)
20240813-10:09:21 keep c_quizzes model 3 validated 11 / 410 (2.68%) nb_accumulated 141 / 410 (finishes Tue 10:31 -- 723/h)
20240813-10:10:10 keep c_quizzes model 4 validated 10 / 410 (2.44%) nb_accumulated 151 / 410 (finishes Tue 10:31 -- 725/h)
20240813-10:10:58 keep c_quizzes model 2 validated 7 / 410 (1.71%) nb_accumulated 158 / 410 (finishes Tue 10:32 -- 712/h)
20240813-10:11:46 keep c_quizzes model 4 validated 5 / 410 (1.22%) nb_accumulated 163 / 410 (finishes Tue 10:33 -- 693/h)
20240813-10:12:34 keep c_quizzes model 3 validated 15 / 410 (3.66%) nb_accumulated 178 / 410 (finishes Tue 10:32 -- 716/h)
20240813-10:13:23 keep c_quizzes model 2 validated 8 / 410 (1.95%) nb_accumulated 186 / 410 (finishes Tue 10:32 -- 710/h)
20240813-10:14:11 keep c_quizzes model 0 validated 15 / 410 (3.66%) nb_accumulated 201 / 410 (finishes Tue 10:31 -- 730/h)
20240813-10:14:59 keep c_quizzes model 3 validated 8 / 410 (1.95%) nb_accumulated 209 / 410 (finishes Tue 10:31 -- 724/h)
20240813-10:15:48 keep c_quizzes model 1 validated 11 / 410 (2.68%) nb_accumulated 220 / 410 (finishes Tue 10:31 -- 728/h)
20240813-10:16:36 keep c_quizzes model 3 validated 7 / 410 (1.71%) nb_accumulated 227 / 410 (finishes Tue 10:31 -- 719/h)
20240813-10:17:24 keep c_quizzes model 1 validated 5 / 410 (1.22%) nb_accumulated 232 / 410 (finishes Tue 10:32 -- 705/h)
20240813-10:18:13 keep c_quizzes model 2 validated 6 / 410 (1.46%) nb_accumulated 238 / 410 (finishes Tue 10:33 -- 695/h)
20240813-10:19:01 keep c_quizzes model 0 validated 7 / 410 (1.71%) nb_accumulated 245 / 410 (finishes Tue 10:33 -- 688/h)
20240813-10:19:49 keep c_quizzes model 1 validated 7 / 410 (1.71%) nb_accumulated 252 / 410 (finishes Tue 10:33 -- 682/h)
20240813-10:20:38 keep c_quizzes model 4 validated 6 / 410 (1.46%) nb_accumulated 258 / 410 (finishes Tue 10:34 -- 674/h)
20240813-10:21:26 keep c_quizzes model 3 validated 10 / 410 (2.44%) nb_accumulated 268 / 410 (finishes Tue 10:34 -- 676/h)
20240813-10:22:14 keep c_quizzes model 4 validated 3 / 410 (0.73%) nb_accumulated 271 / 410 (finishes Tue 10:34 -- 661/h)
20240813-10:23:02 keep c_quizzes model 0 validated 4 / 410 (0.98%) nb_accumulated 275 / 410 (finishes Tue 10:35 -- 650/h)
20240813-10:23:51 keep c_quizzes model 1 validated 7 / 410 (1.71%) nb_accumulated 282 / 410 (finishes Tue 10:35 -- 646/h)
20240813-10:24:39 keep c_quizzes model 4 validated 12 / 410 (2.93%) nb_accumulated 294 / 410 (finishes Tue 10:35 -- 653/h)
20240813-10:25:27 keep c_quizzes model 2 validated 8 / 410 (1.95%) nb_accumulated 302 / 410 (finishes Tue 10:35 -- 652/h)
20240813-10:26:15 keep c_quizzes model 0 validated 5 / 410 (1.22%) nb_accumulated 307 / 410 (finishes Tue 10:35 -- 644/h)
20240813-10:27:03 keep c_quizzes model 2 validated 9 / 410 (2.20%) nb_accumulated 316 / 410 (finishes Tue 10:35 -- 645/h)
20240813-10:27:52 keep c_quizzes model 2 validated 8 / 410 (1.95%) nb_accumulated 324 / 410 (finishes Tue 10:35 -- 643/h)
20240813-10:28:40 keep c_quizzes model 4 validated 10 / 410 (2.44%) nb_accumulated 334 / 410 (finishes Tue 10:35 -- 646/h)
20240813-10:29:28 keep c_quizzes model 2 validated 10 / 410 (2.44%) nb_accumulated 344 / 410 (finishes Tue 10:35 -- 648/h)
20240813-10:30:17 keep c_quizzes model 4 validated 8 / 410 (1.95%) nb_accumulated 352 / 410 (finishes Tue 10:35 -- 647/h)
20240813-10:31:05 keep c_quizzes model 3 validated 9 / 410 (2.20%) nb_accumulated 361 / 410 (finishes Tue 10:35 -- 648/h)
20240813-10:31:53 keep c_quizzes model 3 validated 10 / 410 (2.44%) nb_accumulated 371 / 410 (finishes Tue 10:35 -- 650/h)
20240813-10:32:41 keep c_quizzes model 0 validated 7 / 410 (1.71%) nb_accumulated 378 / 410 (finishes Tue 10:35 -- 647/h)
20240813-10:33:30 keep c_quizzes model 4 validated 13 / 410 (3.17%) nb_accumulated 391 / 410 (finishes Tue 10:35 -- 654/h)
20240813-10:34:18 keep c_quizzes model 3 validated 14 / 410 (3.41%) nb_accumulated 405 / 410 (finishes Tue 10:34 -- 663/h)
20240813-10:35:06 keep c_quizzes model 1 validated 8 / 410 (1.95%) nb_accumulated 413 / 410 (finishes now! -- 661/h)
20240813-10:35:10 wrote c_quizzes.pth
20240813-10:35:10 training model 0
20240813-10:35:10 training model 1
20240813-10:38:53 train_perplexity 153 model 0 1.1591684387119525
20240813-10:38:55 train_perplexity 153 model 1 1.1592264983162963
20240813-10:38:56 test_perplexity 153 model 0 1.1578666281015413
20240813-10:38:57 test_perplexity 153 model 1 1.1570138561107965
20240813-10:39:41 test_accuracy 153 model 0 val 756 / 804
20240813-10:39:43 test_accuracy 153 model 1 val 758 / 786
20240813-10:39:45 wrote gpt_000.pth
20240813-10:39:46 wrote gpt_001.pth
20240813-10:39:59 wrote non_validated_0153_00.png
20240813-10:40:12 wrote non_validated_0153_01.png
20240813-10:40:12 wrote state.pth
20240813-10:40:12 --- epoch 154 ----------------------------------------
20240813-10:40:12 current_test_accuracies 0.9403 0.9644 0.0000 0.0000 0.0000
20240813-10:40:12 training model 2
20240813-10:40:12 training model 3
20240813-10:43:57 train_perplexity 154 model 2 1.158877112329125
20240813-10:43:58 train_perplexity 154 model 3 1.1590462615250219
20240813-10:43:59 test_perplexity 154 model 2 1.1555696314753903
20240813-10:44:01 test_perplexity 154 model 3 1.157793169098434
20240813-10:44:47 test_accuracy 154 model 3 val 748 / 794
20240813-10:44:48 test_accuracy 154 model 2 val 754 / 787
20240813-10:44:50 wrote gpt_002.pth
20240813-10:44:51 wrote gpt_003.pth
20240813-10:45:04 wrote non_validated_0154_02.png
20240813-10:45:17 wrote non_validated_0154_03.png
20240813-10:45:17 wrote state.pth
20240813-10:45:17 --- epoch 155 ----------------------------------------
20240813-10:45:17 current_test_accuracies 0.9403 0.9644 0.9581 0.9421 0.0000
20240813-10:45:17 training model 4
20240813-10:45:17 training model 0
20240813-10:49:01 train_perplexity 155 model 4 1.1592342300287475
20240813-10:49:03 test_perplexity 155 model 4 1.1543958727481862
20240813-10:49:04 train_perplexity 155 model 0 1.1586323798723888
20240813-10:49:06 test_perplexity 155 model 0 1.1571968649644577
20240813-10:49:50 test_accuracy 155 model 4 val 744 / 790
20240813-10:49:52 test_accuracy 155 model 0 val 744 / 785
20240813-10:49:54 wrote gpt_004.pth
20240813-10:49:55 wrote gpt_000.pth
20240813-10:50:08 wrote non_validated_0155_04.png
20240813-10:50:21 wrote non_validated_0155_00.png
20240813-10:50:21 wrote state.pth
20240813-10:50:21 --- epoch 156 ----------------------------------------
20240813-10:50:21 current_test_accuracies 0.9478 0.9644 0.9581 0.9421 0.9418
20240813-10:50:21 training model 4
20240813-10:50:21 training model 3
20240813-10:54:05 train_perplexity 156 model 4 1.1589197166841487
20240813-10:54:07 train_perplexity 156 model 3 1.1589057461020058
20240813-10:54:07 test_perplexity 156 model 4 1.154285711837267
20240813-10:54:10 test_perplexity 156 model 3 1.1545797075257487
20240813-10:54:53 test_accuracy 156 model 4 val 753 / 805
20240813-10:54:56 test_accuracy 156 model 3 val 733 / 778
20240813-10:54:58 wrote gpt_004.pth
20240813-10:54:58 wrote gpt_003.pth
20240813-10:55:11 wrote non_validated_0156_04.png
20240813-10:55:24 wrote non_validated_0156_03.png
20240813-10:55:24 wrote state.pth
20240813-10:55:24 --- epoch 157 ----------------------------------------
20240813-10:55:24 current_test_accuracies 0.9478 0.9644 0.9581 0.9422 0.9354
20240813-10:55:24 training model 4
20240813-10:55:24 training model 3
20240813-10:59:09 train_perplexity 157 model 4 1.158752259869472
20240813-10:59:11 test_perplexity 157 model 4 1.1576687574923883
20240813-10:59:11 train_perplexity 157 model 3 1.158661341937386
20240813-10:59:13 test_perplexity 157 model 3 1.1582081509438267
20240813-10:59:57 test_accuracy 157 model 3 val 756 / 800
20240813-11:00:00 test_accuracy 157 model 4 val 754 / 793
20240813-11:00:02 wrote gpt_004.pth
20240813-11:00:02 wrote gpt_003.pth
20240813-11:00:15 wrote non_validated_0157_04.png
20240813-11:00:28 wrote non_validated_0157_03.png
20240813-11:00:28 wrote state.pth
20240813-11:00:28 --- epoch 158 ----------------------------------------
20240813-11:00:28 current_test_accuracies 0.9478 0.9644 0.9581 0.9450 0.9508
20240813-11:00:28 training model 3
20240813-11:00:28 training model 0
20240813-11:04:12 train_perplexity 158 model 3 1.1590663253173428
20240813-11:04:14 test_perplexity 158 model 3 1.1589899157244035
20240813-11:04:15 train_perplexity 158 model 0 1.1591830286433527
20240813-11:04:17 test_perplexity 158 model 0 1.158811056542367
20240813-11:04:58 test_accuracy 158 model 3 val 764 / 808
20240813-11:05:01 test_accuracy 158 model 0 val 784 / 818
20240813-11:05:03 wrote gpt_003.pth
20240813-11:05:03 wrote gpt_000.pth
20240813-11:05:16 wrote non_validated_0158_03.png
20240813-11:05:29 wrote non_validated_0158_00.png
20240813-11:05:29 wrote state.pth
20240813-11:05:29 --- epoch 159 ----------------------------------------
20240813-11:05:29 current_test_accuracies 0.9584 0.9644 0.9581 0.9455 0.9508
20240813-11:05:29 training model 3
20240813-11:05:29 training model 4
20240813-11:09:14 train_perplexity 159 model 3 1.1586003797395403
20240813-11:09:16 test_perplexity 159 model 3 1.1581785971834102
20240813-11:09:16 train_perplexity 159 model 4 1.1583728228311905
20240813-11:09:18 test_perplexity 159 model 4 1.1566691374552787
20240813-11:10:01 test_accuracy 159 model 4 val 763 / 806
20240813-11:10:04 test_accuracy 159 model 3 val 751 / 797
20240813-11:10:06 wrote gpt_003.pth
20240813-11:10:07 wrote gpt_004.pth
20240813-11:10:19 wrote non_validated_0159_03.png
20240813-11:10:33 wrote non_validated_0159_04.png
20240813-11:10:33 wrote state.pth
20240813-11:10:33 --- epoch 160 ----------------------------------------
20240813-11:10:33 current_test_accuracies 0.9584 0.9644 0.9581 0.9423 0.9467
20240813-11:10:33 training model 3
20240813-11:10:33 training model 4
20240813-11:14:18 train_perplexity 160 model 3 1.1584700276921491
20240813-11:14:19 train_perplexity 160 model 4 1.1584032869428798
20240813-11:14:20 test_perplexity 160 model 3 1.1592594105081147
20240813-11:14:22 test_perplexity 160 model 4 1.15963895210593
20240813-11:15:07 test_accuracy 160 model 3 val 783 / 822
20240813-11:15:08 test_accuracy 160 model 4 val 763 / 810
20240813-11:15:10 wrote gpt_003.pth
20240813-11:15:11 wrote gpt_004.pth
20240813-11:15:24 wrote non_validated_0160_03.png
20240813-11:15:37 wrote non_validated_0160_04.png
20240813-11:15:37 wrote state.pth
20240813-11:15:37 --- epoch 161 ----------------------------------------
20240813-11:15:37 current_test_accuracies 0.9584 0.9644 0.9581 0.9526 0.9420
20240813-11:15:37 training model 4
20240813-11:15:37 training model 3
20240813-11:19:22 train_perplexity 161 model 4 1.1583002346870628
20240813-11:19:23 train_perplexity 161 model 3 1.1582900770596842
20240813-11:19:25 test_perplexity 161 model 4 1.1532412554654736
20240813-11:19:26 test_perplexity 161 model 3 1.1571778417911096
20240813-11:20:13 test_accuracy 161 model 4 val 736 / 778
20240813-11:20:14 test_accuracy 161 model 3 val 751 / 789
20240813-11:20:16 wrote gpt_004.pth
20240813-11:20:17 wrote gpt_003.pth
20240813-11:20:30 wrote non_validated_0161_04.png
20240813-11:20:43 wrote non_validated_0161_03.png
20240813-11:20:43 wrote state.pth
20240813-11:20:43 --- epoch 162 ----------------------------------------
20240813-11:20:43 current_test_accuracies 0.9584 0.9644 0.9581 0.9518 0.9460
20240813-11:20:43 training model 4
20240813-11:20:43 training model 3
20240813-11:24:27 train_perplexity 162 model 4 1.1584154446860437
20240813-11:24:29 train_perplexity 162 model 3 1.1582581207324385
20240813-11:24:29 test_perplexity 162 model 4 1.1570808180615533
20240813-11:24:32 test_perplexity 162 model 3 1.1575071292784016
20240813-11:25:17 test_accuracy 162 model 3 val 775 / 812
20240813-11:25:18 test_accuracy 162 model 4 val 760 / 796
20240813-11:25:20 wrote gpt_004.pth
20240813-11:25:21 wrote gpt_003.pth
20240813-11:25:34 wrote non_validated_0162_04.png
20240813-11:25:47 wrote non_validated_0162_03.png
20240813-11:25:47 wrote state.pth
20240813-11:25:47 --- epoch 163 ----------------------------------------
20240813-11:25:47 current_test_accuracies 0.9584 0.9644 0.9581 0.9544 0.9548
20240813-11:26:59 keep c_quizzes model 4 validated 7 / 410 (1.71%) nb_accumulated 7 / 410 (finishes Tue 12:36 -- 349/h)
20240813-11:27:48 keep c_quizzes model 2 validated 17 / 410 (4.15%) nb_accumulated 24 / 410 (finishes Tue 12:00 -- 717/h)
20240813-11:28:36 keep c_quizzes model 1 validated 18 / 410 (4.39%) nb_accumulated 42 / 410 (finishes Tue 11:53 -- 895/h)
20240813-11:29:24 keep c_quizzes model 1 validated 20 / 410 (4.88%) nb_accumulated 62 / 410 (finishes Tue 11:49 -- 1027/h)
20240813-11:30:13 keep c_quizzes model 4 validated 27 / 410 (6.59%) nb_accumulated 89 / 410 (finishes Tue 11:46 -- 1205/h)
20240813-11:31:01 keep c_quizzes model 2 validated 11 / 410 (2.68%) nb_accumulated 100 / 410 (finishes Tue 11:47 -- 1146/h)
20240813-11:31:50 keep c_quizzes model 1 validated 13 / 410 (3.17%) nb_accumulated 113 / 410 (finishes Tue 11:47 -- 1121/h)
20240813-11:32:38 keep c_quizzes model 2 validated 26 / 410 (6.34%) nb_accumulated 139 / 410 (finishes Tue 11:46 -- 1217/h)
20240813-11:33:27 keep c_quizzes model 0 validated 12 / 410 (2.93%) nb_accumulated 151 / 410 (finishes Tue 11:46 -- 1182/h)
20240813-11:34:15 keep c_quizzes model 0 validated 18 / 410 (4.39%) nb_accumulated 169 / 410 (finishes Tue 11:46 -- 1197/h)
20240813-11:35:04 keep c_quizzes model 2 validated 11 / 410 (2.68%) nb_accumulated 180 / 410 (finishes Tue 11:46 -- 1164/h)
20240813-11:35:52 keep c_quizzes model 4 validated 11 / 410 (2.68%) nb_accumulated 191 / 410 (finishes Tue 11:47 -- 1136/h)
20240813-11:36:41 keep c_quizzes model 1 validated 14 / 410 (3.41%) nb_accumulated 205 / 410 (finishes Tue 11:47 -- 1129/h)
20240813-11:37:29 keep c_quizzes model 3 validated 17 / 410 (4.15%) nb_accumulated 222 / 410 (finishes Tue 11:47 -- 1138/h)
20240813-11:38:18 keep c_quizzes model 4 validated 14 / 410 (3.41%) nb_accumulated 236 / 410 (finishes Tue 11:47 -- 1132/h)
20240813-11:39:06 keep c_quizzes model 4 validated 18 / 410 (4.39%) nb_accumulated 254 / 410 (finishes Tue 11:47 -- 1144/h)
20240813-11:39:55 keep c_quizzes model 1 validated 16 / 410 (3.90%) nb_accumulated 270 / 410 (finishes Tue 11:47 -- 1147/h)
20240813-11:40:43 keep c_quizzes model 1 validated 14 / 410 (3.41%) nb_accumulated 284 / 410 (finishes Tue 11:47 -- 1141/h)
20240813-11:41:32 keep c_quizzes model 4 validated 9 / 410 (2.20%) nb_accumulated 293 / 410 (finishes Tue 11:47 -- 1117/h)
20240813-11:42:20 keep c_quizzes model 4 validated 18 / 410 (4.39%) nb_accumulated 311 / 410 (finishes Tue 11:47 -- 1127/h)
20240813-11:43:09 keep c_quizzes model 2 validated 20 / 410 (4.88%) nb_accumulated 331 / 410 (finishes Tue 11:47 -- 1144/h)
20240813-11:43:57 keep c_quizzes model 1 validated 19 / 410 (4.63%) nb_accumulated 350 / 410 (finishes Tue 11:47 -- 1156/h)
20240813-11:44:45 keep c_quizzes model 3 validated 17 / 410 (4.15%) nb_accumulated 367 / 410 (finishes Tue 11:46 -- 1160/h)
20240813-11:45:34 keep c_quizzes model 4 validated 20 / 410 (4.88%) nb_accumulated 387 / 410 (finishes Tue 11:46 -- 1174/h)
20240813-11:46:23 keep c_quizzes model 3 validated 17 / 410 (4.15%) nb_accumulated 404 / 410 (finishes Tue 11:46 -- 1177/h)
20240813-11:47:11 keep c_quizzes model 3 validated 15 / 410 (3.66%) nb_accumulated 419 / 410 (finishes now! -- 1174/h)
20240813-11:47:15 wrote c_quizzes.pth
20240813-11:47:15 training model 0
20240813-11:47:15 training model 1
20240813-11:50:58 train_perplexity 163 model 0 1.159443765835826
20240813-11:51:00 train_perplexity 163 model 1 1.1601740281264017
20240813-11:51:01 test_perplexity 163 model 0 1.1589285341860223
20240813-11:51:02 test_perplexity 163 model 1 1.1582046284594625
20240813-11:51:47 test_accuracy 163 model 1 val 759 / 802
20240813-11:51:49 test_accuracy 163 model 0 val 734 / 783
20240813-11:51:51 wrote gpt_000.pth
20240813-11:51:52 wrote gpt_001.pth
20240813-11:52:05 wrote non_validated_0163_00.png
20240813-11:52:18 wrote non_validated_0163_01.png
20240813-11:52:18 wrote state.pth
20240813-11:52:18 --- epoch 164 ----------------------------------------
20240813-11:52:18 current_test_accuracies 0.9374 0.9464 0.0000 0.0000 0.0000
20240813-11:52:18 training model 2
20240813-11:52:18 training model 3
20240813-11:56:03 train_perplexity 164 model 2 1.1602631213705046
20240813-11:56:04 train_perplexity 164 model 3 1.1593662995460947
20240813-11:56:06 test_perplexity 164 model 2 1.1557020057634066
20240813-11:56:07 test_perplexity 164 model 3 1.1600540916343545
20240813-11:56:54 test_accuracy 164 model 2 val 730 / 771
20240813-11:56:55 test_accuracy 164 model 3 val 755 / 792
20240813-11:56:57 wrote gpt_002.pth
20240813-11:56:57 wrote gpt_003.pth
20240813-11:57:10 wrote non_validated_0164_02.png
20240813-11:57:23 wrote non_validated_0164_03.png
20240813-11:57:23 wrote state.pth
20240813-11:57:23 --- epoch 165 ----------------------------------------
20240813-11:57:23 current_test_accuracies 0.9374 0.9464 0.9468 0.9533 0.0000
20240813-11:57:23 training model 4
20240813-11:57:23 training model 0
20240813-12:01:08 train_perplexity 165 model 4 1.1593911019361356
20240813-12:01:10 train_perplexity 165 model 0 1.159197159345669
20240813-12:01:10 test_perplexity 165 model 4 1.1602752427989997
20240813-12:01:12 test_perplexity 165 model 0 1.15693861043695
20240813-12:01:56 test_accuracy 165 model 0 val 753 / 802
20240813-12:01:58 test_accuracy 165 model 4 val 756 / 795
20240813-12:02:00 wrote gpt_004.pth
20240813-12:02:01 wrote gpt_000.pth
20240813-12:02:14 wrote non_validated_0165_04.png
20240813-12:02:27 wrote non_validated_0165_00.png
20240813-12:02:27 wrote state.pth
20240813-12:02:27 --- epoch 166 ----------------------------------------
20240813-12:02:27 current_test_accuracies 0.9389 0.9464 0.9468 0.9533 0.9509
20240813-12:02:27 training model 0
20240813-12:02:27 training model 1
20240813-12:06:12 train_perplexity 166 model 0 1.1597728699482055
20240813-12:06:13 train_perplexity 166 model 1 1.1593428471442127
20240813-12:06:14 test_perplexity 166 model 0 1.158288287336899
20240813-12:06:16 test_perplexity 166 model 1 1.1597484796525641
20240813-12:06:59 test_accuracy 166 model 0 val 809 / 836
20240813-12:07:01 test_accuracy 166 model 1 val 755 / 788
20240813-12:07:03 wrote gpt_000.pth
20240813-12:07:04 wrote gpt_001.pth
20240813-12:07:17 wrote non_validated_0166_00.png
20240813-12:07:30 wrote non_validated_0166_01.png
20240813-12:07:30 wrote state.pth
20240813-12:07:30 --- epoch 167 ----------------------------------------
20240813-12:07:30 current_test_accuracies 0.9677 0.9581 0.9468 0.9533 0.9509
20240813-12:07:30 training model 2
20240813-12:07:30 training model 4
20240813-12:11:15 train_perplexity 167 model 2 1.1597925439605732
20240813-12:11:16 train_perplexity 167 model 4 1.159179229215421
20240813-12:11:17 test_perplexity 167 model 2 1.1583105337589248
20240813-12:11:19 test_perplexity 167 model 4 1.158403017020753
20240813-12:12:06 test_accuracy 167 model 4 val 741 / 780
20240813-12:12:07 test_accuracy 167 model 2 val 755 / 793
20240813-12:12:09 wrote gpt_002.pth
20240813-12:12:09 wrote gpt_004.pth
20240813-12:12:22 wrote non_validated_0167_02.png
20240813-12:12:35 wrote non_validated_0167_04.png
20240813-12:12:35 wrote state.pth
20240813-12:12:35 --- epoch 168 ----------------------------------------
20240813-12:12:35 current_test_accuracies 0.9677 0.9581 0.9521 0.9533 0.9500
20240813-12:13:45 keep c_quizzes model 1 validated 17 / 410 (4.15%) nb_accumulated 17 / 410 (finishes Tue 12:40 -- 872/h)
20240813-12:14:34 keep c_quizzes model 0 validated 17 / 410 (4.15%) nb_accumulated 34 / 410 (finishes Tue 12:36 -- 1034/h)
20240813-12:15:22 keep c_quizzes model 2 validated 15 / 410 (3.66%) nb_accumulated 49 / 410 (finishes Tue 12:35 -- 1059/h)
20240813-12:16:10 keep c_quizzes model 1 validated 21 / 410 (5.12%) nb_accumulated 70 / 410 (finishes Tue 12:33 -- 1173/h)
20240813-12:16:58 keep c_quizzes model 4 validated 19 / 410 (4.63%) nb_accumulated 89 / 410 (finishes Tue 12:32 -- 1218/h)
20240813-12:17:47 keep c_quizzes model 2 validated 8 / 410 (1.95%) nb_accumulated 97 / 410 (finishes Tue 12:34 -- 1121/h)
20240813-12:18:35 keep c_quizzes model 3 validated 23 / 410 (5.61%) nb_accumulated 120 / 410 (finishes Tue 12:33 -- 1201/h)
20240813-12:19:23 keep c_quizzes model 2 validated 15 / 410 (3.66%) nb_accumulated 135 / 410 (finishes Tue 12:33 -- 1191/h)
20240813-12:20:12 keep c_quizzes model 2 validated 14 / 410 (3.41%) nb_accumulated 149 / 410 (finishes Tue 12:33 -- 1175/h)
20240813-12:21:00 keep c_quizzes model 3 validated 14 / 410 (3.41%) nb_accumulated 163 / 410 (finishes Tue 12:33 -- 1162/h)
20240813-12:21:48 keep c_quizzes model 0 validated 13 / 410 (3.17%) nb_accumulated 176 / 410 (finishes Tue 12:34 -- 1145/h)
20240813-12:22:37 keep c_quizzes model 4 validated 17 / 410 (4.15%) nb_accumulated 193 / 410 (finishes Tue 12:33 -- 1155/h)
20240813-12:23:25 keep c_quizzes model 3 validated 18 / 410 (4.39%) nb_accumulated 211 / 410 (finishes Tue 12:33 -- 1169/h)
20240813-12:24:13 keep c_quizzes model 4 validated 16 / 410 (3.90%) nb_accumulated 227 / 410 (finishes Tue 12:33 -- 1171/h)
20240813-12:25:01 keep c_quizzes model 4 validated 14 / 410 (3.41%) nb_accumulated 241 / 410 (finishes Tue 12:33 -- 1163/h)
20240813-12:25:50 keep c_quizzes model 0 validated 17 / 410 (4.15%) nb_accumulated 258 / 410 (finishes Tue 12:33 -- 1169/h)
20240813-12:26:38 keep c_quizzes model 2 validated 14 / 410 (3.41%) nb_accumulated 272 / 410 (finishes Tue 12:33 -- 1162/h)
20240813-12:27:26 keep c_quizzes model 3 validated 19 / 410 (4.63%) nb_accumulated 291 / 410 (finishes Tue 12:33 -- 1175/h)
20240813-12:28:15 keep c_quizzes model 4 validated 20 / 410 (4.88%) nb_accumulated 311 / 410 (finishes Tue 12:33 -- 1191/h)
20240813-12:29:03 keep c_quizzes model 2 validated 15 / 410 (3.66%) nb_accumulated 326 / 410 (finishes Tue 12:33 -- 1187/h)
20240813-12:29:52 keep c_quizzes model 0 validated 20 / 410 (4.88%) nb_accumulated 346 / 410 (finishes Tue 12:33 -- 1202/h)
20240813-12:30:40 keep c_quizzes model 4 validated 19 / 410 (4.63%) nb_accumulated 365 / 410 (finishes Tue 12:32 -- 1211/h)
20240813-12:31:28 keep c_quizzes model 2 validated 17 / 410 (4.15%) nb_accumulated 382 / 410 (finishes Tue 12:32 -- 1214/h)
20240813-12:32:16 keep c_quizzes model 1 validated 11 / 410 (2.68%) nb_accumulated 393 / 410 (finishes Tue 12:33 -- 1198/h)
20240813-12:33:05 keep c_quizzes model 1 validated 16 / 410 (3.90%) nb_accumulated 409 / 410 (finishes Tue 12:33 -- 1197/h)
20240813-12:33:53 keep c_quizzes model 3 validated 16 / 410 (3.90%) nb_accumulated 425 / 410 (finishes now! -- 1197/h)
20240813-12:33:57 wrote c_quizzes.pth
20240813-12:33:57 training model 0
20240813-12:33:57 training model 1
20240813-12:37:41 train_perplexity 168 model 0 1.1604770835369254
20240813-12:37:41 train_perplexity 168 model 1 1.16051922503944
20240813-12:37:44 test_perplexity 168 model 0 1.1592284134664028
20240813-12:37:45 test_perplexity 168 model 1 1.1584521940630623
20240813-12:38:29 test_accuracy 168 model 1 val 767 / 807
20240813-12:38:30 test_accuracy 168 model 0 val 759 / 811
20240813-12:38:32 wrote gpt_000.pth
20240813-12:38:33 wrote gpt_001.pth
20240813-12:38:46 wrote non_validated_0168_00.png
20240813-12:38:59 wrote non_validated_0168_01.png
20240813-12:38:59 wrote state.pth
20240813-12:38:59 --- epoch 169 ----------------------------------------
20240813-12:38:59 current_test_accuracies 0.9359 0.9504 0.0000 0.0000 0.0000
20240813-12:38:59 training model 2
20240813-12:38:59 training model 3
20240813-12:42:44 train_perplexity 169 model 2 1.1605233227185952
20240813-12:42:45 train_perplexity 169 model 3 1.1601790812510588
20240813-12:42:46 test_perplexity 169 model 2 1.1582766257843837
20240813-12:42:48 test_perplexity 169 model 3 1.1601843272031735
20240813-12:43:35 test_accuracy 169 model 2 val 749 / 795
20240813-12:43:36 test_accuracy 169 model 3 val 766 / 799
20240813-12:43:38 wrote gpt_002.pth
20240813-12:43:39 wrote gpt_003.pth
20240813-12:43:52 wrote non_validated_0169_02.png
20240813-12:44:05 wrote non_validated_0169_03.png
20240813-12:44:05 wrote state.pth
20240813-12:44:05 --- epoch 170 ----------------------------------------
20240813-12:44:05 current_test_accuracies 0.9359 0.9504 0.9421 0.9587 0.0000
20240813-12:44:05 training model 4
20240813-12:44:05 training model 0
20240813-12:47:50 train_perplexity 170 model 4 1.1605110973075943
20240813-12:47:51 train_perplexity 170 model 0 1.1602912350870944
20240813-12:47:52 test_perplexity 170 model 4 1.1593064368878294
20240813-12:47:54 test_perplexity 170 model 0 1.1577655874836346
20240813-12:48:37 test_accuracy 170 model 4 val 751 / 804
20240813-12:48:40 test_accuracy 170 model 0 val 724 / 775
20240813-12:48:42 wrote gpt_004.pth
20240813-12:48:43 wrote gpt_000.pth
20240813-12:48:56 wrote non_validated_0170_04.png
20240813-12:49:09 wrote non_validated_0170_00.png
20240813-12:49:09 wrote state.pth
20240813-12:49:09 --- epoch 171 ----------------------------------------
20240813-12:49:09 current_test_accuracies 0.9342 0.9504 0.9421 0.9587 0.9341
20240813-12:49:09 training model 4
20240813-12:49:09 training model 0
20240813-12:52:54 train_perplexity 171 model 4 1.1600085022787257
20240813-12:52:55 train_perplexity 171 model 0 1.1601634798133809
20240813-12:52:56 test_perplexity 171 model 4 1.1614704222427614
20240813-12:52:58 test_perplexity 171 model 0 1.1599732142724817
20240813-12:53:41 test_accuracy 171 model 4 val 770 / 813
20240813-12:53:43 test_accuracy 171 model 0 val 763 / 807
20240813-12:53:45 wrote gpt_004.pth
20240813-12:53:45 wrote gpt_000.pth
20240813-12:53:58 wrote non_validated_0171_04.png
20240813-12:54:11 wrote non_validated_0171_00.png
20240813-12:54:11 wrote state.pth
20240813-12:54:11 --- epoch 172 ----------------------------------------
20240813-12:54:11 current_test_accuracies 0.9455 0.9504 0.9421 0.9587 0.9471
20240813-12:54:11 training model 2
20240813-12:54:11 training model 0
20240813-12:57:56 train_perplexity 172 model 2 1.1606102740395596
20240813-12:57:58 test_perplexity 172 model 2 1.1580521704673585
20240813-12:57:58 train_perplexity 172 model 0 1.160317855653144
20240813-12:58:00 test_perplexity 172 model 0 1.160039837128005
20240813-12:58:45 test_accuracy 172 model 0 val 762 / 801
20240813-12:58:46 test_accuracy 172 model 2 val 739 / 788
20240813-12:58:48 wrote gpt_002.pth
20240813-12:58:49 wrote gpt_000.pth
20240813-12:59:02 wrote non_validated_0172_02.png
20240813-12:59:15 wrote non_validated_0172_00.png
20240813-12:59:15 wrote state.pth
20240813-12:59:15 --- epoch 173 ----------------------------------------
20240813-12:59:15 current_test_accuracies 0.9513 0.9504 0.9378 0.9587 0.9471
20240813-12:59:15 training model 2
20240813-12:59:15 training model 4
20240813-13:02:59 train_perplexity 173 model 2 1.1607852337459712
20240813-13:03:01 test_perplexity 173 model 2 1.1586213148504878
20240813-13:03:01 train_perplexity 173 model 4 1.160432083640324
20240813-13:03:04 test_perplexity 173 model 4 1.1603712563751722
20240813-13:03:50 test_accuracy 173 model 2 val 751 / 795
20240813-13:03:50 test_accuracy 173 model 4 val 747 / 792
20240813-13:03:53 wrote gpt_002.pth
20240813-13:03:53 wrote gpt_004.pth
20240813-13:04:06 wrote non_validated_0173_02.png
20240813-13:04:19 wrote non_validated_0173_04.png
20240813-13:04:19 wrote state.pth
20240813-13:04:19 --- epoch 174 ----------------------------------------
20240813-13:04:19 current_test_accuracies 0.9513 0.9504 0.9447 0.9587 0.9432
20240813-13:04:19 training model 4
20240813-13:04:19 training model 2
20240813-13:08:04 train_perplexity 174 model 4 1.1602155169911708
20240813-13:08:05 train_perplexity 174 model 2 1.1604595497025392
20240813-13:08:06 test_perplexity 174 model 4 1.1609949555139514
20240813-13:08:08 test_perplexity 174 model 2 1.1561570028832249
20240813-13:08:54 test_accuracy 174 model 4 val 744 / 783
20240813-13:08:56 test_accuracy 174 model 2 val 753 / 795
20240813-13:08:58 wrote gpt_004.pth
20240813-13:08:58 wrote gpt_002.pth
20240813-13:09:11 wrote non_validated_0174_04.png
20240813-13:09:24 wrote non_validated_0174_02.png
20240813-13:09:24 wrote state.pth
20240813-13:09:24 --- epoch 175 ----------------------------------------
20240813-13:09:24 current_test_accuracies 0.9513 0.9504 0.9472 0.9587 0.9502
20240813-13:09:24 training model 2
20240813-13:09:24 training model 4
20240813-13:13:10 train_perplexity 175 model 2 1.1602293397298078
20240813-13:13:11 train_perplexity 175 model 4 1.1600010901454467
20240813-13:13:12 test_perplexity 175 model 2 1.1595684074906674
20240813-13:13:14 test_perplexity 175 model 4 1.1598863643340973
20240813-13:13:58 test_accuracy 175 model 4 val 757 / 801
20240813-13:14:00 test_accuracy 175 model 2 val 727 / 775
20240813-13:14:02 wrote gpt_002.pth
20240813-13:14:02 wrote gpt_004.pth
20240813-13:14:15 wrote non_validated_0175_02.png
20240813-13:14:28 wrote non_validated_0175_04.png
20240813-13:14:28 wrote state.pth
20240813-13:14:28 --- epoch 176 ----------------------------------------
20240813-13:14:28 current_test_accuracies 0.9513 0.9504 0.9381 0.9587 0.9451
20240813-13:14:28 training model 2
20240813-13:14:28 training model 4
20240813-13:18:13 train_perplexity 176 model 2 1.1600776481085755
20240813-13:18:15 test_perplexity 176 model 2 1.1579665693315813
20240813-13:18:15 train_perplexity 176 model 4 1.1600066414935748
20240813-13:18:17 test_perplexity 176 model 4 1.1581906943860607
20240813-13:19:03 test_accuracy 176 model 2 val 750 / 792
20240813-13:19:05 test_accuracy 176 model 4 val 751 / 790
20240813-13:19:07 wrote gpt_002.pth
20240813-13:19:07 wrote gpt_004.pth
20240813-13:19:20 wrote non_validated_0176_02.png
20240813-13:19:33 wrote non_validated_0176_04.png
20240813-13:19:33 wrote state.pth
20240813-13:19:33 --- epoch 177 ----------------------------------------
20240813-13:19:33 current_test_accuracies 0.9513 0.9504 0.9470 0.9587 0.9506
20240813-13:19:33 training model 2
20240813-13:19:33 training model 1
20240813-13:23:18 train_perplexity 177 model 2 1.1603360623780807
20240813-13:23:19 train_perplexity 177 model 1 1.1608802647790069
20240813-13:23:20 test_perplexity 177 model 2 1.1575796296156071
20240813-13:23:22 test_perplexity 177 model 1 1.1624053612774004
20240813-13:24:07 test_accuracy 177 model 1 val 783 / 821
20240813-13:24:10 test_accuracy 177 model 2 val 763 / 796
20240813-13:24:12 wrote gpt_002.pth
20240813-13:24:12 wrote gpt_001.pth
20240813-13:24:25 wrote non_validated_0177_02.png
20240813-13:24:38 wrote non_validated_0177_01.png
20240813-13:24:38 wrote state.pth
20240813-13:24:39 --- epoch 178 ----------------------------------------
20240813-13:24:39 current_test_accuracies 0.9513 0.9537 0.9585 0.9587 0.9506
20240813-13:25:49 keep c_quizzes model 4 validated 18 / 410 (4.39%) nb_accumulated 18 / 410 (finishes Tue 13:51 -- 921/h)
20240813-13:26:37 keep c_quizzes model 4 validated 18 / 410 (4.39%) nb_accumulated 36 / 410 (finishes Tue 13:47 -- 1090/h)
20240813-13:27:26 keep c_quizzes model 4 validated 12 / 410 (2.93%) nb_accumulated 48 / 410 (finishes Tue 13:48 -- 1031/h)
20240813-13:28:15 keep c_quizzes model 3 validated 14 / 410 (3.41%) nb_accumulated 62 / 410 (finishes Tue 13:48 -- 1032/h)
20240813-13:29:03 keep c_quizzes model 3 validated 18 / 410 (4.39%) nb_accumulated 80 / 410 (finishes Tue 13:47 -- 1088/h)
20240813-13:29:52 keep c_quizzes model 2 validated 21 / 410 (5.12%) nb_accumulated 101 / 410 (finishes Tue 13:45 -- 1161/h)
20240813-13:30:40 keep c_quizzes model 3 validated 14 / 410 (3.41%) nb_accumulated 115 / 410 (finishes Tue 13:46 -- 1144/h)
20240813-13:31:29 keep c_quizzes model 2 validated 19 / 410 (4.63%) nb_accumulated 134 / 410 (finishes Tue 13:45 -- 1175/h)
20240813-13:32:17 keep c_quizzes model 4 validated 18 / 410 (4.39%) nb_accumulated 152 / 410 (finishes Tue 13:45 -- 1193/h)
20240813-13:33:06 keep c_quizzes model 4 validated 23 / 410 (5.61%) nb_accumulated 175 / 410 (finishes Tue 13:44 -- 1241/h)
20240813-13:33:54 keep c_quizzes model 4 validated 21 / 410 (5.12%) nb_accumulated 196 / 410 (finishes Tue 13:44 -- 1269/h)
20240813-13:34:43 keep c_quizzes model 1 validated 24 / 410 (5.85%) nb_accumulated 220 / 410 (finishes Tue 13:43 -- 1310/h)
20240813-13:35:31 keep c_quizzes model 2 validated 23 / 410 (5.61%) nb_accumulated 243 / 410 (finishes Tue 13:43 -- 1339/h)
20240813-13:36:20 keep c_quizzes model 3 validated 16 / 410 (3.90%) nb_accumulated 259 / 410 (finishes Tue 13:43 -- 1329/h)
20240813-13:37:08 keep c_quizzes model 1 validated 14 / 410 (3.41%) nb_accumulated 273 / 410 (finishes Tue 13:43 -- 1310/h)
20240813-13:37:57 keep c_quizzes model 3 validated 18 / 410 (4.39%) nb_accumulated 291 / 410 (finishes Tue 13:43 -- 1312/h)
20240813-13:38:45 keep c_quizzes model 2 validated 15 / 410 (3.66%) nb_accumulated 306 / 410 (finishes Tue 13:43 -- 1300/h)
20240813-13:39:34 keep c_quizzes model 4 validated 15 / 410 (3.66%) nb_accumulated 321 / 410 (finishes Tue 13:43 -- 1290/h)
20240813-13:40:23 keep c_quizzes model 1 validated 26 / 410 (6.34%) nb_accumulated 347 / 410 (finishes Tue 13:43 -- 1323/h)
20240813-13:41:11 keep c_quizzes model 0 validated 27 / 410 (6.59%) nb_accumulated 374 / 410 (finishes Tue 13:42 -- 1356/h)
20240813-13:42:00 keep c_quizzes model 1 validated 17 / 410 (4.15%) nb_accumulated 391 / 410 (finishes Tue 13:42 -- 1351/h)
20240813-13:42:48 keep c_quizzes model 1 validated 23 / 410 (5.61%) nb_accumulated 414 / 410 (finishes now! -- 1367/h)
20240813-13:42:52 wrote c_quizzes.pth
20240813-13:42:52 training model 0
20240813-13:42:52 training model 1
20240813-13:46:36 train_perplexity 178 model 0 1.1618187661021644
20240813-13:46:37 train_perplexity 178 model 1 1.1618408489949872
20240813-13:46:38 test_perplexity 178 model 0 1.161073808054974
20240813-13:46:40 test_perplexity 178 model 1 1.1601559940924209
20240813-13:47:22 test_accuracy 178 model 1 val 762 / 804
20240813-13:47:24 test_accuracy 178 model 0 val 768 / 810
20240813-13:47:26 wrote gpt_000.pth
20240813-13:47:27 wrote gpt_001.pth
20240813-13:47:39 wrote non_validated_0178_00.png
20240813-13:47:52 wrote non_validated_0178_01.png
20240813-13:47:52 wrote state.pth
20240813-13:47:52 --- epoch 179 ----------------------------------------
20240813-13:47:52 current_test_accuracies 0.9481 0.9478 0.0000 0.0000 0.0000
20240813-13:47:52 training model 2
20240813-13:47:52 training model 3
20240813-13:51:37 train_perplexity 179 model 2 1.1607334929047157
20240813-13:51:38 train_perplexity 179 model 3 1.1614723114883538
20240813-13:51:40 test_perplexity 179 model 2 1.1617764925278844
20240813-13:51:41 test_perplexity 179 model 3 1.158447345529505
20240813-13:52:24 test_accuracy 179 model 2 val 766 / 809
20240813-13:52:25 test_accuracy 179 model 3 val 767 / 810
20240813-13:52:27 wrote gpt_002.pth
20240813-13:52:27 wrote gpt_003.pth
20240813-13:52:40 wrote non_validated_0179_02.png
20240813-13:52:53 wrote non_validated_0179_03.png
20240813-13:52:53 wrote state.pth
20240813-13:52:53 --- epoch 180 ----------------------------------------
20240813-13:52:53 current_test_accuracies 0.9481 0.9478 0.9468 0.9469 0.0000
20240813-13:52:53 training model 4
20240813-13:52:53 training model 2
20240813-13:56:38 train_perplexity 180 model 4 1.1614543333216505
20240813-13:56:40 train_perplexity 180 model 2 1.1614837649010348
20240813-13:56:40 test_perplexity 180 model 4 1.1599570531748888
20240813-13:56:42 test_perplexity 180 model 2 1.1576369048971482
20240813-13:57:27 test_accuracy 180 model 4 val 763 / 804
20240813-13:57:29 test_accuracy 180 model 2 val 745 / 785
20240813-13:57:31 wrote gpt_004.pth
20240813-13:57:32 wrote gpt_002.pth
20240813-13:57:45 wrote non_validated_0180_04.png
20240813-13:57:58 wrote non_validated_0180_02.png
20240813-13:57:58 wrote state.pth
20240813-13:57:58 --- epoch 181 ----------------------------------------
20240813-13:57:58 current_test_accuracies 0.9481 0.9478 0.9490 0.9469 0.9490
20240813-13:57:58 training model 3
20240813-13:57:58 training model 1
20240813-14:01:43 train_perplexity 181 model 3 1.1617096520901629
20240813-14:01:44 train_perplexity 181 model 1 1.1620091774143435
20240813-14:01:46 test_perplexity 181 model 3 1.1595206692049824
20240813-14:01:47 test_perplexity 181 model 1 1.1605403004312163
20240813-14:02:35 test_accuracy 181 model 3 val 760 / 793
20240813-14:02:36 test_accuracy 181 model 1 val 765 / 796
20240813-14:02:38 wrote gpt_003.pth
20240813-14:02:38 wrote gpt_001.pth
20240813-14:02:51 wrote non_validated_0181_03.png
20240813-14:03:04 wrote non_validated_0181_01.png
20240813-14:03:04 wrote state.pth
20240813-14:03:04 --- epoch 182 ----------------------------------------
20240813-14:03:04 current_test_accuracies 0.9481 0.9611 0.9490 0.9584 0.9490
20240813-14:03:04 training model 0
20240813-14:03:04 training model 4
20240813-14:06:50 train_perplexity 182 model 0 1.1612127028031145
20240813-14:06:51 train_perplexity 182 model 4 1.1610426534058154
20240813-14:06:52 test_perplexity 182 model 0 1.1592822627038963
20240813-14:06:54 test_perplexity 182 model 4 1.1621324239346025
20240813-14:07:37 test_accuracy 182 model 4 val 754 / 800
20240813-14:07:39 test_accuracy 182 model 0 val 752 / 785
20240813-14:07:41 wrote gpt_000.pth
20240813-14:07:42 wrote gpt_004.pth
20240813-14:07:55 wrote non_validated_0182_00.png
20240813-14:08:08 wrote non_validated_0182_04.png
20240813-14:08:08 wrote state.pth
20240813-14:08:08 --- epoch 183 ----------------------------------------
20240813-14:08:08 current_test_accuracies 0.9580 0.9611 0.9490 0.9584 0.9425
20240813-14:08:08 training model 4
20240813-14:08:08 training model 2
20240813-14:11:52 train_perplexity 183 model 4 1.1613012256980584
20240813-14:11:54 test_perplexity 183 model 4 1.1609911036368277
20240813-14:11:55 train_perplexity 183 model 2 1.1617518576435546
20240813-14:11:57 test_perplexity 183 model 2 1.1620456688217842
20240813-14:12:41 test_accuracy 183 model 4 val 746 / 789
20240813-14:12:42 test_accuracy 183 model 2 val 790 / 826
20240813-14:12:44 wrote gpt_004.pth
20240813-14:12:45 wrote gpt_002.pth
20240813-14:12:58 wrote non_validated_0183_04.png
20240813-14:13:11 wrote non_validated_0183_02.png
20240813-14:13:11 wrote state.pth
20240813-14:13:11 --- epoch 184 ----------------------------------------
20240813-14:13:11 current_test_accuracies 0.9580 0.9611 0.9564 0.9584 0.9455
20240813-14:13:11 training model 4
20240813-14:13:11 training model 2
20240813-14:16:55 train_perplexity 184 model 4 1.160615084844121
20240813-14:16:57 test_perplexity 184 model 4 1.1631586816683728
20240813-14:16:57 train_perplexity 184 model 2 1.1613396648430565
20240813-14:17:00 test_perplexity 184 model 2 1.1601746964783626
20240813-14:17:42 test_accuracy 184 model 2 val 770 / 805
20240813-14:17:45 test_accuracy 184 model 4 val 762 / 794
20240813-14:17:47 wrote gpt_004.pth
20240813-14:17:47 wrote gpt_002.pth
20240813-14:18:00 wrote non_validated_0184_04.png
20240813-14:18:13 wrote non_validated_0184_02.png
20240813-14:18:14 wrote state.pth
20240813-14:18:14 --- epoch 185 ----------------------------------------
20240813-14:18:14 current_test_accuracies 0.9580 0.9611 0.9565 0.9584 0.9597
20240813-14:19:24 keep c_quizzes model 2 validated 13 / 410 (3.17%) nb_accumulated 13 / 410 (finishes Tue 14:55 -- 662/h)
20240813-14:20:14 keep c_quizzes model 2 validated 8 / 410 (1.95%) nb_accumulated 21 / 410 (finishes Tue 14:57 -- 629/h)
20240813-14:21:02 keep c_quizzes model 3 validated 12 / 410 (2.93%) nb_accumulated 33 / 410 (finishes Tue 14:53 -- 703/h)
20240813-14:21:52 keep c_quizzes model 4 validated 7 / 410 (1.71%) nb_accumulated 40 / 410 (finishes Tue 14:55 -- 658/h)
20240813-14:22:41 keep c_quizzes model 4 validated 10 / 410 (2.44%) nb_accumulated 50 / 410 (finishes Tue 14:54 -- 672/h)
20240813-14:23:30 keep c_quizzes model 3 validated 7 / 410 (1.71%) nb_accumulated 57 / 410 (finishes Tue 14:56 -- 648/h)
20240813-14:24:18 keep c_quizzes model 3 validated 16 / 410 (3.90%) nb_accumulated 73 / 410 (finishes Tue 14:52 -- 720/h)
20240813-14:25:07 keep c_quizzes model 4 validated 8 / 410 (1.95%) nb_accumulated 81 / 410 (finishes Tue 14:53 -- 705/h)
20240813-14:25:55 keep c_quizzes model 4 validated 10 / 410 (2.44%) nb_accumulated 91 / 410 (finishes Tue 14:52 -- 709/h)
20240813-14:26:44 keep c_quizzes model 0 validated 14 / 410 (3.41%) nb_accumulated 105 / 410 (finishes Tue 14:51 -- 741/h)
20240813-14:27:32 keep c_quizzes model 1 validated 14 / 410 (3.41%) nb_accumulated 119 / 410 (finishes Tue 14:50 -- 766/h)
20240813-14:28:21 keep c_quizzes model 2 validated 6 / 410 (1.46%) nb_accumulated 125 / 410 (finishes Tue 14:51 -- 741/h)
20240813-14:29:09 keep c_quizzes model 1 validated 13 / 410 (3.17%) nb_accumulated 138 / 410 (finishes Tue 14:50 -- 758/h)
20240813-14:29:57 keep c_quizzes model 2 validated 14 / 410 (3.41%) nb_accumulated 152 / 410 (finishes Tue 14:49 -- 777/h)
20240813-14:30:46 keep c_quizzes model 1 validated 13 / 410 (3.17%) nb_accumulated 165 / 410 (finishes Tue 14:49 -- 789/h)
20240813-14:31:34 keep c_quizzes model 1 validated 20 / 410 (4.88%) nb_accumulated 185 / 410 (finishes Tue 14:47 -- 831/h)
20240813-14:32:23 keep c_quizzes model 4 validated 17 / 410 (4.15%) nb_accumulated 202 / 410 (finishes Tue 14:46 -- 856/h)
20240813-14:33:11 keep c_quizzes model 1 validated 11 / 410 (2.68%) nb_accumulated 213 / 410 (finishes Tue 14:47 -- 854/h)
20240813-14:34:00 keep c_quizzes model 1 validated 18 / 410 (4.39%) nb_accumulated 231 / 410 (finishes Tue 14:46 -- 878/h)
20240813-14:34:48 keep c_quizzes model 2 validated 4 / 410 (0.98%) nb_accumulated 235 / 410 (finishes Tue 14:47 -- 850/h)
20240813-14:35:36 keep c_quizzes model 3 validated 7 / 410 (1.71%) nb_accumulated 242 / 410 (finishes Tue 14:47 -- 835/h)
20240813-14:36:25 keep c_quizzes model 0 validated 14 / 410 (3.41%) nb_accumulated 256 / 410 (finishes Tue 14:47 -- 844/h)
20240813-14:37:14 keep c_quizzes model 4 validated 14 / 410 (3.41%) nb_accumulated 270 / 410 (finishes Tue 14:47 -- 852/h)
20240813-14:38:02 keep c_quizzes model 0 validated 12 / 410 (2.93%) nb_accumulated 282 / 410 (finishes Tue 14:47 -- 854/h)
20240813-14:38:50 keep c_quizzes model 1 validated 17 / 410 (4.15%) nb_accumulated 299 / 410 (finishes Tue 14:46 -- 870/h)
20240813-14:39:39 keep c_quizzes model 3 validated 5 / 410 (1.22%) nb_accumulated 304 / 410 (finishes Tue 14:47 -- 851/h)
20240813-14:40:27 keep c_quizzes model 3 validated 10 / 410 (2.44%) nb_accumulated 314 / 410 (finishes Tue 14:47 -- 847/h)
20240813-14:41:16 keep c_quizzes model 1 validated 5 / 410 (1.22%) nb_accumulated 319 / 410 (finishes Tue 14:47 -- 830/h)
20240813-14:42:04 keep c_quizzes model 0 validated 18 / 410 (4.39%) nb_accumulated 337 / 410 (finishes Tue 14:47 -- 848/h)
20240813-14:42:53 keep c_quizzes model 2 validated 16 / 410 (3.90%) nb_accumulated 353 / 410 (finishes Tue 14:46 -- 859/h)
20240813-14:43:42 keep c_quizzes model 1 validated 12 / 410 (2.93%) nb_accumulated 365 / 410 (finishes Tue 14:46 -- 859/h)
20240813-14:44:30 keep c_quizzes model 1 validated 13 / 410 (3.17%) nb_accumulated 378 / 410 (finishes Tue 14:46 -- 862/h)
20240813-14:45:19 keep c_quizzes model 1 validated 8 / 410 (1.95%) nb_accumulated 386 / 410 (finishes Tue 14:47 -- 854/h)
20240813-14:46:08 keep c_quizzes model 3 validated 10 / 410 (2.44%) nb_accumulated 396 / 410 (finishes Tue 14:47 -- 851/h)
20240813-14:46:56 keep c_quizzes model 1 validated 13 / 410 (3.17%) nb_accumulated 409 / 410 (finishes Tue 14:47 -- 854/h)
20240813-14:47:45 keep c_quizzes model 1 validated 14 / 410 (3.41%) nb_accumulated 423 / 410 (finishes now! -- 859/h)
20240813-14:47:48 wrote c_quizzes.pth
20240813-14:47:48 training model 0
20240813-14:47:48 training model 1
20240813-14:51:32 train_perplexity 185 model 0 1.1627369705757153
20240813-14:51:33 train_perplexity 185 model 1 1.1625001039913208
20240813-14:51:34 test_perplexity 185 model 0 1.1610774478317587
20240813-14:51:36 test_perplexity 185 model 1 1.1631329441834581
20240813-14:52:22 test_accuracy 185 model 1 val 758 / 814
20240813-14:52:23 test_accuracy 185 model 0 val 741 / 784
20240813-14:52:25 wrote gpt_000.pth
20240813-14:52:25 wrote gpt_001.pth
20240813-14:52:38 wrote non_validated_0185_00.png
20240813-14:52:51 wrote non_validated_0185_01.png
20240813-14:52:51 wrote state.pth
20240813-14:52:51 --- epoch 186 ----------------------------------------
20240813-14:52:51 current_test_accuracies 0.9452 0.9312 0.0000 0.0000 0.0000
20240813-14:52:51 training model 2
20240813-14:52:51 training model 3
20240813-14:56:36 train_perplexity 186 model 2 1.1623135818600878
20240813-14:56:38 test_perplexity 186 model 2 1.15979330185794
20240813-14:56:38 train_perplexity 186 model 3 1.1626729448450146
20240813-14:56:40 test_perplexity 186 model 3 1.1594558054003181
20240813-14:57:27 test_accuracy 186 model 2 val 748 / 790
20240813-14:57:28 test_accuracy 186 model 3 val 746 / 789
20240813-14:57:30 wrote gpt_002.pth
20240813-14:57:31 wrote gpt_003.pth
20240813-14:57:44 wrote non_validated_0186_02.png
20240813-14:57:57 wrote non_validated_0186_03.png
20240813-14:57:57 wrote state.pth
20240813-14:57:57 --- epoch 187 ----------------------------------------
20240813-14:57:57 current_test_accuracies 0.9452 0.9312 0.9468 0.9455 0.0000
20240813-14:57:57 training model 4
20240813-14:57:57 training model 1
20240813-15:01:42 train_perplexity 187 model 4 1.161883635791908
20240813-15:01:43 train_perplexity 187 model 1 1.1628042543777068
20240813-15:01:44 test_perplexity 187 model 4 1.1594707455560758
20240813-15:01:46 test_perplexity 187 model 1 1.1611451389458178
20240813-15:02:28 test_accuracy 187 model 4 val 757 / 805
20240813-15:02:32 test_accuracy 187 model 1 val 752 / 796
20240813-15:02:34 wrote gpt_004.pth
20240813-15:02:34 wrote gpt_001.pth
20240813-15:02:47 wrote non_validated_0187_04.png
20240813-15:03:00 wrote non_validated_0187_01.png
20240813-15:03:00 wrote state.pth
20240813-15:03:00 --- epoch 188 ----------------------------------------
20240813-15:03:00 current_test_accuracies 0.9452 0.9447 0.9468 0.9455 0.9404
20240813-15:03:00 training model 4
20240813-15:03:00 training model 1
20240813-15:06:45 train_perplexity 188 model 4 1.1617008213266506
20240813-15:06:47 test_perplexity 188 model 4 1.1590182447522985
20240813-15:06:47 train_perplexity 188 model 1 1.1626286400682582
20240813-15:06:49 test_perplexity 188 model 1 1.1621158719137894
20240813-15:07:36 test_accuracy 188 model 4 val 761 / 798
20240813-15:07:37 test_accuracy 188 model 1 val 752 / 781
20240813-15:07:39 wrote gpt_004.pth
20240813-15:07:40 wrote gpt_001.pth
20240813-15:07:53 wrote non_validated_0188_04.png
20240813-15:08:06 wrote non_validated_0188_01.png
20240813-15:08:06 wrote state.pth
20240813-15:08:06 --- epoch 189 ----------------------------------------
20240813-15:08:06 current_test_accuracies 0.9452 0.9629 0.9468 0.9455 0.9536
20240813-15:08:06 training model 0
20240813-15:08:06 training model 3
20240813-15:11:50 train_perplexity 189 model 0 1.1621341580400817
20240813-15:11:52 test_perplexity 189 model 0 1.1586711619986492
20240813-15:11:52 train_perplexity 189 model 3 1.1622414243684513
20240813-15:11:55 test_perplexity 189 model 3 1.15960996705161
20240813-15:12:40 test_accuracy 189 model 0 val 751 / 782
20240813-15:12:42 test_accuracy 189 model 3 val 744 / 796
20240813-15:12:44 wrote gpt_000.pth
20240813-15:12:45 wrote gpt_003.pth
20240813-15:12:57 wrote non_validated_0189_00.png
20240813-15:13:10 wrote non_validated_0189_03.png
20240813-15:13:11 wrote state.pth
20240813-15:13:11 --- epoch 190 ----------------------------------------
20240813-15:13:11 current_test_accuracies 0.9604 0.9629 0.9468 0.9347 0.9536
20240813-15:13:11 training model 3
20240813-15:13:11 training model 2
20240813-15:16:56 train_perplexity 190 model 3 1.1620372207729703
20240813-15:16:57 train_perplexity 190 model 2 1.1622659419542674
20240813-15:16:58 test_perplexity 190 model 3 1.1604929620164461
20240813-15:17:00 test_perplexity 190 model 2 1.1596585019613308
20240813-15:17:46 test_accuracy 190 model 3 val 744 / 787
20240813-15:17:47 test_accuracy 190 model 2 val 721 / 765
20240813-15:17:49 wrote gpt_003.pth
20240813-15:17:50 wrote gpt_002.pth
20240813-15:18:03 wrote non_validated_0190_03.png
20240813-15:18:16 wrote non_validated_0190_02.png
20240813-15:18:16 wrote state.pth
20240813-15:18:16 --- epoch 191 ----------------------------------------
20240813-15:18:16 current_test_accuracies 0.9604 0.9629 0.9425 0.9454 0.9536
20240813-15:18:16 training model 2
20240813-15:18:16 training model 3
20240813-15:22:00 train_perplexity 191 model 2 1.1616950051869896
20240813-15:22:02 test_perplexity 191 model 2 1.1607652176774452
20240813-15:22:02 train_perplexity 191 model 3 1.1623771770880826
20240813-15:22:05 test_perplexity 191 model 3 1.1604831635858157
20240813-15:22:50 test_accuracy 191 model 2 val 744 / 788
20240813-15:22:53 test_accuracy 191 model 3 val 767 / 796
20240813-15:22:55 wrote gpt_002.pth
20240813-15:22:56 wrote gpt_003.pth
20240813-15:23:09 wrote non_validated_0191_02.png
20240813-15:23:22 wrote non_validated_0191_03.png
20240813-15:23:22 wrote state.pth
20240813-15:23:22 --- epoch 192 ----------------------------------------
20240813-15:23:22 current_test_accuracies 0.9604 0.9629 0.9442 0.9636 0.9536
20240813-15:23:22 training model 2
20240813-15:23:22 training model 4
20240813-15:27:06 train_perplexity 192 model 2 1.1616406236648504
20240813-15:27:08 test_perplexity 192 model 2 1.1625636543845894
20240813-15:27:08 train_perplexity 192 model 4 1.1616017782205998
20240813-15:27:11 test_perplexity 192 model 4 1.1614996039443521
20240813-15:27:53 test_accuracy 192 model 2 val 774 / 810
20240813-15:27:56 test_accuracy 192 model 4 val 750 / 794
20240813-15:27:58 wrote gpt_002.pth
20240813-15:27:59 wrote gpt_004.pth
20240813-15:28:12 wrote non_validated_0192_02.png
20240813-15:28:25 wrote non_validated_0192_04.png
20240813-15:28:25 wrote state.pth
20240813-15:28:25 --- epoch 193 ----------------------------------------
20240813-15:28:25 current_test_accuracies 0.9604 0.9629 0.9556 0.9636 0.9446
20240813-15:28:25 training model 4
20240813-15:28:25 training model 2
20240813-15:32:09 train_perplexity 193 model 4 1.1610272946911215
20240813-15:32:11 test_perplexity 193 model 4 1.1617350820969963
20240813-15:32:12 train_perplexity 193 model 2 1.16188041718917
20240813-15:32:14 test_perplexity 193 model 2 1.1602018600558512
20240813-15:32:56 test_accuracy 193 model 4 val 763 / 814
20240813-15:32:58 test_accuracy 193 model 2 val 770 / 814
20240813-15:33:00 wrote gpt_004.pth
20240813-15:33:01 wrote gpt_002.pth
20240813-15:33:14 wrote non_validated_0193_04.png
20240813-15:33:27 wrote non_validated_0193_02.png
20240813-15:33:27 wrote state.pth
20240813-15:33:27 --- epoch 194 ----------------------------------------
20240813-15:33:27 current_test_accuracies 0.9604 0.9629 0.9459 0.9636 0.9373
20240813-15:33:27 training model 4
20240813-15:33:27 training model 2
20240813-15:37:12 train_perplexity 194 model 4 1.16132568755303
20240813-15:37:13 test_perplexity 194 model 4 1.1580353090064168
20240813-15:37:14 train_perplexity 194 model 2 1.1621609924997984
20240813-15:37:16 test_perplexity 194 model 2 1.1624342598764197
20240813-15:38:00 test_accuracy 194 model 2 val 771 / 808
20240813-15:38:01 test_accuracy 194 model 4 val 743 / 786
20240813-15:38:03 wrote gpt_004.pth
20240813-15:38:04 wrote gpt_002.pth
20240813-15:38:17 wrote non_validated_0194_04.png
20240813-15:38:30 wrote non_validated_0194_02.png
20240813-15:38:30 wrote state.pth
20240813-15:38:30 --- epoch 195 ----------------------------------------
20240813-15:38:30 current_test_accuracies 0.9604 0.9629 0.9542 0.9636 0.9453
20240813-15:38:30 training model 4
20240813-15:38:30 training model 2
20240813-15:42:14 train_perplexity 195 model 4 1.1613891552864943
20240813-15:42:16 test_perplexity 195 model 4 1.1621301584242494
20240813-15:42:16 train_perplexity 195 model 2 1.1614972769436087
20240813-15:42:18 test_perplexity 195 model 2 1.157239787179108
20240813-15:43:02 test_accuracy 195 model 4 val 782 / 820
20240813-15:43:04 test_accuracy 195 model 2 val 743 / 778
20240813-15:43:06 wrote gpt_004.pth
20240813-15:43:07 wrote gpt_002.pth
20240813-15:43:20 wrote non_validated_0195_04.png
20240813-15:43:33 wrote non_validated_0195_02.png
20240813-15:43:33 wrote state.pth
20240813-15:43:33 --- epoch 196 ----------------------------------------
20240813-15:43:33 current_test_accuracies 0.9604 0.9629 0.9550 0.9636 0.9537
20240813-15:44:44 keep c_quizzes model 2 validated 11 / 410 (2.68%) nb_accumulated 11 / 410 (finishes Tue 16:27 -- 558/h)
20240813-15:45:32 keep c_quizzes model 1 validated 5 / 410 (1.22%) nb_accumulated 16 / 410 (finishes Tue 16:34 -- 483/h)
20240813-15:46:20 keep c_quizzes model 1 validated 10 / 410 (2.44%) nb_accumulated 26 / 410 (finishes Tue 16:27 -- 558/h)
20240813-15:47:09 keep c_quizzes model 1 validated 8 / 410 (1.95%) nb_accumulated 34 / 410 (finishes Tue 16:26 -- 566/h)
20240813-15:47:57 keep c_quizzes model 2 validated 9 / 410 (2.20%) nb_accumulated 43 / 410 (finishes Tue 16:25 -- 584/h)
20240813-15:48:46 keep c_quizzes model 3 validated 13 / 410 (3.17%) nb_accumulated 56 / 410 (finishes Tue 16:21 -- 643/h)
20240813-15:49:35 keep c_quizzes model 0 validated 10 / 410 (2.44%) nb_accumulated 66 / 410 (finishes Tue 16:21 -- 656/h)
20240813-15:50:23 keep c_quizzes model 0 validated 12 / 410 (2.93%) nb_accumulated 78 / 410 (finishes Tue 16:19 -- 684/h)
20240813-15:51:12 keep c_quizzes model 1 validated 13 / 410 (3.17%) nb_accumulated 91 / 410 (finishes Tue 16:18 -- 713/h)
20240813-15:52:00 keep c_quizzes model 3 validated 9 / 410 (2.20%) nb_accumulated 100 / 410 (finishes Tue 16:18 -- 709/h)
20240813-15:52:49 keep c_quizzes model 2 validated 8 / 410 (1.95%) nb_accumulated 108 / 410 (finishes Tue 16:18 -- 698/h)
20240813-15:53:38 keep c_quizzes model 0 validated 10 / 410 (2.44%) nb_accumulated 118 / 410 (finishes Tue 16:18 -- 702/h)
20240813-15:54:26 keep c_quizzes model 4 validated 9 / 410 (2.20%) nb_accumulated 127 / 410 (finishes Tue 16:18 -- 699/h)
20240813-15:55:15 keep c_quizzes model 1 validated 16 / 410 (3.90%) nb_accumulated 143 / 410 (finishes Tue 16:17 -- 733/h)
20240813-15:56:04 keep c_quizzes model 3 validated 15 / 410 (3.66%) nb_accumulated 158 / 410 (finishes Tue 16:16 -- 757/h)
20240813-15:56:52 keep c_quizzes model 1 validated 11 / 410 (2.68%) nb_accumulated 169 / 410 (finishes Tue 16:15 -- 760/h)
20240813-15:57:41 keep c_quizzes model 1 validated 9 / 410 (2.20%) nb_accumulated 178 / 410 (finishes Tue 16:16 -- 755/h)
20240813-15:58:30 keep c_quizzes model 3 validated 9 / 410 (2.20%) nb_accumulated 187 / 410 (finishes Tue 16:16 -- 750/h)
20240813-15:59:18 keep c_quizzes model 1 validated 17 / 410 (4.15%) nb_accumulated 204 / 410 (finishes Tue 16:15 -- 776/h)
20240813-16:00:07 keep c_quizzes model 3 validated 11 / 410 (2.68%) nb_accumulated 215 / 410 (finishes Tue 16:15 -- 778/h)
20240813-16:00:56 keep c_quizzes model 1 validated 14 / 410 (3.41%) nb_accumulated 229 / 410 (finishes Tue 16:14 -- 790/h)
20240813-16:01:44 keep c_quizzes model 0 validated 7 / 410 (1.71%) nb_accumulated 236 / 410 (finishes Tue 16:15 -- 778/h)
20240813-16:02:33 keep c_quizzes model 3 validated 8 / 410 (1.95%) nb_accumulated 244 / 410 (finishes Tue 16:15 -- 770/h)
20240813-16:03:21 keep c_quizzes model 0 validated 4 / 410 (0.98%) nb_accumulated 248 / 410 (finishes Tue 16:16 -- 751/h)
20240813-16:04:10 keep c_quizzes model 4 validated 8 / 410 (1.95%) nb_accumulated 256 / 410 (finishes Tue 16:16 -- 744/h)
20240813-16:04:59 keep c_quizzes model 1 validated 18 / 410 (4.39%) nb_accumulated 274 / 410 (finishes Tue 16:15 -- 767/h)
20240813-16:05:47 keep c_quizzes model 0 validated 7 / 410 (1.71%) nb_accumulated 281 / 410 (finishes Tue 16:15 -- 758/h)
20240813-16:06:35 keep c_quizzes model 1 validated 12 / 410 (2.93%) nb_accumulated 293 / 410 (finishes Tue 16:15 -- 762/h)
20240813-16:07:24 keep c_quizzes model 1 validated 14 / 410 (3.41%) nb_accumulated 307 / 410 (finishes Tue 16:15 -- 772/h)
20240813-16:08:12 keep c_quizzes model 3 validated 8 / 410 (1.95%) nb_accumulated 315 / 410 (finishes Tue 16:15 -- 766/h)
20240813-16:09:01 keep c_quizzes model 4 validated 9 / 410 (2.20%) nb_accumulated 324 / 410 (finishes Tue 16:15 -- 763/h)
20240813-16:09:49 keep c_quizzes model 1 validated 7 / 410 (1.71%) nb_accumulated 331 / 410 (finishes Tue 16:16 -- 755/h)
20240813-16:10:38 keep c_quizzes model 2 validated 8 / 410 (1.95%) nb_accumulated 339 / 410 (finishes Tue 16:16 -- 750/h)
20240813-16:11:26 keep c_quizzes model 3 validated 11 / 410 (2.68%) nb_accumulated 350 / 410 (finishes Tue 16:16 -- 752/h)
20240813-16:12:15 keep c_quizzes model 1 validated 13 / 410 (3.17%) nb_accumulated 363 / 410 (finishes Tue 16:15 -- 758/h)
20240813-16:13:04 keep c_quizzes model 4 validated 4 / 410 (0.98%) nb_accumulated 367 / 410 (finishes Tue 16:16 -- 746/h)
20240813-16:13:52 keep c_quizzes model 4 validated 15 / 410 (3.66%) nb_accumulated 382 / 410 (finishes Tue 16:16 -- 755/h)
20240813-16:14:41 keep c_quizzes model 3 validated 15 / 410 (3.66%) nb_accumulated 397 / 410 (finishes Tue 16:15 -- 765/h)
20240813-16:15:29 keep c_quizzes model 3 validated 9 / 410 (2.20%) nb_accumulated 406 / 410 (finishes Tue 16:15 -- 762/h)
20240813-16:16:17 keep c_quizzes model 1 validated 13 / 410 (3.17%) nb_accumulated 419 / 410 (finishes now! -- 767/h)
20240813-16:16:21 wrote c_quizzes.pth
20240813-16:16:21 training model 0
20240813-16:16:21 training model 1
20240813-16:20:05 train_perplexity 196 model 0 1.163581204229351
20240813-16:20:06 train_perplexity 196 model 1 1.1634161375327856
20240813-16:20:08 test_perplexity 196 model 0 1.163453811268953
20240813-16:20:09 test_perplexity 196 model 1 1.1622286734569363
20240813-16:20:49 test_accuracy 196 model 0 val 752 / 796
20240813-16:20:51 test_accuracy 196 model 1 val 745 / 786
20240813-16:20:53 wrote gpt_000.pth
20240813-16:20:54 wrote gpt_001.pth
20240813-16:21:07 wrote non_validated_0196_00.png
20240813-16:21:20 wrote non_validated_0196_01.png
20240813-16:21:20 wrote state.pth
20240813-16:21:20 --- epoch 197 ----------------------------------------
20240813-16:21:20 current_test_accuracies 0.9447 0.9478 0.0000 0.0000 0.0000
20240813-16:21:20 training model 2
20240813-16:21:20 training model 3
20240813-16:25:04 train_perplexity 197 model 2 1.1626599117126006
20240813-16:25:06 test_perplexity 197 model 2 1.1599556029888758
20240813-16:25:07 train_perplexity 197 model 3 1.1636586639665043
20240813-16:25:09 test_perplexity 197 model 3 1.1610065164121035
20240813-16:25:47 test_accuracy 197 model 3 val 778 / 814
20240813-16:25:49 test_accuracy 197 model 2 val 755 / 794
20240813-16:25:51 wrote gpt_002.pth
20240813-16:25:52 wrote gpt_003.pth
20240813-16:26:05 wrote non_validated_0197_02.png
20240813-16:26:18 wrote non_validated_0197_03.png
20240813-16:26:18 wrote state.pth
20240813-16:26:18 --- epoch 198 ----------------------------------------
20240813-16:26:18 current_test_accuracies 0.9447 0.9478 0.9509 0.9558 0.0000
20240813-16:26:18 training model 4
20240813-16:26:18 training model 0
20240813-16:30:04 train_perplexity 198 model 4 1.1625150995278903
20240813-16:30:05 test_perplexity 198 model 4 1.1624019160978825
20240813-16:30:06 train_perplexity 198 model 0 1.1632397455765031
20240813-16:30:08 test_perplexity 198 model 0 1.1631147478592316
20240813-16:30:51 test_accuracy 198 model 4 val 776 / 811
20240813-16:30:53 test_accuracy 198 model 0 val 768 / 809
20240813-16:30:55 wrote gpt_004.pth
20240813-16:30:56 wrote gpt_000.pth
20240813-16:31:09 wrote non_validated_0198_04.png
20240813-16:31:22 wrote non_validated_0198_00.png
20240813-16:31:22 wrote state.pth
20240813-16:31:22 --- epoch 199 ----------------------------------------
20240813-16:31:22 current_test_accuracies 0.9493 0.9478 0.9509 0.9558 0.9568
20240813-16:31:22 training model 1
20240813-16:31:22 training model 0
20240813-16:35:07 train_perplexity 199 model 1 1.1635150164709318
20240813-16:35:09 test_perplexity 199 model 1 1.160641802417081
20240813-16:35:11 train_perplexity 199 model 0 1.163117473568797
20240813-16:35:13 test_perplexity 199 model 0 1.1606880948979246
20240813-16:35:55 test_accuracy 199 model 1 val 764 / 805
20240813-16:36:00 test_accuracy 199 model 0 val 753 / 799
20240813-16:36:02 wrote gpt_001.pth
20240813-16:36:02 wrote gpt_000.pth
20240813-16:36:16 wrote non_validated_0199_01.png
20240813-16:36:29 wrote non_validated_0199_00.png
20240813-16:36:29 wrote state.pth
20240813-16:36:29 --- epoch 200 ----------------------------------------
20240813-16:36:29 current_test_accuracies 0.9424 0.9491 0.9509 0.9558 0.9568
20240813-16:36:29 training model 0
20240813-16:36:29 training model 1
20240813-16:40:13 train_perplexity 200 model 0 1.163079480238532
20240813-16:40:15 test_perplexity 200 model 0 1.1594992360064964
20240813-16:40:16 train_perplexity 200 model 1 1.1633464204890018
20240813-16:40:18 test_perplexity 200 model 1 1.1613083277189338
20240813-16:40:56 test_accuracy 200 model 0 val 766 / 802
20240813-16:40:57 test_accuracy 200 model 1 val 754 / 800
20240813-16:40:59 wrote gpt_000.pth
20240813-16:41:00 wrote gpt_001.pth
20240813-16:41:13 wrote non_validated_0200_00.png
20240813-16:41:26 wrote non_validated_0200_01.png
20240813-16:41:26 wrote state.pth
20240813-16:41:26 --- epoch 201 ----------------------------------------
20240813-16:41:26 current_test_accuracies 0.9551 0.9425 0.9509 0.9558 0.9568
20240813-16:41:26 training model 1
20240813-16:41:26 training model 2
20240813-16:45:11 train_perplexity 201 model 1 1.1636308514041602
20240813-16:45:12 train_perplexity 201 model 2 1.1626705513959368
20240813-16:45:13 test_perplexity 201 model 1 1.1627873575616663
20240813-16:45:15 test_perplexity 201 model 2 1.1603046784583169
20240813-16:46:00 test_accuracy 201 model 1 val 766 / 814
20240813-16:46:01 test_accuracy 201 model 2 val 762 / 796
20240813-16:46:03 wrote gpt_001.pth
20240813-16:46:04 wrote gpt_002.pth
20240813-16:46:17 wrote non_validated_0201_01.png
20240813-16:46:30 wrote non_validated_0201_02.png
20240813-16:46:30 wrote state.pth
20240813-16:46:30 --- epoch 202 ----------------------------------------
20240813-16:46:30 current_test_accuracies 0.9551 0.9410 0.9573 0.9558 0.9568
20240813-16:46:30 training model 1
20240813-16:46:30 training model 0
20240813-16:50:14 train_perplexity 202 model 1 1.1629613759281698
20240813-16:50:16 test_perplexity 202 model 1 1.163633633917938
20240813-16:50:17 train_perplexity 202 model 0 1.1626524550639332
20240813-16:50:19 test_perplexity 202 model 0 1.1619309038705437
20240813-16:51:01 test_accuracy 202 model 1 val 769 / 808
20240813-16:51:03 test_accuracy 202 model 0 val 752 / 804
20240813-16:51:05 wrote gpt_001.pth
20240813-16:51:06 wrote gpt_000.pth
20240813-16:51:19 wrote non_validated_0202_01.png
20240813-16:51:32 wrote non_validated_0202_00.png
20240813-16:51:32 wrote state.pth
20240813-16:51:32 --- epoch 203 ----------------------------------------
20240813-16:51:32 current_test_accuracies 0.9353 0.9517 0.9573 0.9558 0.9568
20240813-16:51:32 training model 0
20240813-16:51:32 training model 1
20240813-16:55:16 train_perplexity 203 model 0 1.1628967330375413
20240813-16:55:18 test_perplexity 203 model 0 1.1602431721798816
20240813-16:55:18 train_perplexity 203 model 1 1.1631950935203546
20240813-16:55:21 test_perplexity 203 model 1 1.161240552252403
20240813-16:56:02 test_accuracy 203 model 0 val 760 / 804
20240813-16:56:06 test_accuracy 203 model 1 val 758 / 796
20240813-16:56:08 wrote gpt_000.pth
20240813-16:56:09 wrote gpt_001.pth
20240813-16:56:22 wrote non_validated_0203_00.png
20240813-16:56:35 wrote non_validated_0203_01.png
20240813-16:56:35 wrote state.pth
20240813-16:56:35 --- epoch 204 ----------------------------------------
20240813-16:56:35 current_test_accuracies 0.9453 0.9523 0.9573 0.9558 0.9568
20240813-16:56:35 training model 0
20240813-16:56:35 training model 1
20240813-17:00:20 train_perplexity 204 model 0 1.1624741873353284
20240813-17:00:21 train_perplexity 204 model 1 1.1633255947090482
20240813-17:00:22 test_perplexity 204 model 0 1.1609824763174945
20240813-17:00:24 test_perplexity 204 model 1 1.161863884577503
20240813-17:01:07 test_accuracy 204 model 0 val 772 / 814
20240813-17:01:10 test_accuracy 204 model 1 val 774 / 798
20240813-17:01:12 wrote gpt_000.pth
20240813-17:01:13 wrote gpt_001.pth
20240813-17:01:26 wrote non_validated_0204_00.png
20240813-17:01:39 wrote non_validated_0204_01.png
20240813-17:01:39 wrote state.pth
20240813-17:01:39 --- epoch 205 ----------------------------------------
20240813-17:01:39 current_test_accuracies 0.9484 0.9699 0.9573 0.9558 0.9568
20240813-17:01:39 training model 0
20240813-17:01:39 training model 3
20240813-17:05:23 train_perplexity 205 model 0 1.162542205869483
20240813-17:05:25 test_perplexity 205 model 0 1.162345302469914
20240813-17:05:25 train_perplexity 205 model 3 1.1629353668216753
20240813-17:05:28 test_perplexity 205 model 3 1.163529392692332
20240813-17:06:12 test_accuracy 205 model 3 val 757 / 806
20240813-17:06:13 test_accuracy 205 model 0 val 755 / 791
20240813-17:06:15 wrote gpt_000.pth
20240813-17:06:16 wrote gpt_003.pth
20240813-17:06:29 wrote non_validated_0205_00.png
20240813-17:06:42 wrote non_validated_0205_03.png
20240813-17:06:42 wrote state.pth
20240813-17:06:42 --- epoch 206 ----------------------------------------
20240813-17:06:42 current_test_accuracies 0.9545 0.9699 0.9573 0.9392 0.9568
20240813-17:06:42 training model 3
20240813-17:06:42 training model 0
20240813-17:10:26 train_perplexity 206 model 3 1.1630351468641043
20240813-17:10:28 test_perplexity 206 model 3 1.1640578343357741
20240813-17:10:28 train_perplexity 206 model 0 1.1628020047818795
20240813-17:10:30 test_perplexity 206 model 0 1.1629309841900184
20240813-17:11:15 test_accuracy 206 model 3 val 767 / 807
20240813-17:11:17 test_accuracy 206 model 0 val 746 / 795
20240813-17:11:19 wrote gpt_003.pth
20240813-17:11:20 wrote gpt_000.pth
20240813-17:11:33 wrote non_validated_0206_03.png
20240813-17:11:46 wrote non_validated_0206_00.png
20240813-17:11:46 wrote state.pth
20240813-17:11:46 --- epoch 207 ----------------------------------------
20240813-17:11:46 current_test_accuracies 0.9384 0.9699 0.9573 0.9504 0.9568
20240813-17:11:46 training model 0
20240813-17:11:46 training model 3
20240813-17:15:31 train_perplexity 207 model 0 1.1627846300483442
20240813-17:15:33 train_perplexity 207 model 3 1.163357207987167
20240813-17:15:33 test_perplexity 207 model 0 1.1598865101649343
20240813-17:15:35 test_perplexity 207 model 3 1.1643961632813167
20240813-17:16:23 test_accuracy 207 model 0 val 735 / 781
20240813-17:16:24 test_accuracy 207 model 3 val 743 / 793
20240813-17:16:26 wrote gpt_000.pth
20240813-17:16:26 wrote gpt_003.pth
20240813-17:16:39 wrote non_validated_0207_00.png
20240813-17:16:52 wrote non_validated_0207_03.png
20240813-17:16:52 wrote state.pth
20240813-17:16:52 --- epoch 208 ----------------------------------------
20240813-17:16:52 current_test_accuracies 0.9411 0.9699 0.9573 0.9369 0.9568
20240813-17:16:52 training model 3
20240813-17:16:52 training model 0
20240813-17:20:37 train_perplexity 208 model 3 1.162387553163124
20240813-17:20:38 test_perplexity 208 model 3 1.1615877025763761
20240813-17:20:39 train_perplexity 208 model 0 1.1629591989799055
20240813-17:20:41 test_perplexity 208 model 0 1.1614766109020223
20240813-17:21:23 test_accuracy 208 model 3 val 784 / 819
20240813-17:21:26 test_accuracy 208 model 0 val 761 / 809
20240813-17:21:28 wrote gpt_003.pth
20240813-17:21:28 wrote gpt_000.pth
20240813-17:21:41 wrote non_validated_0208_03.png
20240813-17:21:54 wrote non_validated_0208_00.png
20240813-17:21:54 wrote state.pth
20240813-17:21:54 --- epoch 209 ----------------------------------------
20240813-17:21:54 current_test_accuracies 0.9407 0.9699 0.9573 0.9573 0.9568
20240813-17:21:54 training model 0
20240813-17:21:54 training model 4
20240813-17:25:38 train_perplexity 209 model 0 1.1628900311304158
20240813-17:25:40 test_perplexity 209 model 0 1.1591199249496453
20240813-17:25:41 train_perplexity 209 model 4 1.1625053727915806
20240813-17:25:43 test_perplexity 209 model 4 1.1617161775529703
20240813-17:26:31 test_accuracy 209 model 0 val 751 / 786
20240813-17:26:31 test_accuracy 209 model 4 val 749 / 795
20240813-17:26:33 wrote gpt_000.pth
20240813-17:26:34 wrote gpt_004.pth
20240813-17:26:47 wrote non_validated_0209_00.png
20240813-17:27:00 wrote non_validated_0209_04.png
20240813-17:27:00 wrote state.pth
20240813-17:27:00 --- epoch 210 ----------------------------------------
20240813-17:27:00 current_test_accuracies 0.9555 0.9699 0.9573 0.9573 0.9421
20240813-17:27:00 training model 4
20240813-17:27:00 training model 0
20240813-17:30:44 train_perplexity 210 model 4 1.162060003533126
20240813-17:30:46 test_perplexity 210 model 4 1.1595982014758888
20240813-17:30:47 train_perplexity 210 model 0 1.1623025712900221
20240813-17:30:49 test_perplexity 210 model 0 1.162286479041478
20240813-17:31:35 test_accuracy 210 model 4 val 750 / 793
20240813-17:31:36 test_accuracy 210 model 0 val 761 / 794
20240813-17:31:38 wrote gpt_004.pth
20240813-17:31:39 wrote gpt_000.pth
20240813-17:31:52 wrote non_validated_0210_04.png
20240813-17:32:05 wrote non_validated_0210_00.png
20240813-17:32:05 wrote state.pth
20240813-17:32:05 --- epoch 211 ----------------------------------------
20240813-17:32:05 current_test_accuracies 0.9584 0.9699 0.9573 0.9573 0.9458
20240813-17:32:05 training model 4
20240813-17:32:05 training model 3
20240813-17:35:50 train_perplexity 211 model 4 1.162008367697739
20240813-17:35:51 train_perplexity 211 model 3 1.1634143335834568
20240813-17:35:53 test_perplexity 211 model 4 1.1628532955805255
20240813-17:35:54 test_perplexity 211 model 3 1.162365261249877
20240813-17:36:38 test_accuracy 211 model 3 val 763 / 801
20240813-17:36:41 test_accuracy 211 model 4 val 748 / 796
20240813-17:36:43 wrote gpt_004.pth
20240813-17:36:44 wrote gpt_003.pth
20240813-17:36:57 wrote non_validated_0211_04.png
20240813-17:37:10 wrote non_validated_0211_03.png
20240813-17:37:10 wrote state.pth
20240813-17:37:10 --- epoch 212 ----------------------------------------
20240813-17:37:10 current_test_accuracies 0.9584 0.9699 0.9573 0.9526 0.9397
20240813-17:37:10 training model 4
20240813-17:37:10 training model 3
20240813-17:40:54 train_perplexity 212 model 4 1.16222219151263
20240813-17:40:56 test_perplexity 212 model 4 1.1597615098354188
20240813-17:40:56 train_perplexity 212 model 3 1.1623363681441525
20240813-17:40:59 test_perplexity 212 model 3 1.1615931847841106
20240813-17:41:43 test_accuracy 212 model 3 val 771 / 814
20240813-17:41:45 test_accuracy 212 model 4 val 752 / 792
20240813-17:41:47 wrote gpt_004.pth
20240813-17:41:48 wrote gpt_003.pth
20240813-17:42:01 wrote non_validated_0212_04.png
20240813-17:42:14 wrote non_validated_0212_03.png
20240813-17:42:14 wrote state.pth
20240813-17:42:14 --- epoch 213 ----------------------------------------
20240813-17:42:14 current_test_accuracies 0.9584 0.9699 0.9573 0.9472 0.9495
20240813-17:42:14 training model 3
20240813-17:42:14 training model 4
20240813-17:45:58 train_perplexity 213 model 3 1.1633670489843295
20240813-17:46:00 test_perplexity 213 model 3 1.1621274188640274
20240813-17:46:01 train_perplexity 213 model 4 1.1618282436839742
20240813-17:46:03 test_perplexity 213 model 4 1.1650225878421259
20240813-17:46:48 test_accuracy 213 model 3 val 744 / 789
20240813-17:46:48 test_accuracy 213 model 4 val 776 / 818
20240813-17:46:51 wrote gpt_003.pth
20240813-17:46:51 wrote gpt_004.pth
20240813-17:47:04 wrote non_validated_0213_03.png
20240813-17:47:17 wrote non_validated_0213_04.png
20240813-17:47:18 wrote state.pth
20240813-17:47:18 --- epoch 214 ----------------------------------------
20240813-17:47:18 current_test_accuracies 0.9584 0.9699 0.9573 0.9430 0.9487
20240813-17:47:18 training model 3
20240813-17:47:18 training model 4
20240813-17:51:02 train_perplexity 214 model 3 1.162521608814101
20240813-17:51:04 test_perplexity 214 model 3 1.1617099772307373
20240813-17:51:05 train_perplexity 214 model 4 1.1624927983911728
20240813-17:51:07 test_perplexity 214 model 4 1.1621802634703609
20240813-17:51:51 test_accuracy 214 model 4 val 794 / 822
20240813-17:51:52 test_accuracy 214 model 3 val 743 / 780
20240813-17:51:54 wrote gpt_003.pth
20240813-17:51:55 wrote gpt_004.pth
20240813-17:52:08 wrote non_validated_0214_03.png
20240813-17:52:21 wrote non_validated_0214_04.png
20240813-17:52:21 wrote state.pth
20240813-17:52:21 --- epoch 215 ----------------------------------------
20240813-17:52:21 current_test_accuracies 0.9584 0.9699 0.9573 0.9526 0.9659
20240813-17:53:34 keep c_quizzes model 0 validated 13 / 410 (3.17%) nb_accumulated 13 / 410 (finishes Tue 18:30 -- 642/h)
20240813-17:54:22 keep c_quizzes model 0 validated 17 / 410 (4.15%) nb_accumulated 30 / 410 (finishes Tue 18:19 -- 891/h)
20240813-17:55:10 keep c_quizzes model 4 validated 30 / 410 (7.32%) nb_accumulated 60 / 410 (finishes Tue 18:11 -- 1273/h)
20240813-17:55:59 keep c_quizzes model 3 validated 12 / 410 (2.93%) nb_accumulated 72 / 410 (finishes Tue 18:13 -- 1187/h)
20240813-17:56:48 keep c_quizzes model 0 validated 25 / 410 (6.10%) nb_accumulated 97 / 410 (finishes Tue 18:11 -- 1309/h)
20240813-17:57:36 keep c_quizzes model 1 validated 16 / 410 (3.90%) nb_accumulated 113 / 410 (finishes Tue 18:11 -- 1290/h)
20240813-17:58:24 keep c_quizzes model 0 validated 15 / 410 (3.66%) nb_accumulated 128 / 410 (finishes Tue 18:11 -- 1267/h)
20240813-17:59:13 keep c_quizzes model 3 validated 17 / 410 (4.15%) nb_accumulated 145 / 410 (finishes Tue 18:11 -- 1267/h)
20240813-18:00:01 keep c_quizzes model 1 validated 16 / 410 (3.90%) nb_accumulated 161 / 410 (finishes Tue 18:11 -- 1258/h)
20240813-18:00:50 keep c_quizzes model 3 validated 23 / 410 (5.61%) nb_accumulated 184 / 410 (finishes Tue 18:11 -- 1301/h)
20240813-18:01:38 keep c_quizzes model 0 validated 20 / 410 (4.88%) nb_accumulated 204 / 410 (finishes Tue 18:11 -- 1317/h)
20240813-18:02:27 keep c_quizzes model 4 validated 19 / 410 (4.63%) nb_accumulated 223 / 410 (finishes Tue 18:10 -- 1324/h)
20240813-18:03:16 keep c_quizzes model 4 validated 20 / 410 (4.88%) nb_accumulated 243 / 410 (finishes Tue 18:10 -- 1336/h)
20240813-18:04:04 keep c_quizzes model 4 validated 23 / 410 (5.61%) nb_accumulated 266 / 410 (finishes Tue 18:10 -- 1361/h)
20240813-18:04:53 keep c_quizzes model 2 validated 28 / 410 (6.83%) nb_accumulated 294 / 410 (finishes Tue 18:09 -- 1407/h)
20240813-18:05:42 keep c_quizzes model 0 validated 18 / 410 (4.39%) nb_accumulated 312 / 410 (finishes Tue 18:09 -- 1402/h)
20240813-18:06:30 keep c_quizzes model 2 validated 12 / 410 (2.93%) nb_accumulated 324 / 410 (finishes Tue 18:10 -- 1373/h)
20240813-18:07:18 keep c_quizzes model 2 validated 17 / 410 (4.15%) nb_accumulated 341 / 410 (finishes Tue 18:10 -- 1367/h)
20240813-18:08:07 keep c_quizzes model 0 validated 18 / 410 (4.39%) nb_accumulated 359 / 410 (finishes Tue 18:10 -- 1365/h)
20240813-18:08:56 keep c_quizzes model 4 validated 19 / 410 (4.63%) nb_accumulated 378 / 410 (finishes Tue 18:10 -- 1367/h)
20240813-18:09:44 keep c_quizzes model 4 validated 21 / 410 (5.12%) nb_accumulated 399 / 410 (finishes Tue 18:10 -- 1376/h)
20240813-18:10:33 keep c_quizzes model 1 validated 16 / 410 (3.90%) nb_accumulated 415 / 410 (finishes now! -- 1368/h)
20240813-18:10:37 wrote c_quizzes.pth
20240813-18:10:37 training model 0
20240813-18:10:37 training model 1
20240813-18:14:19 train_perplexity 215 model 0 1.1634297656831714
20240813-18:14:21 test_perplexity 215 model 0 1.1621251152660008
20240813-18:14:22 train_perplexity 215 model 1 1.1643071931556732
20240813-18:14:24 test_perplexity 215 model 1 1.1634789000746566
20240813-18:15:06 test_accuracy 215 model 0 val 757 / 809
20240813-18:15:08 test_accuracy 215 model 1 val 763 / 811
20240813-18:15:10 wrote gpt_000.pth
20240813-18:15:10 wrote gpt_001.pth
20240813-18:15:23 wrote non_validated_0215_00.png
20240813-18:15:36 wrote non_validated_0215_01.png
20240813-18:15:36 wrote state.pth
20240813-18:15:36 --- epoch 216 ----------------------------------------
20240813-18:15:36 current_test_accuracies 0.9357 0.9408 0.0000 0.0000 0.0000
20240813-18:15:36 training model 2
20240813-18:15:36 training model 3
20240813-18:19:21 train_perplexity 216 model 2 1.1640373997267301
20240813-18:19:23 test_perplexity 216 model 2 1.1638537353710954
20240813-18:19:23 train_perplexity 216 model 3 1.1638862672784562
20240813-18:19:25 test_perplexity 216 model 3 1.1637096861161043
20240813-18:20:12 test_accuracy 216 model 3 val 737 / 785
20240813-18:20:12 test_accuracy 216 model 2 val 741 / 794
20240813-18:20:15 wrote gpt_002.pth
20240813-18:20:15 wrote gpt_003.pth
20240813-18:20:28 wrote non_validated_0216_02.png
20240813-18:20:41 wrote non_validated_0216_03.png
20240813-18:20:41 wrote state.pth
20240813-18:20:41 --- epoch 217 ----------------------------------------
20240813-18:20:41 current_test_accuracies 0.9357 0.9408 0.9332 0.9389 0.0000
20240813-18:20:41 training model 4
20240813-18:20:41 training model 2
20240813-18:24:26 train_perplexity 217 model 4 1.162933734211594
20240813-18:24:28 test_perplexity 217 model 4 1.1631284330977099
20240813-18:24:28 train_perplexity 217 model 2 1.1635799195507723
20240813-18:24:30 test_perplexity 217 model 2 1.1672103354313266
20240813-18:25:15 test_accuracy 217 model 2 val 774 / 820
20240813-18:25:17 test_accuracy 217 model 4 val 750 / 795
20240813-18:25:19 wrote gpt_004.pth
20240813-18:25:20 wrote gpt_002.pth
20240813-18:25:32 wrote non_validated_0217_04.png
20240813-18:25:46 wrote non_validated_0217_02.png
20240813-18:25:46 wrote state.pth
20240813-18:25:46 --- epoch 218 ----------------------------------------
20240813-18:25:46 current_test_accuracies 0.9357 0.9408 0.9439 0.9389 0.9434
20240813-18:25:46 training model 0
20240813-18:25:46 training model 3
20240813-18:29:30 train_perplexity 218 model 0 1.1640412844984378
20240813-18:29:32 test_perplexity 218 model 0 1.1628832029926781
20240813-18:29:32 train_perplexity 218 model 3 1.1638313211975089
20240813-18:29:35 test_perplexity 218 model 3 1.161094600568607
20240813-18:30:18 test_accuracy 218 model 0 val 779 / 824
20240813-18:30:22 test_accuracy 218 model 3 val 764 / 799
20240813-18:30:24 wrote gpt_000.pth
20240813-18:30:25 wrote gpt_003.pth
20240813-18:30:38 wrote non_validated_0218_00.png
20240813-18:30:51 wrote non_validated_0218_03.png
20240813-18:30:51 wrote state.pth
20240813-18:30:51 --- epoch 219 ----------------------------------------
20240813-18:30:51 current_test_accuracies 0.9454 0.9408 0.9439 0.9562 0.9434
20240813-18:30:51 training model 1
20240813-18:30:51 training model 4
20240813-18:34:35 train_perplexity 219 model 1 1.1638535253013673
20240813-18:34:37 test_perplexity 219 model 1 1.162929651155761
20240813-18:34:37 train_perplexity 219 model 4 1.163155558707196
20240813-18:34:40 test_perplexity 219 model 4 1.1642039000183158
20240813-18:35:22 test_accuracy 219 model 1 val 761 / 804
20240813-18:35:26 test_accuracy 219 model 4 val 747 / 796
20240813-18:35:28 wrote gpt_001.pth
20240813-18:35:28 wrote gpt_004.pth
20240813-18:35:41 wrote non_validated_0219_01.png
20240813-18:35:54 wrote non_validated_0219_04.png
20240813-18:35:54 wrote state.pth
20240813-18:35:54 --- epoch 220 ----------------------------------------
20240813-18:35:54 current_test_accuracies 0.9454 0.9465 0.9439 0.9562 0.9384
20240813-18:35:54 training model 4
20240813-18:35:54 training model 2
20240813-18:39:38 train_perplexity 220 model 4 1.1630551577512558
20240813-18:39:40 test_perplexity 220 model 4 1.161520858851001
20240813-18:39:41 train_perplexity 220 model 2 1.1634277758066283
20240813-18:39:44 test_perplexity 220 model 2 1.1591509791130579
20240813-18:40:26 test_accuracy 220 model 4 val 759 / 806
20240813-18:40:30 test_accuracy 220 model 2 val 756 / 793
20240813-18:40:32 wrote gpt_004.pth
20240813-18:40:32 wrote gpt_002.pth
20240813-18:40:45 wrote non_validated_0220_04.png
20240813-18:40:59 wrote non_validated_0220_02.png
20240813-18:40:59 wrote state.pth
20240813-18:40:59 --- epoch 221 ----------------------------------------
20240813-18:40:59 current_test_accuracies 0.9454 0.9465 0.9533 0.9562 0.9417
20240813-18:40:59 training model 4
20240813-18:40:59 training model 0
20240813-18:44:43 train_perplexity 221 model 4 1.162861818197319
20240813-18:44:45 test_perplexity 221 model 4 1.1625919449495385
20240813-18:44:46 train_perplexity 221 model 0 1.1640281280633469
20240813-18:44:48 test_perplexity 221 model 0 1.1623194898883114
20240813-18:45:30 test_accuracy 221 model 4 val 762 / 811
20240813-18:45:31 test_accuracy 221 model 0 val 750 / 800
20240813-18:45:33 wrote gpt_004.pth
20240813-18:45:33 wrote gpt_000.pth
20240813-18:45:46 wrote non_validated_0221_04.png
20240813-18:45:59 wrote non_validated_0221_00.png
20240813-18:46:00 wrote state.pth
20240813-18:46:00 --- epoch 222 ----------------------------------------
20240813-18:46:00 current_test_accuracies 0.9375 0.9465 0.9533 0.9562 0.9396
20240813-18:46:00 training model 0
20240813-18:46:00 training model 4
20240813-18:49:44 train_perplexity 222 model 0 1.1633843248249809
20240813-18:49:46 test_perplexity 222 model 0 1.1650448373072908
20240813-18:49:47 train_perplexity 222 model 4 1.163063469120342
20240813-18:49:49 test_perplexity 222 model 4 1.1608516644294415
20240813-18:50:31 test_accuracy 222 model 0 val 754 / 802
20240813-18:50:33 test_accuracy 222 model 4 val 739 / 781
20240813-18:50:35 wrote gpt_000.pth
20240813-18:50:36 wrote gpt_004.pth
20240813-18:50:49 wrote non_validated_0222_00.png
20240813-18:51:02 wrote non_validated_0222_04.png
20240813-18:51:02 wrote state.pth
20240813-18:51:02 --- epoch 223 ----------------------------------------
20240813-18:51:02 current_test_accuracies 0.9401 0.9465 0.9533 0.9562 0.9462
20240813-18:51:02 training model 0
20240813-18:51:02 training model 4
20240813-18:54:46 train_perplexity 223 model 0 1.1638706162812829
20240813-18:54:48 test_perplexity 223 model 0 1.1604347709706326
20240813-18:54:49 train_perplexity 223 model 4 1.1633854839714763
20240813-18:54:51 test_perplexity 223 model 4 1.1619581323742048
20240813-18:55:37 test_accuracy 223 model 4 val 777 / 815
20240813-18:55:38 test_accuracy 223 model 0 val 748 / 791
20240813-18:55:40 wrote gpt_000.pth
20240813-18:55:40 wrote gpt_004.pth
20240813-18:55:53 wrote non_validated_0223_00.png
20240813-18:56:06 wrote non_validated_0223_04.png
20240813-18:56:06 wrote state.pth
20240813-18:56:06 --- epoch 224 ----------------------------------------
20240813-18:56:06 current_test_accuracies 0.9456 0.9465 0.9533 0.9562 0.9534
20240813-18:56:06 training model 0
20240813-18:56:06 training model 1
20240813-18:59:51 train_perplexity 224 model 0 1.1632352483713038
20240813-18:59:53 test_perplexity 224 model 0 1.1618772460554856
20240813-18:59:53 train_perplexity 224 model 1 1.163869980155608
20240813-18:59:55 test_perplexity 224 model 1 1.162056887369185
20240813-19:00:39 test_accuracy 224 model 1 val 759 / 801
20240813-19:00:41 test_accuracy 224 model 0 val 743 / 788
20240813-19:00:43 wrote gpt_000.pth
20240813-19:00:44 wrote gpt_001.pth
20240813-19:00:57 wrote non_validated_0224_00.png
20240813-19:01:10 wrote non_validated_0224_01.png
20240813-19:01:10 wrote state.pth
20240813-19:01:10 --- epoch 225 ----------------------------------------
20240813-19:01:10 current_test_accuracies 0.9429 0.9476 0.9533 0.9562 0.9534
20240813-19:01:10 training model 0
20240813-19:01:10 training model 1
20240813-19:04:54 train_perplexity 225 model 0 1.1634136897162561
20240813-19:04:56 test_perplexity 225 model 0 1.1616646337010101
20240813-19:04:57 train_perplexity 225 model 1 1.1641935494782694
20240813-19:04:59 test_perplexity 225 model 1 1.1602970294374992
20240813-19:05:45 test_accuracy 225 model 0 val 756 / 796
20240813-19:05:46 test_accuracy 225 model 1 val 763 / 798
20240813-19:05:48 wrote gpt_000.pth
20240813-19:05:49 wrote gpt_001.pth
20240813-19:06:02 wrote non_validated_0225_00.png
20240813-19:06:15 wrote non_validated_0225_01.png
20240813-19:06:15 wrote state.pth
20240813-19:06:15 --- epoch 226 ----------------------------------------
20240813-19:06:15 current_test_accuracies 0.9497 0.9561 0.9533 0.9562 0.9534
20240813-19:06:15 training model 0
20240813-19:06:15 training model 2
20240813-19:09:59 train_perplexity 226 model 0 1.1637394336730251
20240813-19:10:01 test_perplexity 226 model 0 1.1628152723697367
20240813-19:10:02 train_perplexity 226 model 2 1.1630693395335283
20240813-19:10:04 test_perplexity 226 model 2 1.165571912107389
20240813-19:10:46 test_accuracy 226 model 0 val 757 / 801
20240813-19:10:48 test_accuracy 226 model 2 val 789 / 829
20240813-19:10:50 wrote gpt_000.pth
20240813-19:10:51 wrote gpt_002.pth
20240813-19:11:04 wrote non_validated_0226_00.png
20240813-19:11:17 wrote non_validated_0226_02.png
20240813-19:11:17 wrote state.pth
20240813-19:11:17 --- epoch 227 ----------------------------------------
20240813-19:11:17 current_test_accuracies 0.9451 0.9561 0.9517 0.9562 0.9534
20240813-19:11:17 training model 0
20240813-19:11:17 training model 2
20240813-19:15:01 train_perplexity 227 model 0 1.1633334984707988
20240813-19:15:03 test_perplexity 227 model 0 1.1624455575251096
20240813-19:15:04 train_perplexity 227 model 2 1.1639835171612167
20240813-19:15:06 test_perplexity 227 model 2 1.1617465482280416
20240813-19:15:51 test_accuracy 227 model 0 val 753 / 799
20240813-19:15:52 test_accuracy 227 model 2 val 750 / 793
20240813-19:15:54 wrote gpt_000.pth
20240813-19:15:55 wrote gpt_002.pth
20240813-19:16:08 wrote non_validated_0227_00.png
20240813-19:16:21 wrote non_validated_0227_02.png
20240813-19:16:21 wrote state.pth
20240813-19:16:21 --- epoch 228 ----------------------------------------
20240813-19:16:21 current_test_accuracies 0.9424 0.9561 0.9458 0.9562 0.9534
20240813-19:16:21 training model 0
20240813-19:16:21 training model 2
20240813-19:20:05 train_perplexity 228 model 0 1.1631623228028205
20240813-19:20:07 test_perplexity 228 model 0 1.161481553026387
20240813-19:20:08 train_perplexity 228 model 2 1.163445576669594
20240813-19:20:10 test_perplexity 228 model 2 1.1622261726600238
20240813-19:20:53 test_accuracy 228 model 0 val 760 / 792
20240813-19:20:57 test_accuracy 228 model 2 val 741 / 795
20240813-19:20:59 wrote gpt_000.pth
20240813-19:21:00 wrote gpt_002.pth
20240813-19:21:13 wrote non_validated_0228_00.png
20240813-19:21:26 wrote non_validated_0228_02.png
20240813-19:21:26 wrote state.pth
20240813-19:21:26 --- epoch 229 ----------------------------------------
20240813-19:21:26 current_test_accuracies 0.9596 0.9561 0.9321 0.9562 0.9534
20240813-19:21:26 training model 2
20240813-19:21:26 training model 4
20240813-19:25:10 train_perplexity 229 model 2 1.1629792938822152
20240813-19:25:12 test_perplexity 229 model 2 1.1630823457180182
20240813-19:25:13 train_perplexity 229 model 4 1.1634871692594158
20240813-19:25:15 test_perplexity 229 model 4 1.162908730039606
20240813-19:25:56 test_accuracy 229 model 2 val 761 / 806
20240813-19:26:00 test_accuracy 229 model 4 val 739 / 787
20240813-19:26:02 wrote gpt_002.pth
20240813-19:26:03 wrote gpt_004.pth
20240813-19:26:16 wrote non_validated_0229_02.png
20240813-19:26:29 wrote non_validated_0229_04.png
20240813-19:26:29 wrote state.pth
20240813-19:26:29 --- epoch 230 ----------------------------------------
20240813-19:26:29 current_test_accuracies 0.9596 0.9561 0.9442 0.9562 0.9390
20240813-19:26:29 training model 4
20240813-19:26:29 training model 2
20240813-19:30:14 train_perplexity 230 model 4 1.1632455658858138
20240813-19:30:15 test_perplexity 230 model 4 1.1596239352638817
20240813-19:30:16 train_perplexity 230 model 2 1.164095275431693
20240813-19:30:18 test_perplexity 230 model 2 1.1614324442494428
20240813-19:31:02 test_accuracy 230 model 4 val 764 / 814
20240813-19:31:03 test_accuracy 230 model 2 val 786 / 832
20240813-19:31:05 wrote gpt_004.pth
20240813-19:31:06 wrote gpt_002.pth
20240813-19:31:19 wrote non_validated_0230_04.png
20240813-19:31:32 wrote non_validated_0230_02.png
20240813-19:31:32 wrote state.pth
20240813-19:31:32 --- epoch 231 ----------------------------------------
20240813-19:31:32 current_test_accuracies 0.9596 0.9561 0.9447 0.9562 0.9386
20240813-19:31:32 training model 4
20240813-19:31:32 training model 2
20240813-19:35:17 train_perplexity 231 model 4 1.163140665228311
20240813-19:35:19 test_perplexity 231 model 4 1.1634307153962056
20240813-19:35:20 train_perplexity 231 model 2 1.1634577920192706
20240813-19:35:22 test_perplexity 231 model 2 1.163853272752741
20240813-19:36:03 test_accuracy 231 model 4 val 765 / 809
20240813-19:36:06 test_accuracy 231 model 2 val 775 / 816
20240813-19:36:08 wrote gpt_004.pth
20240813-19:36:09 wrote gpt_002.pth
20240813-19:36:22 wrote non_validated_0231_04.png
20240813-19:36:35 wrote non_validated_0231_02.png
20240813-19:36:35 wrote state.pth
20240813-19:36:35 --- epoch 232 ----------------------------------------
20240813-19:36:35 current_test_accuracies 0.9596 0.9561 0.9498 0.9562 0.9456
20240813-19:36:35 training model 4
20240813-19:36:35 training model 2
20240813-19:40:20 train_perplexity 232 model 4 1.1632072786100291
20240813-19:40:22 test_perplexity 232 model 4 1.16215331246851
20240813-19:40:22 train_perplexity 232 model 2 1.163461573684821
20240813-19:40:24 test_perplexity 232 model 2 1.162744844668369
20240813-19:41:08 test_accuracy 232 model 2 val 741 / 800
20240813-19:41:10 test_accuracy 232 model 4 val 757 / 792
20240813-19:41:12 wrote gpt_004.pth
20240813-19:41:13 wrote gpt_002.pth
20240813-19:41:26 wrote non_validated_0232_04.png
20240813-19:41:39 wrote non_validated_0232_02.png
20240813-19:41:39 wrote state.pth
20240813-19:41:39 --- epoch 233 ----------------------------------------
20240813-19:41:39 current_test_accuracies 0.9596 0.9561 0.9262 0.9562 0.9558
20240813-19:41:39 training model 2
20240813-19:41:39 training model 4
20240813-19:45:23 train_perplexity 233 model 2 1.1631540335031012
20240813-19:45:25 test_perplexity 233 model 2 1.1622040701096272
20240813-19:45:26 train_perplexity 233 model 4 1.1629871659766196
20240813-19:45:28 test_perplexity 233 model 4 1.161309554849232
20240813-19:46:13 test_accuracy 233 model 2 val 737 / 785
20240813-19:46:15 test_accuracy 233 model 4 val 742 / 784
20240813-19:46:17 wrote gpt_002.pth
20240813-19:46:18 wrote gpt_004.pth
20240813-19:46:31 wrote non_validated_0233_02.png
20240813-19:46:43 wrote non_validated_0233_04.png
20240813-19:46:44 wrote state.pth
20240813-19:46:44 --- epoch 234 ----------------------------------------
20240813-19:46:44 current_test_accuracies 0.9596 0.9561 0.9389 0.9562 0.9464
20240813-19:46:44 training model 2
20240813-19:46:44 training model 4
20240813-19:50:27 train_perplexity 234 model 2 1.1632212760220266
20240813-19:50:29 test_perplexity 234 model 2 1.1632482750719575
20240813-19:50:30 train_perplexity 234 model 4 1.1629392396841967
20240813-19:50:33 test_perplexity 234 model 4 1.1606925433348714
20240813-19:51:17 test_accuracy 234 model 4 val 796 / 831
20240813-19:51:19 test_accuracy 234 model 2 val 751 / 790
20240813-19:51:21 wrote gpt_002.pth
20240813-19:51:22 wrote gpt_004.pth
20240813-19:51:35 wrote non_validated_0234_02.png
20240813-19:51:48 wrote non_validated_0234_04.png
20240813-19:51:48 wrote state.pth
20240813-19:51:48 --- epoch 235 ----------------------------------------
20240813-19:51:48 current_test_accuracies 0.9596 0.9561 0.9506 0.9562 0.9579
20240813-19:52:58 keep c_quizzes model 2 validated 13 / 410 (3.17%) nb_accumulated 13 / 410 (finishes Tue 20:28 -- 664/h)
20240813-19:53:47 keep c_quizzes model 4 validated 17 / 410 (4.15%) nb_accumulated 30 / 410 (finishes Tue 20:18 -- 905/h)
20240813-19:54:36 keep c_quizzes model 3 validated 21 / 410 (5.12%) nb_accumulated 51 / 410 (finishes Tue 20:14 -- 1090/h)
20240813-19:55:25 keep c_quizzes model 2 validated 21 / 410 (5.12%) nb_accumulated 72 / 410 (finishes Tue 20:12 -- 1194/h)
20240813-19:56:13 keep c_quizzes model 1 validated 14 / 410 (3.41%) nb_accumulated 86 / 410 (finishes Tue 20:12 -- 1165/h)
20240813-19:57:02 keep c_quizzes model 2 validated 21 / 410 (5.12%) nb_accumulated 107 / 410 (finishes Tue 20:11 -- 1225/h)
20240813-19:57:51 keep c_quizzes model 1 validated 15 / 410 (3.66%) nb_accumulated 122 / 410 (finishes Tue 20:12 -- 1207/h)
20240813-19:58:40 keep c_quizzes model 2 validated 17 / 410 (4.15%) nb_accumulated 139 / 410 (finishes Tue 20:12 -- 1212/h)
20240813-19:59:29 keep c_quizzes model 0 validated 21 / 410 (5.12%) nb_accumulated 160 / 410 (finishes Tue 20:11 -- 1248/h)
20240813-20:00:18 keep c_quizzes model 3 validated 21 / 410 (5.12%) nb_accumulated 181 / 410 (finishes Tue 20:11 -- 1276/h)
20240813-20:01:07 keep c_quizzes model 0 validated 13 / 410 (3.17%) nb_accumulated 194 / 410 (finishes Tue 20:11 -- 1248/h)
20240813-20:01:56 keep c_quizzes model 0 validated 15 / 410 (3.66%) nb_accumulated 209 / 410 (finishes Tue 20:11 -- 1237/h)
20240813-20:02:44 keep c_quizzes model 1 validated 14 / 410 (3.41%) nb_accumulated 223 / 410 (finishes Tue 20:11 -- 1222/h)
20240813-20:03:33 keep c_quizzes model 3 validated 16 / 410 (3.90%) nb_accumulated 239 / 410 (finishes Tue 20:11 -- 1219/h)
20240813-20:04:22 keep c_quizzes model 3 validated 17 / 410 (4.15%) nb_accumulated 256 / 410 (finishes Tue 20:11 -- 1221/h)
20240813-20:05:11 keep c_quizzes model 0 validated 20 / 410 (4.88%) nb_accumulated 276 / 410 (finishes Tue 20:11 -- 1237/h)
20240813-20:06:00 keep c_quizzes model 4 validated 12 / 410 (2.93%) nb_accumulated 288 / 410 (finishes Tue 20:12 -- 1217/h)
20240813-20:06:49 keep c_quizzes model 1 validated 20 / 410 (4.88%) nb_accumulated 308 / 410 (finishes Tue 20:11 -- 1230/h)
20240813-20:07:38 keep c_quizzes model 0 validated 21 / 410 (5.12%) nb_accumulated 329 / 410 (finishes Tue 20:11 -- 1246/h)
20240813-20:08:26 keep c_quizzes model 0 validated 13 / 410 (3.17%) nb_accumulated 342 / 410 (finishes Tue 20:11 -- 1232/h)
20240813-20:09:15 keep c_quizzes model 0 validated 21 / 410 (5.12%) nb_accumulated 363 / 410 (finishes Tue 20:11 -- 1247/h)
20240813-20:10:04 keep c_quizzes model 1 validated 24 / 410 (5.85%) nb_accumulated 387 / 410 (finishes Tue 20:11 -- 1271/h)
20240813-20:10:52 keep c_quizzes model 2 validated 17 / 410 (4.15%) nb_accumulated 404 / 410 (finishes Tue 20:11 -- 1270/h)
20240813-20:11:41 keep c_quizzes model 3 validated 12 / 410 (2.93%) nb_accumulated 416 / 410 (finishes now! -- 1254/h)
20240813-20:11:45 wrote c_quizzes.pth
20240813-20:11:45 training model 0
20240813-20:11:45 training model 1
20240813-20:15:28 train_perplexity 235 model 0 1.1647293677490096
20240813-20:15:30 train_perplexity 235 model 1 1.1647481503363757
20240813-20:15:31 test_perplexity 235 model 0 1.1633411469451145
20240813-20:15:33 test_perplexity 235 model 1 1.163143185725955
20240813-20:16:19 test_accuracy 235 model 1 val 749 / 799
20240813-20:16:20 test_accuracy 235 model 0 val 724 / 785
20240813-20:16:22 wrote gpt_000.pth
20240813-20:16:22 wrote gpt_001.pth
20240813-20:16:35 wrote non_validated_0235_00.png
20240813-20:16:48 wrote non_validated_0235_01.png
20240813-20:16:48 wrote state.pth
20240813-20:16:48 --- epoch 236 ----------------------------------------
20240813-20:16:48 current_test_accuracies 0.9223 0.9374 0.0000 0.0000 0.0000
20240813-20:16:48 training model 2
20240813-20:16:48 training model 3
20240813-20:20:33 train_perplexity 236 model 2 1.1646598168866313
20240813-20:20:35 test_perplexity 236 model 2 1.1635737717274095
20240813-20:20:35 train_perplexity 236 model 3 1.1652538846037954
20240813-20:20:37 test_perplexity 236 model 3 1.1642976332465171
20240813-20:21:23 test_accuracy 236 model 3 val 772 / 814
20240813-20:21:25 test_accuracy 236 model 2 val 750 / 794
20240813-20:21:27 wrote gpt_002.pth
20240813-20:21:27 wrote gpt_003.pth
20240813-20:21:40 wrote non_validated_0236_02.png
20240813-20:21:53 wrote non_validated_0236_03.png
20240813-20:21:53 wrote state.pth
20240813-20:21:53 --- epoch 237 ----------------------------------------
20240813-20:21:53 current_test_accuracies 0.9223 0.9374 0.9446 0.9484 0.0000
20240813-20:21:53 training model 4
20240813-20:21:53 training model 0
20240813-20:25:38 train_perplexity 237 model 4 1.1641807038887826
20240813-20:25:39 test_perplexity 237 model 4 1.163272557309159
20240813-20:25:40 train_perplexity 237 model 0 1.1647398752485099
20240813-20:25:42 test_perplexity 237 model 0 1.1616254437452909
20240813-20:26:26 test_accuracy 237 model 0 val 760 / 807
20240813-20:26:29 test_accuracy 237 model 4 val 750 / 798
20240813-20:26:30 wrote gpt_004.pth
20240813-20:26:31 wrote gpt_000.pth
20240813-20:26:44 wrote non_validated_0237_04.png
20240813-20:26:57 wrote non_validated_0237_00.png
20240813-20:26:57 wrote state.pth
20240813-20:26:57 --- epoch 238 ----------------------------------------
20240813-20:26:57 current_test_accuracies 0.9418 0.9374 0.9446 0.9484 0.9398
20240813-20:26:57 training model 1
20240813-20:26:57 training model 4
20240813-20:30:42 train_perplexity 238 model 1 1.1651201001028115
20240813-20:30:44 test_perplexity 238 model 1 1.165545536357421
20240813-20:30:45 train_perplexity 238 model 4 1.1640095507340895
20240813-20:30:47 test_perplexity 238 model 4 1.163990093967105
20240813-20:31:31 test_accuracy 238 model 1 val 729 / 762
20240813-20:31:34 test_accuracy 238 model 4 val 747 / 795
20240813-20:31:36 wrote gpt_001.pth
20240813-20:31:37 wrote gpt_004.pth
20240813-20:31:50 wrote non_validated_0238_01.png
20240813-20:32:03 wrote non_validated_0238_04.png
20240813-20:32:03 wrote state.pth
20240813-20:32:03 --- epoch 239 ----------------------------------------
20240813-20:32:03 current_test_accuracies 0.9418 0.9567 0.9446 0.9484 0.9396
20240813-20:32:03 training model 4
20240813-20:32:03 training model 0
20240813-20:35:47 train_perplexity 239 model 4 1.1643435337104358
20240813-20:35:49 test_perplexity 239 model 4 1.1620649363053634
20240813-20:35:50 train_perplexity 239 model 0 1.1645341137149732
20240813-20:35:52 test_perplexity 239 model 0 1.1620910850183843
20240813-20:36:38 test_accuracy 239 model 4 val 751 / 792
20240813-20:36:39 test_accuracy 239 model 0 val 754 / 799
20240813-20:36:41 wrote gpt_004.pth
20240813-20:36:42 wrote gpt_000.pth
20240813-20:36:55 wrote non_validated_0239_04.png
20240813-20:37:08 wrote non_validated_0239_00.png
20240813-20:37:08 wrote state.pth
20240813-20:37:08 --- epoch 240 ----------------------------------------
20240813-20:37:08 current_test_accuracies 0.9437 0.9567 0.9446 0.9484 0.9482
20240813-20:37:08 training model 0
20240813-20:37:08 training model 2
20240813-20:40:53 train_perplexity 240 model 0 1.164159013328237
20240813-20:40:55 test_perplexity 240 model 0 1.1626621702157889
20240813-20:40:55 train_perplexity 240 model 2 1.1649978596377852
20240813-20:40:57 test_perplexity 240 model 2 1.1630362904930105
20240813-20:41:42 test_accuracy 240 model 0 val 760 / 797
20240813-20:41:42 test_accuracy 240 model 2 val 785 / 817
20240813-20:41:45 wrote gpt_000.pth
20240813-20:41:46 wrote gpt_002.pth
20240813-20:41:59 wrote non_validated_0240_00.png
20240813-20:42:12 wrote non_validated_0240_02.png
20240813-20:42:12 wrote state.pth
20240813-20:42:12 --- epoch 241 ----------------------------------------
20240813-20:42:12 current_test_accuracies 0.9536 0.9567 0.9608 0.9484 0.9482
20240813-20:42:12 training model 4
20240813-20:42:12 training model 3
20240813-20:45:56 train_perplexity 241 model 4 1.16425707510429
20240813-20:45:58 test_perplexity 241 model 4 1.1650751179213814
20240813-20:45:59 train_perplexity 241 model 3 1.1646998902542014
20240813-20:46:01 test_perplexity 241 model 3 1.1646366210717152
20240813-20:46:43 test_accuracy 241 model 4 val 762 / 806
20240813-20:46:45 test_accuracy 241 model 3 val 750 / 803
20240813-20:46:47 wrote gpt_004.pth
20240813-20:46:48 wrote gpt_003.pth
20240813-20:47:01 wrote non_validated_0241_04.png
20240813-20:47:14 wrote non_validated_0241_03.png
20240813-20:47:14 wrote state.pth
20240813-20:47:14 --- epoch 242 ----------------------------------------
20240813-20:47:14 current_test_accuracies 0.9536 0.9567 0.9608 0.9340 0.9454
20240813-20:47:14 training model 3
20240813-20:47:14 training model 4
20240813-20:50:57 train_perplexity 242 model 3 1.1648470310523176
20240813-20:50:59 test_perplexity 242 model 3 1.1619631626875941
20240813-20:51:01 train_perplexity 242 model 4 1.1639627973164652
20240813-20:51:03 test_perplexity 242 model 4 1.161567076050268
20240813-20:51:47 test_accuracy 242 model 3 val 751 / 792
20240813-20:51:49 test_accuracy 242 model 4 val 735 / 774
20240813-20:51:51 wrote gpt_003.pth
20240813-20:51:51 wrote gpt_004.pth
20240813-20:52:04 wrote non_validated_0242_03.png
20240813-20:52:17 wrote non_validated_0242_04.png
20240813-20:52:17 wrote state.pth
20240813-20:52:17 --- epoch 243 ----------------------------------------
20240813-20:52:17 current_test_accuracies 0.9536 0.9567 0.9608 0.9482 0.9496
20240813-20:52:17 training model 3
20240813-20:52:17 training model 4
20240813-20:56:02 train_perplexity 243 model 3 1.1647976531439912
20240813-20:56:03 test_perplexity 243 model 3 1.1642521757046125
20240813-20:56:04 train_perplexity 243 model 4 1.1644461335794574
20240813-20:56:07 test_perplexity 243 model 4 1.1626340862702464
20240813-20:56:50 test_accuracy 243 model 3 val 743 / 781
20240813-20:56:54 test_accuracy 243 model 4 val 749 / 799
20240813-20:56:56 wrote gpt_003.pth
20240813-20:56:57 wrote gpt_004.pth
20240813-20:57:09 wrote non_validated_0243_03.png
20240813-20:57:22 wrote non_validated_0243_04.png
20240813-20:57:22 wrote state.pth
20240813-20:57:22 --- epoch 244 ----------------------------------------
20240813-20:57:22 current_test_accuracies 0.9536 0.9567 0.9608 0.9513 0.9374
20240813-20:57:22 training model 4
20240813-20:57:22 training model 3
20240813-21:01:07 train_perplexity 244 model 4 1.1642473770398123
20240813-21:01:09 test_perplexity 244 model 4 1.167907421702446
20240813-21:01:09 train_perplexity 244 model 3 1.1648316064661954
20240813-21:01:12 test_perplexity 244 model 3 1.1648241990372776
20240813-21:01:54 test_accuracy 244 model 4 val 773 / 806
20240813-21:01:56 test_accuracy 244 model 3 val 783 / 830
20240813-21:01:58 wrote gpt_004.pth
20240813-21:01:59 wrote gpt_003.pth
20240813-21:02:12 wrote non_validated_0244_04.png
20240813-21:02:25 wrote non_validated_0244_03.png
20240813-21:02:25 wrote state.pth
20240813-21:02:25 --- epoch 245 ----------------------------------------
20240813-21:02:25 current_test_accuracies 0.9536 0.9567 0.9608 0.9434 0.9591
20240813-21:02:25 training model 3
20240813-21:02:25 training model 0
20240813-21:06:10 train_perplexity 245 model 3 1.1645410222599428
20240813-21:06:11 test_perplexity 245 model 3 1.1633643147155759
20240813-21:06:12 train_perplexity 245 model 0 1.1644288510699359
20240813-21:06:14 test_perplexity 245 model 0 1.1622441680400322
20240813-21:06:58 test_accuracy 245 model 0 val 754 / 809
20240813-21:07:00 test_accuracy 245 model 3 val 747 / 799
20240813-21:07:02 wrote gpt_003.pth
20240813-21:07:03 wrote gpt_000.pth
20240813-21:07:16 wrote non_validated_0245_03.png
20240813-21:07:29 wrote non_validated_0245_00.png
20240813-21:07:29 wrote state.pth
20240813-21:07:29 --- epoch 246 ----------------------------------------
20240813-21:07:29 current_test_accuracies 0.9320 0.9567 0.9608 0.9349 0.9591
20240813-21:07:29 training model 0
20240813-21:07:29 training model 3
20240813-21:11:13 train_perplexity 246 model 0 1.164065466025428
20240813-21:11:15 test_perplexity 246 model 0 1.1639066415670387
20240813-21:11:15 train_perplexity 246 model 3 1.164616689659353
20240813-21:11:18 test_perplexity 246 model 3 1.1635633257010636
20240813-21:12:00 test_accuracy 246 model 0 val 765 / 802
20240813-21:12:04 test_accuracy 246 model 3 val 749 / 791
20240813-21:12:06 wrote gpt_000.pth
20240813-21:12:07 wrote gpt_003.pth
20240813-21:12:20 wrote non_validated_0246_00.png
20240813-21:12:32 wrote non_validated_0246_03.png
20240813-21:12:33 wrote state.pth
20240813-21:12:33 --- epoch 247 ----------------------------------------
20240813-21:12:33 current_test_accuracies 0.9539 0.9567 0.9608 0.9469 0.9591
20240813-21:12:33 training model 3
20240813-21:12:33 training model 0
20240813-21:16:17 train_perplexity 247 model 3 1.1647875719566654
20240813-21:16:18 test_perplexity 247 model 3 1.160829516665607
20240813-21:16:20 train_perplexity 247 model 0 1.1642779149897116
20240813-21:16:22 test_perplexity 247 model 0 1.1621948607655272
20240813-21:17:06 test_accuracy 247 model 0 val 764 / 806
20240813-21:17:07 test_accuracy 247 model 3 val 736 / 773
20240813-21:17:09 wrote gpt_003.pth
20240813-21:17:09 wrote gpt_000.pth
20240813-21:17:22 wrote non_validated_0247_03.png
20240813-21:17:35 wrote non_validated_0247_00.png
20240813-21:17:35 wrote state.pth
20240813-21:17:35 --- epoch 248 ----------------------------------------
20240813-21:17:35 current_test_accuracies 0.9479 0.9567 0.9608 0.9521 0.9591
20240813-21:17:35 training model 0
20240813-21:17:35 training model 3
20240813-21:21:19 train_perplexity 248 model 0 1.1648727914785622
20240813-21:21:21 test_perplexity 248 model 0 1.163908786100268
20240813-21:21:22 train_perplexity 248 model 3 1.1646237744113574
20240813-21:21:24 test_perplexity 248 model 3 1.1618547826726016
20240813-21:22:09 test_accuracy 248 model 3 val 772 / 808
20240813-21:22:10 test_accuracy 248 model 0 val 746 / 799
20240813-21:22:12 wrote gpt_000.pth
20240813-21:22:13 wrote gpt_003.pth
20240813-21:22:26 wrote non_validated_0248_00.png
20240813-21:22:39 wrote non_validated_0248_03.png
20240813-21:22:39 wrote state.pth
20240813-21:22:39 --- epoch 249 ----------------------------------------
20240813-21:22:39 current_test_accuracies 0.9337 0.9567 0.9608 0.9554 0.9591
20240813-21:22:39 training model 0
20240813-21:22:39 training model 3
20240813-21:26:23 train_perplexity 249 model 0 1.1638711706674254
20240813-21:26:25 test_perplexity 249 model 0 1.163396287845959
20240813-21:26:26 train_perplexity 249 model 3 1.164844752715737
20240813-21:26:28 test_perplexity 249 model 3 1.163706505849712
20240813-21:27:11 test_accuracy 249 model 0 val 771 / 810
20240813-21:27:13 test_accuracy 249 model 3 val 774 / 819
20240813-21:27:15 wrote gpt_000.pth
20240813-21:27:16 wrote gpt_003.pth
20240813-21:27:29 wrote non_validated_0249_00.png
20240813-21:27:42 wrote non_validated_0249_03.png
20240813-21:27:42 wrote state.pth
20240813-21:27:42 --- epoch 250 ----------------------------------------
20240813-21:27:42 current_test_accuracies 0.9519 0.9567 0.9608 0.9451 0.9591
20240813-21:27:42 training model 3
20240813-21:27:42 training model 0
20240813-21:31:26 train_perplexity 250 model 3 1.1647840714706414
20240813-21:31:28 test_perplexity 250 model 3 1.1612440476318597
20240813-21:31:28 train_perplexity 250 model 0 1.1642886105377386
20240813-21:31:31 test_perplexity 250 model 0 1.1638398499634308
20240813-21:32:17 test_accuracy 250 model 3 val 754 / 792
20240813-21:32:19 test_accuracy 250 model 0 val 733 / 791
20240813-21:32:21 wrote gpt_003.pth
20240813-21:32:21 wrote gpt_000.pth
20240813-21:32:34 wrote non_validated_0250_03.png
20240813-21:32:47 wrote non_validated_0250_00.png
20240813-21:32:47 wrote state.pth
20240813-21:32:47 --- epoch 251 ----------------------------------------
20240813-21:32:47 current_test_accuracies 0.9267 0.9567 0.9608 0.9520 0.9591
20240813-21:32:47 training model 0
20240813-21:32:47 training model 3
20240813-21:36:32 train_perplexity 251 model 0 1.163863970404813
20240813-21:36:34 test_perplexity 251 model 0 1.1631012105333005
20240813-21:36:34 train_perplexity 251 model 3 1.1644474113031469
20240813-21:36:36 test_perplexity 251 model 3 1.1643490965684489
20240813-21:37:20 test_accuracy 251 model 3 val 762 / 804
20240813-21:37:21 test_accuracy 251 model 0 val 771 / 809
20240813-21:37:23 wrote gpt_000.pth
20240813-21:37:23 wrote gpt_003.pth
20240813-21:37:36 wrote non_validated_0251_00.png
20240813-21:37:49 wrote non_validated_0251_03.png
20240813-21:37:49 wrote state.pth
20240813-21:37:49 --- epoch 252 ----------------------------------------
20240813-21:37:49 current_test_accuracies 0.9530 0.9567 0.9608 0.9478 0.9591
20240813-21:37:49 training model 3
20240813-21:37:49 training model 0
20240813-21:41:34 train_perplexity 252 model 3 1.1646806770027656
20240813-21:41:36 test_perplexity 252 model 3 1.161874199780802
20240813-21:41:36 train_perplexity 252 model 0 1.1636460340781254
20240813-21:41:39 test_perplexity 252 model 0 1.163182342822069
20240813-21:42:23 test_accuracy 252 model 3 val 743 / 780
20240813-21:42:26 test_accuracy 252 model 0 val 736 / 781
20240813-21:42:27 wrote gpt_003.pth
20240813-21:42:28 wrote gpt_000.pth
20240813-21:42:41 wrote non_validated_0252_03.png
20240813-21:42:54 wrote non_validated_0252_00.png
20240813-21:42:54 wrote state.pth
20240813-21:42:54 --- epoch 253 ----------------------------------------
20240813-21:42:54 current_test_accuracies 0.9424 0.9567 0.9608 0.9526 0.9591
20240813-21:42:54 training model 0
20240813-21:42:54 training model 3
20240813-21:46:39 train_perplexity 253 model 0 1.1635998314099494
20240813-21:46:41 train_perplexity 253 model 3 1.164427967317622
20240813-21:46:41 test_perplexity 253 model 0 1.1612925570577264
20240813-21:46:43 test_perplexity 253 model 3 1.1640578885414423
20240813-21:47:29 test_accuracy 253 model 0 val 737 / 777
20240813-21:47:30 test_accuracy 253 model 3 val 746 / 785
20240813-21:47:32 wrote gpt_000.pth
20240813-21:47:33 wrote gpt_003.pth
20240813-21:47:46 wrote non_validated_0253_00.png
20240813-21:47:59 wrote non_validated_0253_03.png
20240813-21:47:59 wrote state.pth
20240813-21:47:59 --- epoch 254 ----------------------------------------
20240813-21:47:59 current_test_accuracies 0.9485 0.9567 0.9608 0.9503 0.9591
20240813-21:47:59 training model 0
20240813-21:47:59 training model 3
20240813-21:51:44 train_perplexity 254 model 0 1.1643432880605702
20240813-21:51:46 test_perplexity 254 model 0 1.1617126963321696
20240813-21:51:46 train_perplexity 254 model 3 1.1644480946426212
20240813-21:51:48 test_perplexity 254 model 3 1.1629465119638933
20240813-21:52:30 test_accuracy 254 model 3 val 764 / 800
20240813-21:52:33 test_accuracy 254 model 0 val 759 / 793
20240813-21:52:35 wrote gpt_000.pth
20240813-21:52:35 wrote gpt_003.pth
20240813-21:52:48 wrote non_validated_0254_00.png
20240813-21:53:01 wrote non_validated_0254_03.png
20240813-21:53:01 wrote state.pth
20240813-21:53:01 --- epoch 255 ----------------------------------------
20240813-21:53:01 current_test_accuracies 0.9571 0.9567 0.9608 0.9550 0.9591
20240813-21:54:11 keep c_quizzes model 2 validated 16 / 410 (3.90%) nb_accumulated 16 / 410 (finishes Tue 22:22 -- 830/h)
20240813-21:54:59 keep c_quizzes model 2 validated 21 / 410 (5.12%) nb_accumulated 37 / 410 (finishes Tue 22:14 -- 1134/h)
20240813-21:55:47 keep c_quizzes model 4 validated 19 / 410 (4.63%) nb_accumulated 56 / 410 (finishes Tue 22:13 -- 1216/h)
20240813-21:56:36 keep c_quizzes model 4 validated 21 / 410 (5.12%) nb_accumulated 77 / 410 (finishes Tue 22:12 -- 1293/h)
20240813-21:57:24 keep c_quizzes model 4 validated 19 / 410 (4.63%) nb_accumulated 96 / 410 (finishes Tue 22:11 -- 1315/h)
20240813-21:58:13 keep c_quizzes model 4 validated 17 / 410 (4.15%) nb_accumulated 113 / 410 (finishes Tue 22:11 -- 1306/h)
20240813-21:59:01 keep c_quizzes model 3 validated 19 / 410 (4.63%) nb_accumulated 132 / 410 (finishes Tue 22:11 -- 1320/h)
20240813-21:59:50 keep c_quizzes model 0 validated 21 / 410 (5.12%) nb_accumulated 153 / 410 (finishes Tue 22:11 -- 1349/h)
20240813-22:00:38 keep c_quizzes model 4 validated 13 / 410 (3.17%) nb_accumulated 166 / 410 (finishes Tue 22:11 -- 1308/h)
20240813-22:01:26 keep c_quizzes model 4 validated 22 / 410 (5.37%) nb_accumulated 188 / 410 (finishes Tue 22:11 -- 1340/h)
20240813-22:02:15 keep c_quizzes model 2 validated 19 / 410 (4.63%) nb_accumulated 207 / 410 (finishes Tue 22:11 -- 1346/h)
20240813-22:03:03 keep c_quizzes model 4 validated 20 / 410 (4.88%) nb_accumulated 227 / 410 (finishes Tue 22:11 -- 1357/h)
20240813-22:03:52 keep c_quizzes model 4 validated 11 / 410 (2.68%) nb_accumulated 238 / 410 (finishes Tue 22:11 -- 1317/h)
20240813-22:04:40 keep c_quizzes model 1 validated 15 / 410 (3.66%) nb_accumulated 253 / 410 (finishes Tue 22:11 -- 1303/h)
20240813-22:05:28 keep c_quizzes model 2 validated 16 / 410 (3.90%) nb_accumulated 269 / 410 (finishes Tue 22:12 -- 1296/h)
20240813-22:06:17 keep c_quizzes model 2 validated 15 / 410 (3.66%) nb_accumulated 284 / 410 (finishes Tue 22:12 -- 1285/h)
20240813-22:07:05 keep c_quizzes model 3 validated 21 / 410 (5.12%) nb_accumulated 305 / 410 (finishes Tue 22:11 -- 1300/h)
20240813-22:07:54 keep c_quizzes model 2 validated 13 / 410 (3.17%) nb_accumulated 318 / 410 (finishes Tue 22:12 -- 1282/h)
20240813-22:08:42 keep c_quizzes model 1 validated 21 / 410 (5.12%) nb_accumulated 339 / 410 (finishes Tue 22:11 -- 1297/h)
20240813-22:09:31 keep c_quizzes model 3 validated 19 / 410 (4.63%) nb_accumulated 358 / 410 (finishes Tue 22:11 -- 1302/h)
20240813-22:10:19 keep c_quizzes model 2 validated 18 / 410 (4.39%) nb_accumulated 376 / 410 (finishes Tue 22:11 -- 1304/h)
20240813-22:11:07 keep c_quizzes model 4 validated 18 / 410 (4.39%) nb_accumulated 394 / 410 (finishes Tue 22:11 -- 1306/h)
20240813-22:11:56 keep c_quizzes model 1 validated 12 / 410 (2.93%) nb_accumulated 406 / 410 (finishes Tue 22:12 -- 1288/h)
20240813-22:12:44 keep c_quizzes model 1 validated 19 / 410 (4.63%) nb_accumulated 425 / 410 (finishes now! -- 1293/h)
20240813-22:12:48 wrote c_quizzes.pth
20240813-22:12:48 training model 0
20240813-22:12:48 training model 1
20240813-22:16:32 train_perplexity 255 model 0 1.165496288628955
20240813-22:16:33 train_perplexity 255 model 1 1.1665523706487746
20240813-22:16:36 test_perplexity 255 model 0 1.166620878764872
20240813-22:16:36 test_perplexity 255 model 1 1.1662791662200405
20240813-22:17:20 test_accuracy 255 model 1 val 770 / 805
20240813-22:17:22 test_accuracy 255 model 0 val 757 / 797
20240813-22:17:24 wrote gpt_000.pth
20240813-22:17:25 wrote gpt_001.pth
20240813-22:17:38 wrote non_validated_0255_00.png
20240813-22:17:51 wrote non_validated_0255_01.png
20240813-22:17:51 wrote state.pth
20240813-22:17:51 --- epoch 256 ----------------------------------------
20240813-22:17:51 current_test_accuracies 0.9498 0.9565 0.0000 0.0000 0.0000
20240813-22:17:51 training model 2
20240813-22:17:51 training model 3
20240813-22:21:36 train_perplexity 256 model 2 1.1663164482302733
20240813-22:21:37 train_perplexity 256 model 3 1.1658766683187503
20240813-22:21:39 test_perplexity 256 model 2 1.1654586141518641
20240813-22:21:40 test_perplexity 256 model 3 1.1663882704960429
20240813-22:22:25 test_accuracy 256 model 2 val 768 / 810
20240813-22:22:27 test_accuracy 256 model 3 val 738 / 787
20240813-22:22:29 wrote gpt_002.pth
20240813-22:22:30 wrote gpt_003.pth
20240813-22:22:43 wrote non_validated_0256_02.png
20240813-22:22:56 wrote non_validated_0256_03.png
20240813-22:22:56 wrote state.pth
20240813-22:22:56 --- epoch 257 ----------------------------------------
20240813-22:22:56 current_test_accuracies 0.9498 0.9565 0.9481 0.9377 0.0000
20240813-22:22:56 training model 4
20240813-22:22:56 training model 3
20240813-22:26:40 train_perplexity 257 model 4 1.1646221455862968
20240813-22:26:42 test_perplexity 257 model 4 1.1669987578478198
20240813-22:26:43 train_perplexity 257 model 3 1.1654120919899085
20240813-22:26:45 test_perplexity 257 model 3 1.162190267161058
20240813-22:27:28 test_accuracy 257 model 4 val 763 / 807
20240813-22:27:32 test_accuracy 257 model 3 val 744 / 786
20240813-22:27:34 wrote gpt_004.pth
20240813-22:27:35 wrote gpt_003.pth
20240813-22:27:48 wrote non_validated_0257_04.png
20240813-22:28:01 wrote non_validated_0257_03.png
20240813-22:28:01 wrote state.pth
20240813-22:28:01 --- epoch 258 ----------------------------------------
20240813-22:28:01 current_test_accuracies 0.9498 0.9565 0.9481 0.9466 0.9455
20240813-22:28:01 training model 4
20240813-22:28:01 training model 3
20240813-22:31:46 train_perplexity 258 model 4 1.1650580222038456
20240813-22:31:48 test_perplexity 258 model 4 1.1665001513535735
20240813-22:31:48 train_perplexity 258 model 3 1.1660618513443601
20240813-22:31:50 test_perplexity 258 model 3 1.162850753585596
20240813-22:32:34 test_accuracy 258 model 4 val 793 / 831
20240813-22:32:36 test_accuracy 258 model 3 val 741 / 781
20240813-22:32:38 wrote gpt_004.pth
20240813-22:32:39 wrote gpt_003.pth
20240813-22:32:52 wrote non_validated_0258_04.png
20240813-22:33:05 wrote non_validated_0258_03.png
20240813-22:33:05 wrote state.pth
20240813-22:33:05 --- epoch 259 ----------------------------------------
20240813-22:33:05 current_test_accuracies 0.9498 0.9565 0.9481 0.9488 0.9543
20240813-22:33:05 training model 2
20240813-22:33:05 training model 3
20240813-22:36:49 train_perplexity 259 model 2 1.1658870150763367
20240813-22:36:51 test_perplexity 259 model 2 1.1660878035838727
20240813-22:36:52 train_perplexity 259 model 3 1.165479074855381
20240813-22:36:54 test_perplexity 259 model 3 1.1649289754800924
20240813-22:37:38 test_accuracy 259 model 3 val 753 / 805
20240813-22:37:40 test_accuracy 259 model 2 val 757 / 794
20240813-22:37:42 wrote gpt_002.pth
20240813-22:37:42 wrote gpt_003.pth
20240813-22:37:55 wrote non_validated_0259_02.png
20240813-22:38:08 wrote non_validated_0259_03.png
20240813-22:38:09 wrote state.pth
20240813-22:38:09 --- epoch 260 ----------------------------------------
20240813-22:38:09 current_test_accuracies 0.9498 0.9565 0.9534 0.9354 0.9543
20240813-22:38:09 training model 3
20240813-22:38:09 training model 0
20240813-22:41:53 train_perplexity 260 model 3 1.1655690450752696
20240813-22:41:55 test_perplexity 260 model 3 1.1639277610122432
20240813-22:41:55 train_perplexity 260 model 0 1.1655218731293344
20240813-22:41:58 test_perplexity 260 model 0 1.1655016491617984
20240813-22:42:43 test_accuracy 260 model 0 val 786 / 824
20240813-22:42:44 test_accuracy 260 model 3 val 744 / 788
20240813-22:42:46 wrote gpt_003.pth
20240813-22:42:47 wrote gpt_000.pth
20240813-22:43:00 wrote non_validated_0260_03.png
20240813-22:43:13 wrote non_validated_0260_00.png
20240813-22:43:13 wrote state.pth
20240813-22:43:13 --- epoch 261 ----------------------------------------
20240813-22:43:13 current_test_accuracies 0.9539 0.9565 0.9534 0.9442 0.9543
20240813-22:43:13 training model 3
20240813-22:43:13 training model 2
20240813-22:46:57 train_perplexity 261 model 3 1.165749250881199
20240813-22:46:59 test_perplexity 261 model 3 1.1638650767321796
20240813-22:47:00 train_perplexity 261 model 2 1.1655500586521805
20240813-22:47:02 test_perplexity 261 model 2 1.1664748622550487
20240813-22:47:47 test_accuracy 261 model 3 val 747 / 792
20240813-22:47:49 test_accuracy 261 model 2 val 750 / 785
20240813-22:47:51 wrote gpt_003.pth
20240813-22:47:52 wrote gpt_002.pth
20240813-22:48:05 wrote non_validated_0261_03.png
20240813-22:48:18 wrote non_validated_0261_02.png
20240813-22:48:18 wrote state.pth
20240813-22:48:18 --- epoch 262 ----------------------------------------
20240813-22:48:18 current_test_accuracies 0.9539 0.9565 0.9554 0.9432 0.9543
20240813-22:48:18 training model 3
20240813-22:48:18 training model 0
20240813-22:52:02 train_perplexity 262 model 3 1.1652998459965107
20240813-22:52:04 test_perplexity 262 model 3 1.165911347384792
20240813-22:52:05 train_perplexity 262 model 0 1.1649693453633843
20240813-22:52:07 test_perplexity 262 model 0 1.164979165175679
20240813-22:52:49 test_accuracy 262 model 3 val 764 / 810
20240813-22:52:53 test_accuracy 262 model 0 val 753 / 797
20240813-22:52:55 wrote gpt_003.pth
20240813-22:52:56 wrote gpt_000.pth
20240813-22:53:09 wrote non_validated_0262_03.png
20240813-22:53:22 wrote non_validated_0262_00.png
20240813-22:53:22 wrote state.pth
20240813-22:53:22 --- epoch 263 ----------------------------------------
20240813-22:53:22 current_test_accuracies 0.9448 0.9565 0.9554 0.9432 0.9543
20240813-22:53:22 training model 3
20240813-22:53:22 training model 0
20240813-22:57:06 train_perplexity 263 model 3 1.165137557961864
20240813-22:57:08 test_perplexity 263 model 3 1.1653630548370753
20240813-22:57:09 train_perplexity 263 model 0 1.1651524954627215
20240813-22:57:11 test_perplexity 263 model 0 1.1649878106938265
20240813-22:57:53 test_accuracy 263 model 3 val 770 / 813
20240813-22:57:56 test_accuracy 263 model 0 val 760 / 799
20240813-22:57:58 wrote gpt_003.pth
20240813-22:57:59 wrote gpt_000.pth
20240813-22:58:12 wrote non_validated_0263_03.png
20240813-22:58:25 wrote non_validated_0263_00.png
20240813-22:58:25 wrote state.pth
20240813-22:58:25 --- epoch 264 ----------------------------------------
20240813-22:58:25 current_test_accuracies 0.9512 0.9565 0.9554 0.9471 0.9543
20240813-22:58:25 training model 3
20240813-22:58:25 training model 0
20240813-23:02:09 train_perplexity 264 model 3 1.1651792540656634
20240813-23:02:11 test_perplexity 264 model 3 1.1653545615180245
20240813-23:02:12 train_perplexity 264 model 0 1.1649099757727126
20240813-23:02:14 test_perplexity 264 model 0 1.161601929800654
20240813-23:02:56 test_accuracy 264 model 3 val 762 / 807
20240813-23:03:00 test_accuracy 264 model 0 val 742 / 775
20240813-23:03:01 wrote gpt_003.pth
20240813-23:03:02 wrote gpt_000.pth
20240813-23:03:15 wrote non_validated_0264_03.png
20240813-23:03:28 wrote non_validated_0264_00.png
20240813-23:03:28 wrote state.pth
20240813-23:03:28 --- epoch 265 ----------------------------------------
20240813-23:03:28 current_test_accuracies 0.9574 0.9565 0.9554 0.9442 0.9543
20240813-23:03:28 training model 3
20240813-23:03:28 training model 4
20240813-23:07:14 train_perplexity 265 model 3 1.16554112651575
20240813-23:07:15 train_perplexity 265 model 4 1.1652867692603204
20240813-23:07:17 test_perplexity 265 model 3 1.1651752336174204
20240813-23:07:18 test_perplexity 265 model 4 1.1650264817391103
20240813-23:08:00 test_accuracy 265 model 3 val 764 / 808
20240813-23:08:04 test_accuracy 265 model 4 val 750 / 798
20240813-23:08:06 wrote gpt_003.pth
20240813-23:08:07 wrote gpt_004.pth
20240813-23:08:20 wrote non_validated_0265_03.png
20240813-23:08:33 wrote non_validated_0265_04.png
20240813-23:08:33 wrote state.pth
20240813-23:08:33 --- epoch 266 ----------------------------------------
20240813-23:08:33 current_test_accuracies 0.9574 0.9565 0.9554 0.9455 0.9398
20240813-23:08:33 training model 4
20240813-23:08:33 training model 3
20240813-23:12:18 train_perplexity 266 model 4 1.1653536513681806
20240813-23:12:19 test_perplexity 266 model 4 1.1625951035466549
20240813-23:12:20 train_perplexity 266 model 3 1.165148986539107
20240813-23:12:22 test_perplexity 266 model 3 1.164656734171335
20240813-23:13:06 test_accuracy 266 model 4 val 714 / 762
20240813-23:13:09 test_accuracy 266 model 3 val 734 / 787
20240813-23:13:11 wrote gpt_004.pth
20240813-23:13:12 wrote gpt_003.pth
20240813-23:13:25 wrote non_validated_0266_04.png
20240813-23:13:38 wrote non_validated_0266_03.png
20240813-23:13:38 wrote state.pth
20240813-23:13:38 --- epoch 267 ----------------------------------------
20240813-23:13:38 current_test_accuracies 0.9574 0.9565 0.9554 0.9327 0.9370
20240813-23:13:38 training model 3
20240813-23:13:38 training model 4
20240813-23:17:22 train_perplexity 267 model 3 1.165036270203825
20240813-23:17:24 test_perplexity 267 model 3 1.1659983641676395
20240813-23:17:25 train_perplexity 267 model 4 1.1649454261948387
20240813-23:17:27 test_perplexity 267 model 4 1.1626452026516512
20240813-23:18:09 test_accuracy 267 model 3 val 765 / 807
20240813-23:18:10 test_accuracy 267 model 4 val 755 / 803
20240813-23:18:12 wrote gpt_003.pth
20240813-23:18:13 wrote gpt_004.pth
20240813-23:18:26 wrote non_validated_0267_03.png
20240813-23:18:39 wrote non_validated_0267_04.png
20240813-23:18:39 wrote state.pth
20240813-23:18:39 --- epoch 268 ----------------------------------------
20240813-23:18:39 current_test_accuracies 0.9574 0.9565 0.9554 0.9480 0.9402
20240813-23:18:39 training model 4
20240813-23:18:39 training model 3
20240813-23:22:22 train_perplexity 268 model 4 1.165011208374941
20240813-23:22:24 test_perplexity 268 model 4 1.1666265138039504
20240813-23:22:26 train_perplexity 268 model 3 1.1652255445481403
20240813-23:22:28 test_perplexity 268 model 3 1.1634943094681802
20240813-23:23:09 test_accuracy 268 model 4 val 767 / 803
20240813-23:23:13 test_accuracy 268 model 3 val 749 / 789
20240813-23:23:15 wrote gpt_004.pth
20240813-23:23:16 wrote gpt_003.pth
20240813-23:23:29 wrote non_validated_0268_04.png
20240813-23:23:42 wrote non_validated_0268_03.png
20240813-23:23:42 wrote state.pth
20240813-23:23:42 --- epoch 269 ----------------------------------------
20240813-23:23:42 current_test_accuracies 0.9574 0.9565 0.9554 0.9493 0.9552
20240813-23:23:42 training model 3
20240813-23:23:42 training model 4
20240813-23:27:27 train_perplexity 269 model 3 1.1648212637863982
20240813-23:27:29 test_perplexity 269 model 3 1.1631006723885298
20240813-23:27:29 train_perplexity 269 model 4 1.1647263585357313
20240813-23:27:31 test_perplexity 269 model 4 1.1661472360099552
20240813-23:28:17 test_accuracy 269 model 3 val 758 / 788
20240813-23:28:19 test_accuracy 269 model 4 val 761 / 798
20240813-23:28:21 wrote gpt_003.pth
20240813-23:28:22 wrote gpt_004.pth
20240813-23:28:35 wrote non_validated_0269_03.png
20240813-23:28:48 wrote non_validated_0269_04.png
20240813-23:28:48 wrote state.pth
20240813-23:28:48 --- epoch 270 ----------------------------------------
20240813-23:28:48 current_test_accuracies 0.9574 0.9565 0.9554 0.9619 0.9536
20240813-23:29:59 keep c_quizzes model 1 validated 11 / 410 (2.68%) nb_accumulated 11 / 410 (finishes Wed 00:13 -- 556/h)
20240813-23:30:48 keep c_quizzes model 2 validated 18 / 410 (4.39%) nb_accumulated 29 / 410 (finishes Tue 23:57 -- 871/h)
20240813-23:31:36 keep c_quizzes model 0 validated 14 / 410 (3.41%) nb_accumulated 43 / 410 (finishes Tue 23:55 -- 918/h)
20240813-23:32:25 keep c_quizzes model 3 validated 22 / 410 (5.37%) nb_accumulated 65 / 410 (finishes Tue 23:51 -- 1076/h)
20240813-23:33:14 keep c_quizzes model 0 validated 18 / 410 (4.39%) nb_accumulated 83 / 410 (finishes Tue 23:50 -- 1122/h)
20240813-23:34:03 keep c_quizzes model 2 validated 8 / 410 (1.95%) nb_accumulated 91 / 410 (finishes Tue 23:52 -- 1040/h)
20240813-23:34:51 keep c_quizzes model 0 validated 9 / 410 (2.20%) nb_accumulated 100 / 410 (finishes Tue 23:53 -- 989/h)
20240813-23:35:40 keep c_quizzes model 2 validated 14 / 410 (3.41%) nb_accumulated 114 / 410 (finishes Tue 23:53 -- 995/h)
20240813-23:36:29 keep c_quizzes model 2 validated 13 / 410 (3.17%) nb_accumulated 127 / 410 (finishes Tue 23:53 -- 991/h)
20240813-23:37:18 keep c_quizzes model 2 validated 17 / 410 (4.15%) nb_accumulated 144 / 410 (finishes Tue 23:52 -- 1016/h)
20240813-23:38:06 keep c_quizzes model 2 validated 9 / 410 (2.20%) nb_accumulated 153 / 410 (finishes Tue 23:53 -- 985/h)
20240813-23:38:55 keep c_quizzes model 3 validated 18 / 410 (4.39%) nb_accumulated 171 / 410 (finishes Tue 23:53 -- 1013/h)
20240813-23:39:44 keep c_quizzes model 1 validated 10 / 410 (2.44%) nb_accumulated 181 / 410 (finishes Tue 23:53 -- 992/h)
20240813-23:40:33 keep c_quizzes model 0 validated 15 / 410 (3.66%) nb_accumulated 196 / 410 (finishes Tue 23:53 -- 1000/h)
20240813-23:41:22 keep c_quizzes model 1 validated 13 / 410 (3.17%) nb_accumulated 209 / 410 (finishes Tue 23:53 -- 998/h)
20240813-23:42:10 keep c_quizzes model 0 validated 9 / 410 (2.20%) nb_accumulated 218 / 410 (finishes Tue 23:53 -- 977/h)
20240813-23:42:59 keep c_quizzes model 1 validated 13 / 410 (3.17%) nb_accumulated 231 / 410 (finishes Tue 23:53 -- 976/h)
20240813-23:43:48 keep c_quizzes model 0 validated 11 / 410 (2.68%) nb_accumulated 242 / 410 (finishes Tue 23:54 -- 967/h)
20240813-23:44:37 keep c_quizzes model 1 validated 14 / 410 (3.41%) nb_accumulated 256 / 410 (finishes Tue 23:54 -- 971/h)
20240813-23:45:25 keep c_quizzes model 0 validated 17 / 410 (4.15%) nb_accumulated 273 / 410 (finishes Tue 23:53 -- 985/h)
20240813-23:46:14 keep c_quizzes model 1 validated 10 / 410 (2.44%) nb_accumulated 283 / 410 (finishes Tue 23:54 -- 973/h)
20240813-23:47:03 keep c_quizzes model 2 validated 15 / 410 (3.66%) nb_accumulated 298 / 410 (finishes Tue 23:53 -- 979/h)
20240813-23:47:52 keep c_quizzes model 2 validated 17 / 410 (4.15%) nb_accumulated 315 / 410 (finishes Tue 23:53 -- 991/h)
20240813-23:48:40 keep c_quizzes model 1 validated 24 / 410 (5.85%) nb_accumulated 339 / 410 (finishes Tue 23:52 -- 1023/h)
20240813-23:49:29 keep c_quizzes model 2 validated 20 / 410 (4.88%) nb_accumulated 359 / 410 (finishes Tue 23:52 -- 1041/h)
20240813-23:50:17 keep c_quizzes model 1 validated 16 / 410 (3.90%) nb_accumulated 375 / 410 (finishes Tue 23:52 -- 1046/h)
20240813-23:51:06 keep c_quizzes model 0 validated 17 / 410 (4.15%) nb_accumulated 392 / 410 (finishes Tue 23:52 -- 1054/h)
20240813-23:51:55 keep c_quizzes model 4 validated 18 / 410 (4.39%) nb_accumulated 410 / 410 (finishes now! -- 1064/h)
20240813-23:51:58 wrote c_quizzes.pth
20240813-23:51:58 training model 0
20240813-23:51:58 training model 1
20240813-23:55:42 train_perplexity 270 model 0 1.1667822618598558
20240813-23:55:43 test_perplexity 270 model 0 1.1677233027755662
20240813-23:55:44 train_perplexity 270 model 1 1.1672394515249565
20240813-23:55:46 test_perplexity 270 model 1 1.1663015387448976
20240813-23:56:33 test_accuracy 270 model 0 val 736 / 799
20240813-23:56:34 test_accuracy 270 model 1 val 745 / 788
20240813-23:56:36 wrote gpt_000.pth
20240813-23:56:36 wrote gpt_001.pth
20240813-23:56:49 wrote non_validated_0270_00.png
20240813-23:57:02 wrote non_validated_0270_01.png
20240813-23:57:02 wrote state.pth
20240813-23:57:02 --- epoch 271 ----------------------------------------
20240813-23:57:02 current_test_accuracies 0.9212 0.9454 0.0000 0.0000 0.0000
20240813-23:57:02 training model 2
20240813-23:57:02 training model 3
20240814-00:00:47 train_perplexity 271 model 2 1.167365532639511
20240814-00:00:49 train_perplexity 271 model 3 1.1664969302884405
20240814-00:00:49 test_perplexity 271 model 2 1.1665283204288968
20240814-00:00:51 test_perplexity 271 model 3 1.1696428977006774
20240814-00:01:35 test_accuracy 271 model 3 val 774 / 814
20240814-00:01:37 test_accuracy 271 model 2 val 740 / 793
20240814-00:01:39 wrote gpt_002.pth
20240814-00:01:40 wrote gpt_003.pth
20240814-00:01:53 wrote non_validated_0271_02.png
20240814-00:02:06 wrote non_validated_0271_03.png
20240814-00:02:06 wrote state.pth
20240814-00:02:06 --- epoch 272 ----------------------------------------
20240814-00:02:06 current_test_accuracies 0.9212 0.9454 0.9332 0.9509 0.0000
20240814-00:02:06 training model 4
20240814-00:02:06 training model 0
20240814-00:05:51 train_perplexity 272 model 4 1.1663477862785934
20240814-00:05:53 test_perplexity 272 model 4 1.167039126848441
20240814-00:05:53 train_perplexity 272 model 0 1.1663845410075364
20240814-00:05:55 test_perplexity 272 model 0 1.1664404193638769
20240814-00:06:38 test_accuracy 272 model 4 val 772 / 825
20240814-00:06:40 test_accuracy 272 model 0 val 756 / 816
20240814-00:06:42 wrote gpt_004.pth
20240814-00:06:43 wrote gpt_000.pth
20240814-00:06:56 wrote non_validated_0272_04.png
20240814-00:07:09 wrote non_validated_0272_00.png
20240814-00:07:09 wrote state.pth
20240814-00:07:09 --- epoch 273 ----------------------------------------
20240814-00:07:09 current_test_accuracies 0.9265 0.9454 0.9332 0.9509 0.9358
20240814-00:07:09 training model 0
20240814-00:07:09 training model 2
20240814-00:10:53 train_perplexity 273 model 0 1.1660286181994142
20240814-00:10:55 test_perplexity 273 model 0 1.1691855389642407
20240814-00:10:56 train_perplexity 273 model 2 1.1672815813297834
20240814-00:10:58 test_perplexity 273 model 2 1.1633423634387758
20240814-00:11:41 test_accuracy 273 model 0 val 760 / 801
20240814-00:11:42 test_accuracy 273 model 2 val 757 / 800
20240814-00:11:44 wrote gpt_000.pth
20240814-00:11:45 wrote gpt_002.pth
20240814-00:11:58 wrote non_validated_0273_00.png
20240814-00:12:11 wrote non_validated_0273_02.png
20240814-00:12:11 wrote state.pth
20240814-00:12:11 --- epoch 274 ----------------------------------------
20240814-00:12:11 current_test_accuracies 0.9488 0.9454 0.9463 0.9509 0.9358
20240814-00:12:11 training model 4
20240814-00:12:11 training model 1
20240814-00:15:55 train_perplexity 274 model 4 1.1660503491708083
20240814-00:15:57 test_perplexity 274 model 4 1.1658143837728372
20240814-00:15:58 train_perplexity 274 model 1 1.1670396814721773
20240814-00:16:01 test_perplexity 274 model 1 1.1677758911137857
20240814-00:16:42 test_accuracy 274 model 4 val 757 / 805
20240814-00:16:46 test_accuracy 274 model 1 val 758 / 797
20240814-00:16:48 wrote gpt_004.pth
20240814-00:16:49 wrote gpt_001.pth
20240814-00:17:02 wrote non_validated_0274_04.png
20240814-00:17:15 wrote non_validated_0274_01.png
20240814-00:17:15 wrote state.pth
20240814-00:17:15 --- epoch 275 ----------------------------------------
20240814-00:17:15 current_test_accuracies 0.9488 0.9511 0.9463 0.9509 0.9404
20240814-00:17:15 training model 4
20240814-00:17:15 training model 2
20240814-00:20:59 train_perplexity 275 model 4 1.1658424484324734
20240814-00:21:01 test_perplexity 275 model 4 1.1671381688918712
20240814-00:21:02 train_perplexity 275 model 2 1.1670387940482403
20240814-00:21:04 test_perplexity 275 model 2 1.164675911314411
20240814-00:21:49 test_accuracy 275 model 2 val 763 / 807
20240814-00:21:50 test_accuracy 275 model 4 val 758 / 797
20240814-00:21:52 wrote gpt_004.pth
20240814-00:21:53 wrote gpt_002.pth
20240814-00:22:06 wrote non_validated_0275_04.png
20240814-00:22:19 wrote non_validated_0275_02.png
20240814-00:22:19 wrote state.pth
20240814-00:22:19 --- epoch 276 ----------------------------------------
20240814-00:22:19 current_test_accuracies 0.9488 0.9511 0.9455 0.9509 0.9511
20240814-00:22:19 training model 2
20240814-00:22:19 training model 0
20240814-00:26:04 train_perplexity 276 model 2 1.1667744327419804
20240814-00:26:06 test_perplexity 276 model 2 1.1668893404282459
20240814-00:26:07 train_perplexity 276 model 0 1.1663015930767704
20240814-00:26:09 test_perplexity 276 model 0 1.1639828668433272
20240814-00:26:51 test_accuracy 276 model 2 val 774 / 822
20240814-00:26:55 test_accuracy 276 model 0 val 733 / 789
20240814-00:26:57 wrote gpt_002.pth
20240814-00:26:57 wrote gpt_000.pth
20240814-00:27:10 wrote non_validated_0276_02.png
20240814-00:27:23 wrote non_validated_0276_00.png
20240814-00:27:23 wrote state.pth
20240814-00:27:23 --- epoch 277 ----------------------------------------
20240814-00:27:23 current_test_accuracies 0.9290 0.9511 0.9416 0.9509 0.9511
20240814-00:27:23 training model 0
20240814-00:27:23 training model 2
20240814-00:31:08 train_perplexity 277 model 0 1.1662813734636686
20240814-00:31:10 train_perplexity 277 model 2 1.1669001807050117
20240814-00:31:11 test_perplexity 277 model 0 1.1693960035398507
20240814-00:31:13 test_perplexity 277 model 2 1.166410542566681
20240814-00:31:57 test_accuracy 277 model 2 val 771 / 812
20240814-00:31:58 test_accuracy 277 model 0 val 779 / 819
20240814-00:32:00 wrote gpt_000.pth
20240814-00:32:00 wrote gpt_002.pth
20240814-00:32:13 wrote non_validated_0277_00.png
20240814-00:32:26 wrote non_validated_0277_02.png
20240814-00:32:27 wrote state.pth
20240814-00:32:27 --- epoch 278 ----------------------------------------
20240814-00:32:27 current_test_accuracies 0.9512 0.9511 0.9495 0.9509 0.9511
20240814-00:32:27 training model 2
20240814-00:32:27 training model 3
20240814-00:36:13 train_perplexity 278 model 2 1.1668700787517146
20240814-00:36:13 train_perplexity 278 model 3 1.1660682184608744
20240814-00:36:16 test_perplexity 278 model 2 1.1641980147275919
20240814-00:36:17 test_perplexity 278 model 3 1.165251587771424
20240814-00:37:03 test_accuracy 278 model 2 val 726 / 774
20240814-00:37:04 test_accuracy 278 model 3 val 747 / 788
20240814-00:37:06 wrote gpt_002.pth
20240814-00:37:07 wrote gpt_003.pth
20240814-00:37:20 wrote non_validated_0278_02.png
20240814-00:37:33 wrote non_validated_0278_03.png
20240814-00:37:33 wrote state.pth
20240814-00:37:33 --- epoch 279 ----------------------------------------
20240814-00:37:33 current_test_accuracies 0.9512 0.9511 0.9380 0.9480 0.9511
20240814-00:37:33 training model 2
20240814-00:37:33 training model 3
20240814-00:41:18 train_perplexity 279 model 2 1.1666209962970544
20240814-00:41:20 test_perplexity 279 model 2 1.1670240096123297
20240814-00:41:20 train_perplexity 279 model 3 1.166985461791114
20240814-00:41:22 test_perplexity 279 model 3 1.1657713020385068
20240814-00:42:07 test_accuracy 279 model 2 val 740 / 779
20240814-00:42:09 test_accuracy 279 model 3 val 752 / 792
20240814-00:42:11 wrote gpt_002.pth
20240814-00:42:12 wrote gpt_003.pth
20240814-00:42:24 wrote non_validated_0279_02.png
20240814-00:42:37 wrote non_validated_0279_03.png
20240814-00:42:38 wrote state.pth
20240814-00:42:38 --- epoch 280 ----------------------------------------
20240814-00:42:38 current_test_accuracies 0.9512 0.9511 0.9499 0.9495 0.9511
20240814-00:42:38 training model 3
20240814-00:42:38 training model 2
20240814-00:46:22 train_perplexity 280 model 3 1.1665934684972477
20240814-00:46:24 test_perplexity 280 model 3 1.164561560773701
20240814-00:46:24 train_perplexity 280 model 2 1.1662409261002726
20240814-00:46:27 test_perplexity 280 model 2 1.1663711538316925
20240814-00:47:09 test_accuracy 280 model 2 val 767 / 812
20240814-00:47:11 test_accuracy 280 model 3 val 736 / 783
20240814-00:47:13 wrote gpt_003.pth
20240814-00:47:14 wrote gpt_002.pth
20240814-00:47:26 wrote non_validated_0280_03.png
20240814-00:47:39 wrote non_validated_0280_02.png
20240814-00:47:40 wrote state.pth
20240814-00:47:40 --- epoch 281 ----------------------------------------
20240814-00:47:40 current_test_accuracies 0.9512 0.9511 0.9446 0.9400 0.9511
20240814-00:47:40 training model 3
20240814-00:47:40 training model 2
20240814-00:51:24 train_perplexity 281 model 3 1.16643510657012
20240814-00:51:26 test_perplexity 281 model 3 1.1641332444498214
20240814-00:51:26 train_perplexity 281 model 2 1.1668903357127092
20240814-00:51:28 test_perplexity 281 model 2 1.1635784817677228
20240814-00:52:11 test_accuracy 281 model 3 val 752 / 808
20240814-00:52:14 test_accuracy 281 model 2 val 734 / 790
20240814-00:52:16 wrote gpt_003.pth
20240814-00:52:17 wrote gpt_002.pth
20240814-00:52:29 wrote non_validated_0281_03.png
20240814-00:52:42 wrote non_validated_0281_02.png
20240814-00:52:42 wrote state.pth
20240814-00:52:42 --- epoch 282 ----------------------------------------
20240814-00:52:42 current_test_accuracies 0.9512 0.9511 0.9291 0.9307 0.9511
20240814-00:52:42 training model 2
20240814-00:52:42 training model 3
20240814-00:56:27 train_perplexity 282 model 2 1.1670295383561409
20240814-00:56:29 test_perplexity 282 model 2 1.1675336843369168
20240814-00:56:29 train_perplexity 282 model 3 1.1664094940334893
20240814-00:56:31 test_perplexity 282 model 3 1.1661455378489543
20240814-00:57:14 test_accuracy 282 model 2 val 761 / 805
20240814-00:57:17 test_accuracy 282 model 3 val 736 / 789
20240814-00:57:19 wrote gpt_002.pth
20240814-00:57:19 wrote gpt_003.pth
20240814-00:57:33 wrote non_validated_0282_02.png
20240814-00:57:46 wrote non_validated_0282_03.png
20240814-00:57:46 wrote state.pth
20240814-00:57:46 --- epoch 283 ----------------------------------------
20240814-00:57:46 current_test_accuracies 0.9512 0.9511 0.9453 0.9328 0.9511
20240814-00:57:46 training model 3
20240814-00:57:46 training model 2
20240814-01:01:30 train_perplexity 283 model 3 1.1663369276381819
20240814-01:01:32 test_perplexity 283 model 3 1.167664121921997
20240814-01:01:32 train_perplexity 283 model 2 1.1668974865256483
20240814-01:01:35 test_perplexity 283 model 2 1.1652640297266752
20240814-01:02:16 test_accuracy 283 model 3 val 770 / 812
20240814-01:02:19 test_accuracy 283 model 2 val 761 / 803
20240814-01:02:21 wrote gpt_003.pth
20240814-01:02:21 wrote gpt_002.pth
20240814-01:02:34 wrote non_validated_0283_03.png
20240814-01:02:47 wrote non_validated_0283_02.png
20240814-01:02:47 wrote state.pth
20240814-01:02:47 --- epoch 284 ----------------------------------------
20240814-01:02:47 current_test_accuracies 0.9512 0.9511 0.9477 0.9483 0.9511
20240814-01:02:47 training model 2
20240814-01:02:47 training model 3
20240814-01:06:33 train_perplexity 284 model 2 1.1670640276635174
20240814-01:06:34 train_perplexity 284 model 3 1.1661284255069175
20240814-01:06:35 test_perplexity 284 model 2 1.165494737854134
20240814-01:06:37 test_perplexity 284 model 3 1.1642436193526073
20240814-01:07:22 test_accuracy 284 model 2 val 744 / 787
20240814-01:07:23 test_accuracy 284 model 3 val 734 / 771
20240814-01:07:25 wrote gpt_002.pth
20240814-01:07:26 wrote gpt_003.pth
20240814-01:07:39 wrote non_validated_0284_02.png
20240814-01:07:52 wrote non_validated_0284_03.png
20240814-01:07:52 wrote state.pth
20240814-01:07:52 --- epoch 285 ----------------------------------------
20240814-01:07:52 current_test_accuracies 0.9512 0.9511 0.9454 0.9520 0.9511
20240814-01:07:52 training model 2
20240814-01:07:52 training model 1
20240814-01:11:37 train_perplexity 285 model 2 1.1662458363780075
20240814-01:11:39 train_perplexity 285 model 1 1.1672980819764012
20240814-01:11:39 test_perplexity 285 model 2 1.1621374766490267
20240814-01:11:41 test_perplexity 285 model 1 1.168175636319893
20240814-01:12:27 test_accuracy 285 model 1 val 771 / 815
20240814-01:12:28 test_accuracy 285 model 2 val 751 / 793
20240814-01:12:30 wrote gpt_002.pth
20240814-01:12:30 wrote gpt_001.pth
20240814-01:12:43 wrote non_validated_0285_02.png
20240814-01:12:56 wrote non_validated_0285_01.png
20240814-01:12:56 wrote state.pth
20240814-01:12:56 --- epoch 286 ----------------------------------------
20240814-01:12:56 current_test_accuracies 0.9512 0.9460 0.9470 0.9520 0.9511
20240814-01:12:56 training model 1
20240814-01:12:56 training model 2
20240814-01:16:41 train_perplexity 286 model 1 1.1674424029082946
20240814-01:16:43 test_perplexity 286 model 1 1.1676191471229946
20240814-01:16:43 train_perplexity 286 model 2 1.1664900252245707
20240814-01:16:45 test_perplexity 286 model 2 1.1677522587603886
20240814-01:17:31 test_accuracy 286 model 1 val 740 / 780
20240814-01:17:33 test_accuracy 286 model 2 val 744 / 792
20240814-01:17:35 wrote gpt_001.pth
20240814-01:17:35 wrote gpt_002.pth
20240814-01:17:48 wrote non_validated_0286_01.png
20240814-01:18:02 wrote non_validated_0286_02.png
20240814-01:18:02 wrote state.pth
20240814-01:18:02 --- epoch 287 ----------------------------------------
20240814-01:18:02 current_test_accuracies 0.9512 0.9487 0.9394 0.9520 0.9511
20240814-01:18:02 training model 2
20240814-01:18:02 training model 1
20240814-01:21:46 train_perplexity 287 model 2 1.1661375074793465
20240814-01:21:48 test_perplexity 287 model 2 1.162920180028182
20240814-01:21:48 train_perplexity 287 model 1 1.1672210949810928
20240814-01:21:51 test_perplexity 287 model 1 1.1644369450111067
20240814-01:22:35 test_accuracy 287 model 1 val 770 / 808
20240814-01:22:36 test_accuracy 287 model 2 val 747 / 793
20240814-01:22:38 wrote gpt_002.pth
20240814-01:22:38 wrote gpt_001.pth
20240814-01:22:51 wrote non_validated_0287_02.png
20240814-01:23:04 wrote non_validated_0287_01.png
20240814-01:23:05 wrote state.pth
20240814-01:23:05 --- epoch 288 ----------------------------------------
20240814-01:23:05 current_test_accuracies 0.9512 0.9530 0.9420 0.9520 0.9511
20240814-01:23:05 training model 2
20240814-01:23:05 training model 4
20240814-01:26:49 train_perplexity 288 model 2 1.166650274527412
20240814-01:26:51 test_perplexity 288 model 2 1.162550779594701
20240814-01:26:51 train_perplexity 288 model 4 1.1659659645098486
20240814-01:26:54 test_perplexity 288 model 4 1.1683472614621693
20240814-01:27:39 test_accuracy 288 model 4 val 765 / 810
20240814-01:27:40 test_accuracy 288 model 2 val 729 / 775
20240814-01:27:42 wrote gpt_002.pth
20240814-01:27:43 wrote gpt_004.pth
20240814-01:27:56 wrote non_validated_0288_02.png
20240814-01:28:09 wrote non_validated_0288_04.png
20240814-01:28:09 wrote state.pth
20240814-01:28:09 --- epoch 289 ----------------------------------------
20240814-01:28:09 current_test_accuracies 0.9512 0.9530 0.9406 0.9520 0.9444
20240814-01:28:09 training model 2
20240814-01:28:09 training model 4
20240814-01:31:54 train_perplexity 289 model 2 1.1665488151927799
20240814-01:31:56 test_perplexity 289 model 2 1.1680250583086098
20240814-01:31:56 train_perplexity 289 model 4 1.1660578807214592
20240814-01:31:58 test_perplexity 289 model 4 1.1680608303380862
20240814-01:32:44 test_accuracy 289 model 2 val 774 / 832
20240814-01:32:46 test_accuracy 289 model 4 val 758 / 799
20240814-01:32:48 wrote gpt_002.pth
20240814-01:32:48 wrote gpt_004.pth
20240814-01:33:01 wrote non_validated_0289_02.png
20240814-01:33:14 wrote non_validated_0289_04.png
20240814-01:33:14 wrote state.pth
20240814-01:33:14 --- epoch 290 ----------------------------------------
20240814-01:33:14 current_test_accuracies 0.9512 0.9530 0.9303 0.9520 0.9487
20240814-01:33:14 training model 2
20240814-01:33:14 training model 4
20240814-01:36:59 train_perplexity 290 model 2 1.1660446314602342
20240814-01:37:00 test_perplexity 290 model 2 1.165772105029256
20240814-01:37:01 train_perplexity 290 model 4 1.1658937258403943
20240814-01:37:04 test_perplexity 290 model 4 1.1645991000795453
20240814-01:37:48 test_accuracy 290 model 2 val 739 / 779
20240814-01:37:51 test_accuracy 290 model 4 val 757 / 791
20240814-01:37:53 wrote gpt_002.pth
20240814-01:37:53 wrote gpt_004.pth
20240814-01:38:06 wrote non_validated_0290_02.png
20240814-01:38:19 wrote non_validated_0290_04.png
20240814-01:38:19 wrote state.pth
20240814-01:38:19 --- epoch 291 ----------------------------------------
20240814-01:38:19 current_test_accuracies 0.9512 0.9530 0.9487 0.9520 0.9570
20240814-01:38:19 training model 2
20240814-01:38:19 training model 0
20240814-01:42:04 train_perplexity 291 model 2 1.1663984107705938
20240814-01:42:05 test_perplexity 291 model 2 1.1660975098926853
20240814-01:42:06 train_perplexity 291 model 0 1.1662899557839634
20240814-01:42:09 test_perplexity 291 model 0 1.1679919428534935
20240814-01:42:50 test_accuracy 291 model 2 val 761 / 812
20240814-01:42:55 test_accuracy 291 model 0 val 745 / 795
20240814-01:42:57 wrote gpt_002.pth
20240814-01:42:57 wrote gpt_000.pth
20240814-01:43:10 wrote non_validated_0291_02.png
20240814-01:43:23 wrote non_validated_0291_00.png
20240814-01:43:23 wrote state.pth
20240814-01:43:23 --- epoch 292 ----------------------------------------
20240814-01:43:23 current_test_accuracies 0.9371 0.9530 0.9372 0.9520 0.9570
20240814-01:43:23 training model 0
20240814-01:43:23 training model 2
20240814-01:47:07 train_perplexity 292 model 0 1.1664427507819657
20240814-01:47:09 test_perplexity 292 model 0 1.166340358112011
20240814-01:47:10 train_perplexity 292 model 2 1.1662723442451162
20240814-01:47:13 test_perplexity 292 model 2 1.164823085571303
20240814-01:47:58 test_accuracy 292 model 0 val 748 / 799
20240814-01:48:00 test_accuracy 292 model 2 val 741 / 787
20240814-01:48:02 wrote gpt_000.pth
20240814-01:48:03 wrote gpt_002.pth
20240814-01:48:16 wrote non_validated_0292_00.png
20240814-01:48:29 wrote non_validated_0292_02.png
20240814-01:48:29 wrote state.pth
20240814-01:48:29 --- epoch 293 ----------------------------------------
20240814-01:48:29 current_test_accuracies 0.9362 0.9530 0.9416 0.9520 0.9570
20240814-01:48:29 training model 0
20240814-01:48:29 training model 2
20240814-01:52:13 train_perplexity 293 model 0 1.1660091055898563
20240814-01:52:15 test_perplexity 293 model 0 1.1652239903896253
20240814-01:52:16 train_perplexity 293 model 2 1.1661453148541856
20240814-01:52:18 test_perplexity 293 model 2 1.162714158121685
20240814-01:53:02 test_accuracy 293 model 0 val 758 / 796
20240814-01:53:03 test_accuracy 293 model 2 val 756 / 801
20240814-01:53:05 wrote gpt_000.pth
20240814-01:53:06 wrote gpt_002.pth
20240814-01:53:19 wrote non_validated_0293_00.png
20240814-01:53:32 wrote non_validated_0293_02.png
20240814-01:53:32 wrote state.pth
20240814-01:53:32 --- epoch 294 ----------------------------------------
20240814-01:53:32 current_test_accuracies 0.9523 0.9530 0.9438 0.9520 0.9570
20240814-01:53:32 training model 2
20240814-01:53:32 training model 3
20240814-01:57:17 train_perplexity 294 model 2 1.165687872175052
20240814-01:57:18 test_perplexity 294 model 2 1.1667609461956827
20240814-01:57:19 train_perplexity 294 model 3 1.1658125127460803
20240814-01:57:21 test_perplexity 294 model 3 1.1658666659431773
20240814-01:58:04 test_accuracy 294 model 2 val 763 / 803
20240814-01:58:08 test_accuracy 294 model 3 val 753 / 796
20240814-01:58:10 wrote gpt_002.pth
20240814-01:58:10 wrote gpt_003.pth
20240814-01:58:23 wrote non_validated_0294_02.png
20240814-01:58:36 wrote non_validated_0294_03.png
20240814-01:58:36 wrote state.pth
20240814-01:58:36 --- epoch 295 ----------------------------------------
20240814-01:58:36 current_test_accuracies 0.9523 0.9530 0.9502 0.9460 0.9570
20240814-01:58:36 training model 3
20240814-01:58:36 training model 2
20240814-02:02:20 train_perplexity 295 model 3 1.1659581840657667
20240814-02:02:22 test_perplexity 295 model 3 1.1663486331108692
20240814-02:02:23 train_perplexity 295 model 2 1.1658708631352626
20240814-02:02:25 test_perplexity 295 model 2 1.1641272929477433
20240814-02:03:09 test_accuracy 295 model 2 val 755 / 808
20240814-02:03:11 test_accuracy 295 model 3 val 741 / 782
20240814-02:03:13 wrote gpt_003.pth
20240814-02:03:14 wrote gpt_002.pth
20240814-02:03:27 wrote non_validated_0295_03.png
20240814-02:03:40 wrote non_validated_0295_02.png
20240814-02:03:40 wrote state.pth
20240814-02:03:40 --- epoch 296 ----------------------------------------
20240814-02:03:40 current_test_accuracies 0.9523 0.9530 0.9344 0.9476 0.9570
20240814-02:03:40 training model 2
20240814-02:03:40 training model 3
20240814-02:07:24 train_perplexity 296 model 2 1.1660697244524545
20240814-02:07:26 test_perplexity 296 model 2 1.16508367387389
20240814-02:07:27 train_perplexity 296 model 3 1.166243158806882
20240814-02:07:29 test_perplexity 296 model 3 1.1641063069196602
20240814-02:08:14 test_accuracy 296 model 2 val 752 / 794
20240814-02:08:16 test_accuracy 296 model 3 val 737 / 773
20240814-02:08:18 wrote gpt_002.pth
20240814-02:08:18 wrote gpt_003.pth
20240814-02:08:31 wrote non_validated_0296_02.png
20240814-02:08:44 wrote non_validated_0296_03.png
20240814-02:08:44 wrote state.pth
20240814-02:08:44 --- epoch 297 ----------------------------------------
20240814-02:08:44 current_test_accuracies 0.9523 0.9530 0.9471 0.9534 0.9570
20240814-02:08:44 training model 2
20240814-02:08:44 training model 0
20240814-02:12:29 train_perplexity 297 model 2 1.1660250201417497
20240814-02:12:31 test_perplexity 297 model 2 1.167447666339655
20240814-02:12:32 train_perplexity 297 model 0 1.1660817638485796
20240814-02:12:34 test_perplexity 297 model 0 1.1679473583250952
20240814-02:13:18 test_accuracy 297 model 2 val 768 / 818
20240814-02:13:19 test_accuracy 297 model 0 val 776 / 824
20240814-02:13:21 wrote gpt_002.pth
20240814-02:13:22 wrote gpt_000.pth
20240814-02:13:35 wrote non_validated_0297_02.png
20240814-02:13:48 wrote non_validated_0297_00.png
20240814-02:13:48 wrote state.pth
20240814-02:13:48 --- epoch 298 ----------------------------------------
20240814-02:13:48 current_test_accuracies 0.9417 0.9530 0.9389 0.9534 0.9570
20240814-02:13:48 training model 2
20240814-02:13:48 training model 0
20240814-02:17:33 train_perplexity 298 model 2 1.1658412080704714
20240814-02:17:34 test_perplexity 298 model 2 1.1669748925545727
20240814-02:17:35 train_perplexity 298 model 0 1.1660591050134663
20240814-02:17:37 test_perplexity 298 model 0 1.1652048376456643
20240814-02:18:20 test_accuracy 298 model 2 val 757 / 803
20240814-02:18:23 test_accuracy 298 model 0 val 754 / 794
20240814-02:18:25 wrote gpt_002.pth
20240814-02:18:25 wrote gpt_000.pth
20240814-02:18:38 wrote non_validated_0298_02.png
20240814-02:18:51 wrote non_validated_0298_00.png
20240814-02:18:52 wrote state.pth
20240814-02:18:52 --- epoch 299 ----------------------------------------
20240814-02:18:52 current_test_accuracies 0.9496 0.9530 0.9427 0.9534 0.9570
20240814-02:18:52 training model 2
20240814-02:18:52 training model 0
20240814-02:22:36 train_perplexity 299 model 2 1.1663094771884293
20240814-02:22:38 test_perplexity 299 model 2 1.1657913105266333
20240814-02:22:39 train_perplexity 299 model 0 1.1657362496047954
20240814-02:22:41 test_perplexity 299 model 0 1.1668565636275825
20240814-02:23:23 test_accuracy 299 model 2 val 764 / 811
20240814-02:23:25 test_accuracy 299 model 0 val 767 / 810
20240814-02:23:27 wrote gpt_002.pth
20240814-02:23:27 wrote gpt_000.pth
20240814-02:23:40 wrote non_validated_0299_02.png
20240814-02:23:53 wrote non_validated_0299_00.png
20240814-02:23:53 wrote state.pth
20240814-02:23:53 --- epoch 300 ----------------------------------------
20240814-02:23:53 current_test_accuracies 0.9469 0.9530 0.9420 0.9534 0.9570
20240814-02:23:53 training model 2
20240814-02:23:53 training model 0
20240814-02:27:37 train_perplexity 300 model 2 1.1659089939710847
20240814-02:27:39 test_perplexity 300 model 2 1.1686769342343422
20240814-02:27:40 train_perplexity 300 model 0 1.165848094326167
20240814-02:27:42 test_perplexity 300 model 0 1.1643100251119194
20240814-02:28:23 test_accuracy 300 model 2 val 767 / 806
20240814-02:28:26 test_accuracy 300 model 0 val 761 / 801
20240814-02:28:28 wrote gpt_002.pth
20240814-02:28:28 wrote gpt_000.pth
20240814-02:28:41 wrote non_validated_0300_02.png
20240814-02:28:54 wrote non_validated_0300_00.png
20240814-02:28:54 wrote state.pth
20240814-02:28:54 --- epoch 301 ----------------------------------------
20240814-02:28:54 current_test_accuracies 0.9501 0.9530 0.9516 0.9534 0.9570
20240814-02:30:06 keep c_quizzes model 0 validated 15 / 410 (3.66%) nb_accumulated 15 / 410 (finishes Wed 03:01 -- 759/h)
20240814-02:30:55 keep c_quizzes model 0 validated 17 / 410 (4.15%) nb_accumulated 32 / 410 (finishes Wed 02:54 -- 958/h)
20240814-02:31:43 keep c_quizzes model 1 validated 5 / 410 (1.22%) nb_accumulated 37 / 410 (finishes Wed 03:00 -- 788/h)
20240814-02:32:32 keep c_quizzes model 4 validated 14 / 410 (3.41%) nb_accumulated 51 / 410 (finishes Wed 02:58 -- 842/h)
20240814-02:33:21 keep c_quizzes model 0 validated 20 / 410 (4.88%) nb_accumulated 71 / 410 (finishes Wed 02:54 -- 958/h)
20240814-02:34:10 keep c_quizzes model 2 validated 19 / 410 (4.63%) nb_accumulated 90 / 410 (finishes Wed 02:52 -- 1027/h)
20240814-02:34:59 keep c_quizzes model 1 validated 18 / 410 (4.39%) nb_accumulated 108 / 410 (finishes Wed 02:51 -- 1067/h)
20240814-02:35:48 keep c_quizzes model 0 validated 14 / 410 (3.41%) nb_accumulated 122 / 410 (finishes Wed 02:52 -- 1063/h)
20240814-02:36:36 keep c_quizzes model 1 validated 15 / 410 (3.66%) nb_accumulated 137 / 410 (finishes Wed 02:51 -- 1067/h)
20240814-02:37:25 keep c_quizzes model 1 validated 9 / 410 (2.20%) nb_accumulated 146 / 410 (finishes Wed 02:52 -- 1028/h)
20240814-02:38:14 keep c_quizzes model 1 validated 16 / 410 (3.90%) nb_accumulated 162 / 410 (finishes Wed 02:52 -- 1041/h)
20240814-02:39:03 keep c_quizzes model 1 validated 19 / 410 (4.63%) nb_accumulated 181 / 410 (finishes Wed 02:51 -- 1070/h)
20240814-02:39:52 keep c_quizzes model 1 validated 16 / 410 (3.90%) nb_accumulated 197 / 410 (finishes Wed 02:51 -- 1079/h)
20240814-02:40:40 keep c_quizzes model 4 validated 9 / 410 (2.20%) nb_accumulated 206 / 410 (finishes Wed 02:52 -- 1050/h)
20240814-02:41:29 keep c_quizzes model 0 validated 18 / 410 (4.39%) nb_accumulated 224 / 410 (finishes Wed 02:51 -- 1068/h)
20240814-02:42:18 keep c_quizzes model 4 validated 15 / 410 (3.66%) nb_accumulated 239 / 410 (finishes Wed 02:51 -- 1070/h)
20240814-02:43:07 keep c_quizzes model 3 validated 13 / 410 (3.17%) nb_accumulated 252 / 410 (finishes Wed 02:52 -- 1064/h)
20240814-02:43:55 keep c_quizzes model 4 validated 16 / 410 (3.90%) nb_accumulated 268 / 410 (finishes Wed 02:51 -- 1070/h)
20240814-02:44:44 keep c_quizzes model 0 validated 14 / 410 (3.41%) nb_accumulated 282 / 410 (finishes Wed 02:51 -- 1069/h)
20240814-02:45:33 keep c_quizzes model 0 validated 18 / 410 (4.39%) nb_accumulated 300 / 410 (finishes Wed 02:51 -- 1081/h)
20240814-02:46:22 keep c_quizzes model 0 validated 16 / 410 (3.90%) nb_accumulated 316 / 410 (finishes Wed 02:51 -- 1086/h)
20240814-02:47:10 keep c_quizzes model 3 validated 16 / 410 (3.90%) nb_accumulated 332 / 410 (finishes Wed 02:51 -- 1090/h)
20240814-02:47:59 keep c_quizzes model 0 validated 14 / 410 (3.41%) nb_accumulated 346 / 410 (finishes Wed 02:51 -- 1088/h)
20240814-02:48:47 keep c_quizzes model 2 validated 15 / 410 (3.66%) nb_accumulated 361 / 410 (finishes Wed 02:51 -- 1089/h)
20240814-02:49:36 keep c_quizzes model 0 validated 20 / 410 (4.88%) nb_accumulated 381 / 410 (finishes Wed 02:51 -- 1104/h)
20240814-02:50:25 keep c_quizzes model 3 validated 9 / 410 (2.20%) nb_accumulated 390 / 410 (finishes Wed 02:51 -- 1087/h)
20240814-02:51:14 keep c_quizzes model 0 validated 11 / 410 (2.68%) nb_accumulated 401 / 410 (finishes Wed 02:51 -- 1077/h)
20240814-02:52:03 keep c_quizzes model 3 validated 15 / 410 (3.66%) nb_accumulated 416 / 410 (finishes now! -- 1078/h)
20240814-02:52:06 wrote c_quizzes.pth
20240814-02:52:06 training model 0
20240814-02:52:06 training model 1
20240814-02:55:50 train_perplexity 301 model 0 1.1672878733494827
20240814-02:55:51 train_perplexity 301 model 1 1.1691938270931532
20240814-02:55:53 test_perplexity 301 model 0 1.1671277608670412
20240814-02:55:54 test_perplexity 301 model 1 1.167905019196367
20240814-02:56:41 test_accuracy 301 model 1 val 756 / 796
20240814-02:56:42 test_accuracy 301 model 0 val 750 / 795
20240814-02:56:44 wrote gpt_000.pth
20240814-02:56:45 wrote gpt_001.pth
20240814-02:56:57 wrote non_validated_0301_00.png
20240814-02:57:10 wrote non_validated_0301_01.png
20240814-02:57:10 wrote state.pth
20240814-02:57:10 --- epoch 302 ----------------------------------------
20240814-02:57:10 current_test_accuracies 0.9434 0.9497 0.0000 0.0000 0.0000
20240814-02:57:10 training model 2
20240814-02:57:10 training model 3
20240814-03:00:55 train_perplexity 302 model 2 1.1673251885396336
20240814-03:00:57 test_perplexity 302 model 2 1.1662689639732866
20240814-03:00:57 train_perplexity 302 model 3 1.167443455517647
20240814-03:00:59 test_perplexity 302 model 3 1.165793454623795
20240814-03:01:43 test_accuracy 302 model 3 val 753 / 801
20240814-03:01:45 test_accuracy 302 model 2 val 755 / 796
20240814-03:01:47 wrote gpt_002.pth
20240814-03:01:47 wrote gpt_003.pth
20240814-03:02:00 wrote non_validated_0302_02.png
20240814-03:02:13 wrote non_validated_0302_03.png
20240814-03:02:13 wrote state.pth
20240814-03:02:13 --- epoch 303 ----------------------------------------
20240814-03:02:13 current_test_accuracies 0.9434 0.9497 0.9485 0.9401 0.0000
20240814-03:02:13 training model 4
20240814-03:02:13 training model 3
20240814-03:05:58 train_perplexity 303 model 4 1.1674625413748647
20240814-03:06:00 test_perplexity 303 model 4 1.169273568055544
20240814-03:06:00 train_perplexity 303 model 3 1.1672758638653788
20240814-03:06:02 test_perplexity 303 model 3 1.1670340458666706
20240814-03:06:46 test_accuracy 303 model 4 val 772 / 825
20240814-03:06:48 test_accuracy 303 model 3 val 753 / 796
20240814-03:06:50 wrote gpt_004.pth
20240814-03:06:51 wrote gpt_003.pth
20240814-03:07:04 wrote non_validated_0303_04.png
20240814-03:07:17 wrote non_validated_0303_03.png
20240814-03:07:17 wrote state.pth
20240814-03:07:17 --- epoch 304 ----------------------------------------
20240814-03:07:17 current_test_accuracies 0.9434 0.9497 0.9485 0.9460 0.9358
20240814-03:07:17 training model 4
20240814-03:07:17 training model 0
20240814-03:11:02 train_perplexity 304 model 4 1.1669448074104374
20240814-03:11:03 test_perplexity 304 model 4 1.168256690412802
20240814-03:11:03 train_perplexity 304 model 0 1.167305157682724
20240814-03:11:06 test_perplexity 304 model 0 1.1661637446617734
20240814-03:11:50 test_accuracy 304 model 0 val 762 / 802
20240814-03:11:52 test_accuracy 304 model 4 val 723 / 772
20240814-03:11:54 wrote gpt_004.pth
20240814-03:11:55 wrote gpt_000.pth
20240814-03:12:08 wrote non_validated_0304_04.png
20240814-03:12:21 wrote non_validated_0304_00.png
20240814-03:12:21 wrote state.pth
20240814-03:12:21 --- epoch 305 ----------------------------------------
20240814-03:12:21 current_test_accuracies 0.9501 0.9497 0.9485 0.9460 0.9365
20240814-03:12:21 training model 4
20240814-03:12:21 training model 3
20240814-03:16:05 train_perplexity 305 model 4 1.1669537874294338
20240814-03:16:07 test_perplexity 305 model 4 1.1683773040800123
20240814-03:16:07 train_perplexity 305 model 3 1.1672209246117278
20240814-03:16:10 test_perplexity 305 model 3 1.1664351528368024
20240814-03:16:53 test_accuracy 305 model 3 val 759 / 804
20240814-03:16:55 test_accuracy 305 model 4 val 725 / 776
20240814-03:16:57 wrote gpt_004.pth
20240814-03:16:57 wrote gpt_003.pth
20240814-03:17:10 wrote non_validated_0305_04.png
20240814-03:17:23 wrote non_validated_0305_03.png
20240814-03:17:23 wrote state.pth
20240814-03:17:23 --- epoch 306 ----------------------------------------
20240814-03:17:23 current_test_accuracies 0.9501 0.9497 0.9485 0.9440 0.9343
20240814-03:17:23 training model 4
20240814-03:17:23 training model 3
20240814-03:21:08 train_perplexity 306 model 4 1.167229790656726
20240814-03:21:10 test_perplexity 306 model 4 1.1693509267491513
20240814-03:21:10 train_perplexity 306 model 3 1.167317301339731
20240814-03:21:12 test_perplexity 306 model 3 1.1679824531231995
20240814-03:21:56 test_accuracy 306 model 4 val 788 / 819
20240814-03:21:57 test_accuracy 306 model 3 val 767 / 815
20240814-03:21:59 wrote gpt_004.pth
20240814-03:22:00 wrote gpt_003.pth
20240814-03:22:12 wrote non_validated_0306_04.png
20240814-03:22:25 wrote non_validated_0306_03.png
20240814-03:22:26 wrote state.pth
20240814-03:22:26 --- epoch 307 ----------------------------------------
20240814-03:22:26 current_test_accuracies 0.9501 0.9497 0.9485 0.9411 0.9621
20240814-03:22:26 training model 3
20240814-03:22:26 training model 2
20240814-03:26:11 train_perplexity 307 model 3 1.167627532973401
20240814-03:26:12 train_perplexity 307 model 2 1.1670779115824326
20240814-03:26:13 test_perplexity 307 model 3 1.1681455749533078
20240814-03:26:15 test_perplexity 307 model 2 1.1684274577872502
20240814-03:26:58 test_accuracy 307 model 3 val 772 / 811
20240814-03:27:00 test_accuracy 307 model 2 val 759 / 803
20240814-03:27:02 wrote gpt_003.pth
20240814-03:27:03 wrote gpt_002.pth
20240814-03:27:16 wrote non_validated_0307_03.png
20240814-03:27:29 wrote non_validated_0307_02.png
20240814-03:27:29 wrote state.pth
20240814-03:27:29 --- epoch 308 ----------------------------------------
20240814-03:27:29 current_test_accuracies 0.9501 0.9497 0.9452 0.9519 0.9621
20240814-03:27:29 training model 2
20240814-03:27:29 training model 1
20240814-03:31:13 train_perplexity 308 model 2 1.167354119812383
20240814-03:31:15 test_perplexity 308 model 2 1.1679184984418953
20240814-03:31:15 train_perplexity 308 model 1 1.1686016201843374
20240814-03:31:18 test_perplexity 308 model 1 1.1661301154976742
20240814-03:32:01 test_accuracy 308 model 2 val 765 / 811
20240814-03:32:04 test_accuracy 308 model 1 val 755 / 792
20240814-03:32:06 wrote gpt_002.pth
20240814-03:32:06 wrote gpt_001.pth
20240814-03:32:19 wrote non_validated_0308_02.png
20240814-03:32:32 wrote non_validated_0308_01.png
20240814-03:32:32 wrote state.pth
20240814-03:32:32 --- epoch 309 ----------------------------------------
20240814-03:32:32 current_test_accuracies 0.9501 0.9533 0.9433 0.9519 0.9621
20240814-03:32:32 training model 2
20240814-03:32:32 training model 0
20240814-03:36:17 train_perplexity 309 model 2 1.167515829357666
20240814-03:36:19 test_perplexity 309 model 2 1.1657925573770653
20240814-03:36:19 train_perplexity 309 model 0 1.1676553533531702
20240814-03:36:21 test_perplexity 309 model 0 1.1661776221714233
20240814-03:37:07 test_accuracy 309 model 2 val 748 / 798
20240814-03:37:07 test_accuracy 309 model 0 val 768 / 817
20240814-03:37:09 wrote gpt_002.pth
20240814-03:37:10 wrote gpt_000.pth
20240814-03:37:23 wrote non_validated_0309_02.png
20240814-03:37:36 wrote non_validated_0309_00.png
20240814-03:37:36 wrote state.pth
20240814-03:37:36 --- epoch 310 ----------------------------------------
20240814-03:37:36 current_test_accuracies 0.9400 0.9533 0.9373 0.9519 0.9621
20240814-03:37:36 training model 2
20240814-03:37:36 training model 0
20240814-03:41:21 train_perplexity 310 model 2 1.1671166432572695
20240814-03:41:22 train_perplexity 310 model 0 1.1671832552322339
20240814-03:41:23 test_perplexity 310 model 2 1.1664404841092835
20240814-03:41:25 test_perplexity 310 model 0 1.1668885366679382
20240814-03:42:09 test_accuracy 310 model 0 val 751 / 808
20240814-03:42:10 test_accuracy 310 model 2 val 751 / 801
20240814-03:42:12 wrote gpt_002.pth
20240814-03:42:12 wrote gpt_000.pth
20240814-03:42:25 wrote non_validated_0310_02.png
20240814-03:42:38 wrote non_validated_0310_00.png
20240814-03:42:39 wrote state.pth
20240814-03:42:39 --- epoch 311 ----------------------------------------
20240814-03:42:39 current_test_accuracies 0.9295 0.9533 0.9376 0.9519 0.9621
20240814-03:42:39 training model 0
20240814-03:42:39 training model 2
20240814-03:46:23 train_perplexity 311 model 0 1.16669808854599
20240814-03:46:25 train_perplexity 311 model 2 1.1669297168051953
20240814-03:46:25 test_perplexity 311 model 0 1.164041919660745
20240814-03:46:28 test_perplexity 311 model 2 1.1678533512839664
20240814-03:47:11 test_accuracy 311 model 2 val 752 / 800
20240814-03:47:13 test_accuracy 311 model 0 val 745 / 777
20240814-03:47:15 wrote gpt_000.pth
20240814-03:47:16 wrote gpt_002.pth
20240814-03:47:29 wrote non_validated_0311_00.png
20240814-03:47:42 wrote non_validated_0311_02.png
20240814-03:47:42 wrote state.pth
20240814-03:47:42 --- epoch 312 ----------------------------------------
20240814-03:47:42 current_test_accuracies 0.9588 0.9533 0.9400 0.9519 0.9621
20240814-03:47:42 training model 2
20240814-03:47:42 training model 3
20240814-03:51:26 train_perplexity 312 model 2 1.1675098316123822
20240814-03:51:28 test_perplexity 312 model 2 1.1661897916286494
20240814-03:51:29 train_perplexity 312 model 3 1.1671036082634403
20240814-03:51:31 test_perplexity 312 model 3 1.1674941728638744
20240814-03:52:17 test_accuracy 312 model 2 val 748 / 794
20240814-03:52:19 test_accuracy 312 model 3 val 742 / 790
20240814-03:52:21 wrote gpt_002.pth
20240814-03:52:22 wrote gpt_003.pth
20240814-03:52:34 wrote non_validated_0312_02.png
20240814-03:52:48 wrote non_validated_0312_03.png
20240814-03:52:48 wrote state.pth
20240814-03:52:48 --- epoch 313 ----------------------------------------
20240814-03:52:48 current_test_accuracies 0.9588 0.9533 0.9421 0.9392 0.9621
20240814-03:52:48 training model 3
20240814-03:52:48 training model 2
20240814-03:56:31 train_perplexity 313 model 3 1.1672035967776007
20240814-03:56:33 test_perplexity 313 model 3 1.1662585762991338
20240814-03:56:35 train_perplexity 313 model 2 1.167020379990788
20240814-03:56:37 test_perplexity 313 model 2 1.1672078743542276
20240814-03:57:22 test_accuracy 313 model 3 val 745 / 788
20240814-03:57:23 test_accuracy 313 model 2 val 731 / 777
20240814-03:57:25 wrote gpt_003.pth
20240814-03:57:26 wrote gpt_002.pth
20240814-03:57:39 wrote non_validated_0313_03.png
20240814-03:57:52 wrote non_validated_0313_02.png
20240814-03:57:52 wrote state.pth
20240814-03:57:52 --- epoch 314 ----------------------------------------
20240814-03:57:52 current_test_accuracies 0.9588 0.9533 0.9408 0.9454 0.9621
20240814-03:57:52 training model 2
20240814-03:57:52 training model 3
20240814-04:01:36 train_perplexity 314 model 2 1.167054537266245
20240814-04:01:38 test_perplexity 314 model 2 1.1689280141835408
20240814-04:01:39 train_perplexity 314 model 3 1.1673987342839092
20240814-04:01:41 test_perplexity 314 model 3 1.1706473502333326
20240814-04:02:23 test_accuracy 314 model 2 val 760 / 801
20240814-04:02:25 test_accuracy 314 model 3 val 768 / 818
20240814-04:02:27 wrote gpt_002.pth
20240814-04:02:28 wrote gpt_003.pth
20240814-04:02:41 wrote non_validated_0314_02.png
20240814-04:02:54 wrote non_validated_0314_03.png
20240814-04:02:54 wrote state.pth
20240814-04:02:54 --- epoch 315 ----------------------------------------
20240814-04:02:54 current_test_accuracies 0.9588 0.9533 0.9488 0.9389 0.9621
20240814-04:02:54 training model 3
20240814-04:02:54 training model 2
20240814-04:06:39 train_perplexity 315 model 3 1.1669541254057827
20240814-04:06:40 test_perplexity 315 model 3 1.1677189766008844
20240814-04:06:41 train_perplexity 315 model 2 1.167418610417296
20240814-04:06:43 test_perplexity 315 model 2 1.1676779733519547
20240814-04:07:28 test_accuracy 315 model 3 val 741 / 785
20240814-04:07:30 test_accuracy 315 model 2 val 747 / 786
20240814-04:07:32 wrote gpt_003.pth
20240814-04:07:33 wrote gpt_002.pth
20240814-04:07:46 wrote non_validated_0315_03.png
20240814-04:07:59 wrote non_validated_0315_02.png
20240814-04:07:59 wrote state.pth
20240814-04:07:59 --- epoch 316 ----------------------------------------
20240814-04:07:59 current_test_accuracies 0.9588 0.9533 0.9504 0.9439 0.9621
20240814-04:07:59 training model 3
20240814-04:07:59 training model 2
20240814-04:11:44 train_perplexity 316 model 3 1.1670399515590388
20240814-04:11:46 test_perplexity 316 model 3 1.1690549222788507
20240814-04:11:46 train_perplexity 316 model 2 1.1665367034425178
20240814-04:11:48 test_perplexity 316 model 2 1.1671456073516484
20240814-04:12:32 test_accuracy 316 model 3 val 781 / 817
20240814-04:12:34 test_accuracy 316 model 2 val 780 / 829
20240814-04:12:36 wrote gpt_003.pth
20240814-04:12:36 wrote gpt_002.pth
20240814-04:12:49 wrote non_validated_0316_03.png
20240814-04:13:02 wrote non_validated_0316_02.png
20240814-04:13:03 wrote state.pth
20240814-04:13:03 --- epoch 317 ----------------------------------------
20240814-04:13:03 current_test_accuracies 0.9588 0.9533 0.9409 0.9559 0.9621
20240814-04:13:03 training model 2
20240814-04:13:03 training model 1
20240814-04:16:47 train_perplexity 317 model 2 1.16663904494244
20240814-04:16:49 train_perplexity 317 model 1 1.16872333304416
20240814-04:16:49 test_perplexity 317 model 2 1.1662712592755136
20240814-04:16:51 test_perplexity 317 model 1 1.1679188608665445
20240814-04:17:38 test_accuracy 317 model 2 val 746 / 783
20240814-04:17:39 test_accuracy 317 model 1 val 749 / 795
20240814-04:17:41 wrote gpt_002.pth
20240814-04:17:41 wrote gpt_001.pth
20240814-04:17:54 wrote non_validated_0317_02.png
20240814-04:18:07 wrote non_validated_0317_01.png
20240814-04:18:07 wrote state.pth
20240814-04:18:07 --- epoch 318 ----------------------------------------
20240814-04:18:07 current_test_accuracies 0.9588 0.9421 0.9527 0.9559 0.9621
20240814-04:18:07 training model 1
20240814-04:18:07 training model 2
20240814-04:21:52 train_perplexity 318 model 1 1.168880814100744
20240814-04:21:53 test_perplexity 318 model 1 1.1659945456426994
20240814-04:21:54 train_perplexity 318 model 2 1.166655496136069
20240814-04:21:57 test_perplexity 318 model 2 1.1675380494048309
20240814-04:22:39 test_accuracy 318 model 2 val 769 / 800
20240814-04:22:41 test_accuracy 318 model 1 val 733 / 782
20240814-04:22:43 wrote gpt_001.pth
20240814-04:22:44 wrote gpt_002.pth
20240814-04:22:57 wrote non_validated_0318_01.png
20240814-04:23:10 wrote non_validated_0318_02.png
20240814-04:23:10 wrote state.pth
20240814-04:23:10 --- epoch 319 ----------------------------------------
20240814-04:23:10 current_test_accuracies 0.9588 0.9373 0.9613 0.9559 0.9621
20240814-04:23:10 training model 1
20240814-04:23:10 training model 3
20240814-04:26:54 train_perplexity 319 model 1 1.1687662891377475
20240814-04:26:56 test_perplexity 319 model 1 1.1650322735660457
20240814-04:26:56 train_perplexity 319 model 3 1.1672259539073715
20240814-04:26:59 test_perplexity 319 model 3 1.1654238365781935
20240814-04:27:44 test_accuracy 319 model 3 val 765 / 810
20240814-04:27:45 test_accuracy 319 model 1 val 737 / 784
20240814-04:27:47 wrote gpt_001.pth
20240814-04:27:48 wrote gpt_003.pth
20240814-04:28:01 wrote non_validated_0319_01.png
20240814-04:28:14 wrote non_validated_0319_03.png
20240814-04:28:14 wrote state.pth
20240814-04:28:14 --- epoch 320 ----------------------------------------
20240814-04:28:14 current_test_accuracies 0.9588 0.9401 0.9613 0.9444 0.9621
20240814-04:28:14 training model 1
20240814-04:28:14 training model 3
20240814-04:31:58 train_perplexity 320 model 1 1.1680116163955996
20240814-04:32:00 test_perplexity 320 model 1 1.1669554410669782
20240814-04:32:01 train_perplexity 320 model 3 1.1670439782458677
20240814-04:32:03 test_perplexity 320 model 3 1.1683692122923006
20240814-04:32:45 test_accuracy 320 model 1 val 762 / 811
20240814-04:32:49 test_accuracy 320 model 3 val 765 / 799
20240814-04:32:51 wrote gpt_001.pth
20240814-04:32:52 wrote gpt_003.pth
20240814-04:33:05 wrote non_validated_0320_01.png
20240814-04:33:18 wrote non_validated_0320_03.png
20240814-04:33:18 wrote state.pth
20240814-04:33:18 --- epoch 321 ----------------------------------------
20240814-04:33:18 current_test_accuracies 0.9588 0.9396 0.9613 0.9574 0.9621
20240814-04:33:18 training model 1
20240814-04:33:18 training model 3
20240814-04:37:03 train_perplexity 321 model 1 1.1684409501248336
20240814-04:37:05 test_perplexity 321 model 1 1.1645876181590848
20240814-04:37:05 train_perplexity 321 model 3 1.167001140920619
20240814-04:37:08 test_perplexity 321 model 3 1.1675357333419534
20240814-04:37:50 test_accuracy 321 model 1 val 759 / 805
20240814-04:37:53 test_accuracy 321 model 3 val 749 / 787
20240814-04:37:55 wrote gpt_001.pth
20240814-04:37:56 wrote gpt_003.pth
20240814-04:38:09 wrote non_validated_0321_01.png
20240814-04:38:22 wrote non_validated_0321_03.png
20240814-04:38:22 wrote state.pth
20240814-04:38:22 --- epoch 322 ----------------------------------------
20240814-04:38:22 current_test_accuracies 0.9588 0.9429 0.9613 0.9517 0.9621
20240814-04:38:22 training model 1
20240814-04:38:22 training model 3
20240814-04:42:06 train_perplexity 322 model 1 1.1679162277757116
20240814-04:42:08 test_perplexity 322 model 1 1.1668120754687277
20240814-04:42:09 train_perplexity 322 model 3 1.1666049214323488
20240814-04:42:11 test_perplexity 322 model 3 1.1672257668508692
20240814-04:42:53 test_accuracy 322 model 1 val 766 / 802
20240814-04:42:57 test_accuracy 322 model 3 val 753 / 793
20240814-04:42:59 wrote gpt_001.pth
20240814-04:43:00 wrote gpt_003.pth
20240814-04:43:13 wrote non_validated_0322_01.png
20240814-04:43:26 wrote non_validated_0322_03.png
20240814-04:43:26 wrote state.pth
20240814-04:43:26 --- epoch 323 ----------------------------------------
20240814-04:43:26 current_test_accuracies 0.9588 0.9551 0.9613 0.9496 0.9621
20240814-04:43:26 training model 3
20240814-04:43:26 training model 1
20240814-04:47:11 train_perplexity 323 model 3 1.1665896907488857
20240814-04:47:13 test_perplexity 323 model 3 1.1678725828025456
20240814-04:47:13 train_perplexity 323 model 1 1.1682167647332722
20240814-04:47:15 test_perplexity 323 model 1 1.1671507288205023
20240814-04:47:58 test_accuracy 323 model 1 val 756 / 807
20240814-04:48:01 test_accuracy 323 model 3 val 752 / 788
20240814-04:48:03 wrote gpt_003.pth
20240814-04:48:04 wrote gpt_001.pth
20240814-04:48:17 wrote non_validated_0323_03.png
20240814-04:48:30 wrote non_validated_0323_01.png
20240814-04:48:30 wrote state.pth
20240814-04:48:30 --- epoch 324 ----------------------------------------
20240814-04:48:30 current_test_accuracies 0.9588 0.9368 0.9613 0.9543 0.9621
20240814-04:48:30 training model 1
20240814-04:48:30 training model 3
20240814-04:52:14 train_perplexity 324 model 1 1.1679228747216177
20240814-04:52:16 test_perplexity 324 model 1 1.1661114973887754
20240814-04:52:16 train_perplexity 324 model 3 1.166872008089191
20240814-04:52:19 test_perplexity 324 model 3 1.1696977006709572
20240814-04:53:04 test_accuracy 324 model 1 val 756 / 797
20240814-04:53:04 test_accuracy 324 model 3 val 788 / 826
20240814-04:53:06 wrote gpt_001.pth
20240814-04:53:07 wrote gpt_003.pth
20240814-04:53:20 wrote non_validated_0324_01.png
20240814-04:53:33 wrote non_validated_0324_03.png
20240814-04:53:33 wrote state.pth
20240814-04:53:33 --- epoch 325 ----------------------------------------
20240814-04:53:33 current_test_accuracies 0.9588 0.9486 0.9613 0.9540 0.9621
20240814-04:53:33 training model 1
20240814-04:53:33 training model 3
20240814-04:57:18 train_perplexity 325 model 1 1.1680051217681842
20240814-04:57:19 test_perplexity 325 model 1 1.165502021256859
20240814-04:57:20 train_perplexity 325 model 3 1.1666822483476598
20240814-04:57:22 test_perplexity 325 model 3 1.1657019168672036
20240814-04:58:04 test_accuracy 325 model 3 val 770 / 804
20240814-04:58:07 test_accuracy 325 model 1 val 761 / 791
20240814-04:58:09 wrote gpt_001.pth
20240814-04:58:10 wrote gpt_003.pth
20240814-04:58:23 wrote non_validated_0325_01.png
20240814-04:58:36 wrote non_validated_0325_03.png
20240814-04:58:36 wrote state.pth
20240814-04:58:36 --- epoch 326 ----------------------------------------
20240814-04:58:36 current_test_accuracies 0.9588 0.9621 0.9613 0.9577 0.9621
20240814-04:59:48 keep c_quizzes model 0 validated 24 / 410 (5.85%) nb_accumulated 24 / 410 (finishes Wed 05:19 -- 1202/h)
20240814-05:00:37 keep c_quizzes model 1 validated 23 / 410 (5.61%) nb_accumulated 47 / 410 (finishes Wed 05:16 -- 1402/h)
20240814-05:01:26 keep c_quizzes model 0 validated 26 / 410 (6.34%) nb_accumulated 73 / 410 (finishes Wed 05:14 -- 1550/h)
20240814-05:02:14 keep c_quizzes model 1 validated 30 / 410 (7.32%) nb_accumulated 103 / 410 (finishes Wed 05:13 -- 1698/h)
20240814-05:03:03 keep c_quizzes model 4 validated 24 / 410 (5.85%) nb_accumulated 127 / 410 (finishes Wed 05:12 -- 1710/h)
20240814-05:03:52 keep c_quizzes model 3 validated 26 / 410 (6.34%) nb_accumulated 153 / 410 (finishes Wed 05:12 -- 1741/h)
20240814-05:04:41 keep c_quizzes model 1 validated 24 / 410 (5.85%) nb_accumulated 177 / 410 (finishes Wed 05:12 -- 1745/h)
20240814-05:05:30 keep c_quizzes model 4 validated 28 / 410 (6.83%) nb_accumulated 205 / 410 (finishes Wed 05:12 -- 1782/h)
20240814-05:06:19 keep c_quizzes model 4 validated 22 / 410 (5.37%) nb_accumulated 227 / 410 (finishes Wed 05:12 -- 1765/h)
20240814-05:07:08 keep c_quizzes model 0 validated 32 / 410 (7.80%) nb_accumulated 259 / 410 (finishes Wed 05:12 -- 1821/h)
20240814-05:07:57 keep c_quizzes model 2 validated 21 / 410 (5.12%) nb_accumulated 280 / 410 (finishes Wed 05:12 -- 1797/h)
20240814-05:08:46 keep c_quizzes model 0 validated 21 / 410 (5.12%) nb_accumulated 301 / 410 (finishes Wed 05:12 -- 1777/h)
20240814-05:09:34 keep c_quizzes model 4 validated 20 / 410 (4.88%) nb_accumulated 321 / 410 (finishes Wed 05:12 -- 1755/h)
20240814-05:10:23 keep c_quizzes model 2 validated 26 / 410 (6.34%) nb_accumulated 347 / 410 (finishes Wed 05:12 -- 1766/h)
20240814-05:11:12 keep c_quizzes model 0 validated 24 / 410 (5.85%) nb_accumulated 371 / 410 (finishes Wed 05:12 -- 1766/h)
20240814-05:12:01 keep c_quizzes model 2 validated 17 / 410 (4.15%) nb_accumulated 388 / 410 (finishes Wed 05:12 -- 1735/h)
20240814-05:12:50 keep c_quizzes model 3 validated 21 / 410 (5.12%) nb_accumulated 409 / 410 (finishes Wed 05:12 -- 1724/h)
20240814-05:13:39 keep c_quizzes model 4 validated 26 / 410 (6.34%) nb_accumulated 435 / 410 (finishes now! -- 1734/h)
20240814-05:13:42 wrote c_quizzes.pth
20240814-05:13:42 training model 0
20240814-05:13:42 training model 1
20240814-05:17:26 train_perplexity 326 model 0 1.1686372574224915
20240814-05:17:28 train_perplexity 326 model 1 1.1696840466551246
20240814-05:17:28 test_perplexity 326 model 0 1.1666159191185692
20240814-05:17:30 test_perplexity 326 model 1 1.1672211998877606
20240814-05:18:13 test_accuracy 326 model 1 val 762 / 800
20240814-05:18:16 test_accuracy 326 model 0 val 735 / 794
20240814-05:18:18 wrote gpt_000.pth
20240814-05:18:19 wrote gpt_001.pth
20240814-05:18:31 wrote non_validated_0326_00.png
20240814-05:18:44 wrote non_validated_0326_01.png
20240814-05:18:45 wrote state.pth
20240814-05:18:45 --- epoch 327 ----------------------------------------
20240814-05:18:45 current_test_accuracies 0.9257 0.9525 0.0000 0.0000 0.0000
20240814-05:18:45 training model 2
20240814-05:18:45 training model 3
20240814-05:22:29 train_perplexity 327 model 2 1.167958692907395
20240814-05:22:31 test_perplexity 327 model 2 1.1676143193784354
20240814-05:22:31 train_perplexity 327 model 3 1.1679856983542727
20240814-05:22:33 test_perplexity 327 model 3 1.1653794121610999
20240814-05:23:16 test_accuracy 327 model 2 val 755 / 806
20240814-05:23:19 test_accuracy 327 model 3 val 735 / 777
20240814-05:23:21 wrote gpt_002.pth
20240814-05:23:22 wrote gpt_003.pth
20240814-05:23:35 wrote non_validated_0327_02.png
20240814-05:23:48 wrote non_validated_0327_03.png
20240814-05:23:48 wrote state.pth
20240814-05:23:48 --- epoch 328 ----------------------------------------
20240814-05:23:48 current_test_accuracies 0.9257 0.9525 0.9367 0.9459 0.0000
20240814-05:23:48 training model 4
20240814-05:23:48 training model 0
20240814-05:27:32 train_perplexity 328 model 4 1.1686097635642336
20240814-05:27:34 test_perplexity 328 model 4 1.167410248312201
20240814-05:27:35 train_perplexity 328 model 0 1.1681019736657507
20240814-05:27:37 test_perplexity 328 model 0 1.166574203208539
20240814-05:28:23 test_accuracy 328 model 4 val 749 / 792
20240814-05:28:25 test_accuracy 328 model 0 val 737 / 775
20240814-05:28:27 wrote gpt_004.pth
20240814-05:28:27 wrote gpt_000.pth
20240814-05:28:40 wrote non_validated_0328_04.png
20240814-05:28:53 wrote non_validated_0328_00.png
20240814-05:28:53 wrote state.pth
20240814-05:28:53 --- epoch 329 ----------------------------------------
20240814-05:28:53 current_test_accuracies 0.9510 0.9525 0.9367 0.9459 0.9457
20240814-05:28:53 training model 2
20240814-05:28:53 training model 4
20240814-05:32:39 train_perplexity 329 model 2 1.1679887055566998
20240814-05:32:40 train_perplexity 329 model 4 1.1686373718545873
20240814-05:32:41 test_perplexity 329 model 2 1.1682891405213467
20240814-05:32:43 test_perplexity 329 model 4 1.1683309930524186
20240814-05:33:26 test_accuracy 329 model 2 val 768 / 822
20240814-05:33:27 test_accuracy 329 model 4 val 770 / 812
20240814-05:33:29 wrote gpt_002.pth
20240814-05:33:30 wrote gpt_004.pth
20240814-05:33:43 wrote non_validated_0329_02.png
20240814-05:33:56 wrote non_validated_0329_04.png
20240814-05:33:56 wrote state.pth
20240814-05:33:56 --- epoch 330 ----------------------------------------
20240814-05:33:56 current_test_accuracies 0.9510 0.9525 0.9343 0.9459 0.9483
20240814-05:33:56 training model 2
20240814-05:33:56 training model 3
20240814-05:37:40 train_perplexity 330 model 2 1.1682452790624542
20240814-05:37:42 test_perplexity 330 model 2 1.1685269628538442
20240814-05:37:43 train_perplexity 330 model 3 1.168297896092456
20240814-05:37:45 test_perplexity 330 model 3 1.168184125829237
20240814-05:38:27 test_accuracy 330 model 2 val 763 / 800
20240814-05:38:29 test_accuracy 330 model 3 val 763 / 808
20240814-05:38:31 wrote gpt_002.pth
20240814-05:38:32 wrote gpt_003.pth
20240814-05:38:45 wrote non_validated_0330_02.png
20240814-05:38:58 wrote non_validated_0330_03.png
20240814-05:38:58 wrote state.pth
20240814-05:38:58 --- epoch 331 ----------------------------------------
20240814-05:38:58 current_test_accuracies 0.9510 0.9525 0.9538 0.9443 0.9483
20240814-05:38:58 training model 3
20240814-05:38:58 training model 4
20240814-05:42:42 train_perplexity 331 model 3 1.1682048585045743
20240814-05:42:44 train_perplexity 331 model 4 1.1683538131703073
20240814-05:42:44 test_perplexity 331 model 3 1.1710139236015142
20240814-05:42:46 test_perplexity 331 model 4 1.166708822984058
20240814-05:43:31 test_accuracy 331 model 4 val 765 / 801
20240814-05:43:32 test_accuracy 331 model 3 val 786 / 837
20240814-05:43:34 wrote gpt_003.pth
20240814-05:43:35 wrote gpt_004.pth
20240814-05:43:48 wrote non_validated_0331_03.png
20240814-05:44:01 wrote non_validated_0331_04.png
20240814-05:44:01 wrote state.pth
20240814-05:44:01 --- epoch 332 ----------------------------------------
20240814-05:44:01 current_test_accuracies 0.9510 0.9525 0.9538 0.9391 0.9551
20240814-05:44:01 training model 3
20240814-05:44:01 training model 0
20240814-05:47:47 train_perplexity 332 model 3 1.1682943238972145
20240814-05:47:47 train_perplexity 332 model 0 1.168634045649871
20240814-05:47:51 test_perplexity 332 model 3 1.1705145883883468
20240814-05:47:51 test_perplexity 332 model 0 1.1670369000305705
20240814-05:48:35 test_accuracy 332 model 3 val 755 / 803
20240814-05:48:38 test_accuracy 332 model 0 val 759 / 799
20240814-05:48:40 wrote gpt_003.pth
20240814-05:48:41 wrote gpt_000.pth
20240814-05:48:54 wrote non_validated_0332_03.png
20240814-05:49:07 wrote non_validated_0332_00.png
20240814-05:49:07 wrote state.pth
20240814-05:49:07 --- epoch 333 ----------------------------------------
20240814-05:49:07 current_test_accuracies 0.9499 0.9525 0.9538 0.9402 0.9551
20240814-05:49:07 training model 3
20240814-05:49:07 training model 0
20240814-05:52:52 train_perplexity 333 model 3 1.1679555771438646
20240814-05:52:53 train_perplexity 333 model 0 1.16853842660872
20240814-05:52:54 test_perplexity 333 model 3 1.1696205238236907
20240814-05:52:56 test_perplexity 333 model 0 1.1670345736582197
20240814-05:53:43 test_accuracy 333 model 0 val 725 / 777
20240814-05:53:43 test_accuracy 333 model 3 val 750 / 799
20240814-05:53:45 wrote gpt_003.pth
20240814-05:53:46 wrote gpt_000.pth
20240814-05:53:59 wrote non_validated_0333_03.png
20240814-05:54:12 wrote non_validated_0333_00.png
20240814-05:54:12 wrote state.pth
20240814-05:54:12 --- epoch 334 ----------------------------------------
20240814-05:54:12 current_test_accuracies 0.9331 0.9525 0.9538 0.9387 0.9551
20240814-05:54:12 training model 0
20240814-05:54:12 training model 3
20240814-05:57:57 train_perplexity 334 model 0 1.1679924805419186
20240814-05:57:59 test_perplexity 334 model 0 1.167930332774281
20240814-05:57:59 train_perplexity 334 model 3 1.1677664856145367
20240814-05:58:01 test_perplexity 334 model 3 1.1702068995973651
20240814-05:58:47 test_accuracy 334 model 0 val 725 / 771
20240814-05:58:49 test_accuracy 334 model 3 val 753 / 796
20240814-05:58:51 wrote gpt_000.pth
20240814-05:58:52 wrote gpt_003.pth
20240814-05:59:05 wrote non_validated_0334_00.png
20240814-05:59:18 wrote non_validated_0334_03.png
20240814-05:59:18 wrote state.pth
20240814-05:59:18 --- epoch 335 ----------------------------------------
20240814-05:59:18 current_test_accuracies 0.9403 0.9525 0.9538 0.9460 0.9551
20240814-05:59:18 training model 0
20240814-05:59:18 training model 3
20240814-06:03:03 train_perplexity 335 model 0 1.1682593436217625
20240814-06:03:04 train_perplexity 335 model 3 1.167950621999165
20240814-06:03:05 test_perplexity 335 model 0 1.1685366267805963
20240814-06:03:07 test_perplexity 335 model 3 1.1666451010207637
20240814-06:03:55 test_accuracy 335 model 0 val 743 / 787
20240814-06:03:56 test_accuracy 335 model 3 val 740 / 794
20240814-06:03:58 wrote gpt_000.pth
20240814-06:03:59 wrote gpt_003.pth
20240814-06:04:11 wrote non_validated_0335_00.png
20240814-06:04:24 wrote non_validated_0335_03.png
20240814-06:04:24 wrote state.pth
20240814-06:04:24 --- epoch 336 ----------------------------------------
20240814-06:04:24 current_test_accuracies 0.9441 0.9525 0.9538 0.9320 0.9551
20240814-06:04:24 training model 3
20240814-06:04:24 training model 0
20240814-06:08:09 train_perplexity 336 model 3 1.1680362329088907
20240814-06:08:11 train_perplexity 336 model 0 1.1685809760714656
20240814-06:08:11 test_perplexity 336 model 3 1.1679921384358618
20240814-06:08:14 test_perplexity 336 model 0 1.168523015902783
20240814-06:08:58 test_accuracy 336 model 0 val 779 / 817
20240814-06:08:59 test_accuracy 336 model 3 val 760 / 810
20240814-06:09:01 wrote gpt_003.pth
20240814-06:09:01 wrote gpt_000.pth
20240814-06:09:14 wrote non_validated_0336_03.png
20240814-06:09:27 wrote non_validated_0336_00.png
20240814-06:09:27 wrote state.pth
20240814-06:09:27 --- epoch 337 ----------------------------------------
20240814-06:09:27 current_test_accuracies 0.9535 0.9525 0.9538 0.9383 0.9551
20240814-06:09:27 training model 3
20240814-06:09:27 training model 1
20240814-06:13:12 train_perplexity 337 model 3 1.1674886014927504
20240814-06:13:14 train_perplexity 337 model 1 1.1692924515890661
20240814-06:13:14 test_perplexity 337 model 3 1.1678583945019823
20240814-06:13:17 test_perplexity 337 model 1 1.1681842759672088
20240814-06:14:04 test_accuracy 337 model 3 val 745 / 790
20240814-06:14:05 test_accuracy 337 model 1 val 756 / 796
20240814-06:14:07 wrote gpt_003.pth
20240814-06:14:08 wrote gpt_001.pth
20240814-06:14:21 wrote non_validated_0337_03.png
20240814-06:14:34 wrote non_validated_0337_01.png
20240814-06:14:34 wrote state.pth
20240814-06:14:34 --- epoch 338 ----------------------------------------
20240814-06:14:34 current_test_accuracies 0.9535 0.9497 0.9538 0.9430 0.9551
20240814-06:14:34 training model 3
20240814-06:14:34 training model 1
20240814-06:18:19 train_perplexity 338 model 3 1.1674203463927921
20240814-06:18:20 train_perplexity 338 model 1 1.1695239888112545
20240814-06:18:21 test_perplexity 338 model 3 1.1671988384193661
20240814-06:18:23 test_perplexity 338 model 1 1.1678384623452753
20240814-06:19:06 test_accuracy 338 model 3 val 765 / 811
20240814-06:19:08 test_accuracy 338 model 1 val 768 / 809
20240814-06:19:10 wrote gpt_003.pth
20240814-06:19:11 wrote gpt_001.pth
20240814-06:19:24 wrote non_validated_0338_03.png
20240814-06:19:37 wrote non_validated_0338_01.png
20240814-06:19:37 wrote state.pth
20240814-06:19:37 --- epoch 339 ----------------------------------------
20240814-06:19:37 current_test_accuracies 0.9535 0.9493 0.9538 0.9433 0.9551
20240814-06:19:37 training model 3
20240814-06:19:37 training model 1
20240814-06:23:21 train_perplexity 339 model 3 1.1674896929661422
20240814-06:23:23 test_perplexity 339 model 3 1.1683965294278411
20240814-06:23:24 train_perplexity 339 model 1 1.169303120109167
20240814-06:23:26 test_perplexity 339 model 1 1.1657697846524135
20240814-06:24:11 test_accuracy 339 model 3 val 734 / 778
20240814-06:24:13 test_accuracy 339 model 1 val 754 / 794
20240814-06:24:15 wrote gpt_003.pth
20240814-06:24:16 wrote gpt_001.pth
20240814-06:24:29 wrote non_validated_0339_03.png
20240814-06:24:42 wrote non_validated_0339_01.png
20240814-06:24:42 wrote state.pth
20240814-06:24:42 --- epoch 340 ----------------------------------------
20240814-06:24:42 current_test_accuracies 0.9535 0.9496 0.9538 0.9434 0.9551
20240814-06:24:42 training model 3
20240814-06:24:42 training model 1
20240814-06:28:28 train_perplexity 340 model 3 1.1675517701817542
20240814-06:28:28 train_perplexity 340 model 1 1.1692220244053126
20240814-06:28:31 test_perplexity 340 model 3 1.1670577284649222
20240814-06:28:31 test_perplexity 340 model 1 1.1689228731585832
20240814-06:29:15 test_accuracy 340 model 3 val 753 / 802
20240814-06:29:18 test_accuracy 340 model 1 val 746 / 784
20240814-06:29:20 wrote gpt_003.pth
20240814-06:29:21 wrote gpt_001.pth
20240814-06:29:34 wrote non_validated_0340_03.png
20240814-06:29:47 wrote non_validated_0340_01.png
20240814-06:29:47 wrote state.pth
20240814-06:29:47 --- epoch 341 ----------------------------------------
20240814-06:29:47 current_test_accuracies 0.9535 0.9515 0.9538 0.9389 0.9551
20240814-06:29:47 training model 3
20240814-06:29:47 training model 1
20240814-06:33:32 train_perplexity 341 model 3 1.1672357073570239
20240814-06:33:34 test_perplexity 341 model 3 1.1677340167064265
20240814-06:33:34 train_perplexity 341 model 1 1.1693204386550813
20240814-06:33:36 test_perplexity 341 model 1 1.167648053546931
20240814-06:34:19 test_accuracy 341 model 3 val 776 / 812
20240814-06:34:20 test_accuracy 341 model 1 val 767 / 822
20240814-06:34:22 wrote gpt_003.pth
20240814-06:34:23 wrote gpt_001.pth
20240814-06:34:36 wrote non_validated_0341_03.png
20240814-06:34:49 wrote non_validated_0341_01.png
20240814-06:34:49 wrote state.pth
20240814-06:34:49 --- epoch 342 ----------------------------------------
20240814-06:34:49 current_test_accuracies 0.9535 0.9331 0.9538 0.9557 0.9551
20240814-06:34:49 training model 1
20240814-06:34:49 training model 0
20240814-06:38:34 train_perplexity 342 model 1 1.1687156490754098
20240814-06:38:36 test_perplexity 342 model 1 1.1703433145507756
20240814-06:38:36 train_perplexity 342 model 0 1.1679282661300834
20240814-06:38:38 test_perplexity 342 model 0 1.1692867908501987
20240814-06:39:25 test_accuracy 342 model 0 val 744 / 792
20240814-06:39:25 test_accuracy 342 model 1 val 750 / 795
20240814-06:39:27 wrote gpt_001.pth
20240814-06:39:28 wrote gpt_000.pth
20240814-06:39:41 wrote non_validated_0342_01.png
20240814-06:39:54 wrote non_validated_0342_00.png
20240814-06:39:54 wrote state.pth
20240814-06:39:54 --- epoch 343 ----------------------------------------
20240814-06:39:54 current_test_accuracies 0.9394 0.9434 0.9538 0.9557 0.9551
20240814-06:39:54 training model 0
20240814-06:39:54 training model 1
20240814-06:43:39 train_perplexity 343 model 0 1.1685263715013896
20240814-06:43:41 train_perplexity 343 model 1 1.1688380944906285
20240814-06:43:41 test_perplexity 343 model 0 1.1667583626251332
20240814-06:43:43 test_perplexity 343 model 1 1.1688037615145805
20240814-06:44:27 test_accuracy 343 model 1 val 761 / 802
20240814-06:44:28 test_accuracy 343 model 0 val 760 / 813
20240814-06:44:30 wrote gpt_000.pth
20240814-06:44:31 wrote gpt_001.pth
20240814-06:44:44 wrote non_validated_0343_00.png
20240814-06:44:57 wrote non_validated_0343_01.png
20240814-06:44:57 wrote state.pth
20240814-06:44:57 --- epoch 344 ----------------------------------------
20240814-06:44:57 current_test_accuracies 0.9348 0.9489 0.9538 0.9557 0.9551
20240814-06:44:57 training model 0
20240814-06:44:57 training model 1
20240814-06:48:42 train_perplexity 344 model 0 1.1683198109262107
20240814-06:48:44 train_perplexity 344 model 1 1.1690577606440526
20240814-06:48:44 test_perplexity 344 model 0 1.1681026089822508
20240814-06:48:46 test_perplexity 344 model 1 1.1689664267076696
20240814-06:49:32 test_accuracy 344 model 0 val 770 / 817
20240814-06:49:34 test_accuracy 344 model 1 val 749 / 789
20240814-06:49:36 wrote gpt_000.pth
20240814-06:49:36 wrote gpt_001.pth
20240814-06:49:49 wrote non_validated_0344_00.png
20240814-06:50:02 wrote non_validated_0344_01.png
20240814-06:50:02 wrote state.pth
20240814-06:50:02 --- epoch 345 ----------------------------------------
20240814-06:50:02 current_test_accuracies 0.9425 0.9493 0.9538 0.9557 0.9551
20240814-06:50:02 training model 0
20240814-06:50:02 training model 1
20240814-06:53:47 train_perplexity 345 model 0 1.1681753393154732
20240814-06:53:49 test_perplexity 345 model 0 1.1684196033097074
20240814-06:53:49 train_perplexity 345 model 1 1.168678771284748
20240814-06:53:51 test_perplexity 345 model 1 1.1670754130139522
20240814-06:54:38 test_accuracy 345 model 1 val 739 / 791
20240814-06:54:40 test_accuracy 345 model 0 val 749 / 788
20240814-06:54:42 wrote gpt_000.pth
20240814-06:54:42 wrote gpt_001.pth
20240814-06:54:55 wrote non_validated_0345_00.png
20240814-06:55:08 wrote non_validated_0345_01.png
20240814-06:55:08 wrote state.pth
20240814-06:55:08 --- epoch 346 ----------------------------------------
20240814-06:55:08 current_test_accuracies 0.9505 0.9343 0.9538 0.9557 0.9551
20240814-06:55:08 training model 1
20240814-06:55:08 training model 0
20240814-06:58:53 train_perplexity 346 model 1 1.1686831539125442
20240814-06:58:55 test_perplexity 346 model 1 1.1681163302798563
20240814-06:58:55 train_perplexity 346 model 0 1.1682255604801777
20240814-06:58:57 test_perplexity 346 model 0 1.1676820127126921
20240814-06:59:40 test_accuracy 346 model 1 val 769 / 814
20240814-06:59:41 test_accuracy 346 model 0 val 760 / 807
20240814-06:59:43 wrote gpt_001.pth
20240814-06:59:44 wrote gpt_000.pth
20240814-06:59:57 wrote non_validated_0346_01.png
20240814-07:00:10 wrote non_validated_0346_00.png
20240814-07:00:10 wrote state.pth
20240814-07:00:10 --- epoch 347 ----------------------------------------
20240814-07:00:10 current_test_accuracies 0.9418 0.9447 0.9538 0.9557 0.9551
20240814-07:00:10 training model 0
20240814-07:00:10 training model 1
20240814-07:03:54 train_perplexity 347 model 0 1.1682137821468106
20240814-07:03:55 test_perplexity 347 model 0 1.168945384796811
20240814-07:03:57 train_perplexity 347 model 1 1.1689454496867036
20240814-07:03:59 test_perplexity 347 model 1 1.1691116118439244
20240814-07:04:40 test_accuracy 347 model 0 val 761 / 802
20240814-07:04:42 test_accuracy 347 model 1 val 754 / 800
20240814-07:04:44 wrote gpt_000.pth
20240814-07:04:45 wrote gpt_001.pth
20240814-07:04:58 wrote non_validated_0347_00.png
20240814-07:05:11 wrote non_validated_0347_01.png
20240814-07:05:11 wrote state.pth
20240814-07:05:11 --- epoch 348 ----------------------------------------
20240814-07:05:11 current_test_accuracies 0.9489 0.9425 0.9538 0.9557 0.9551
20240814-07:05:11 training model 1
20240814-07:05:11 training model 0
20240814-07:08:55 train_perplexity 348 model 1 1.169093703194346
20240814-07:08:57 test_perplexity 348 model 1 1.169434035002868
20240814-07:08:58 train_perplexity 348 model 0 1.167835857567301
20240814-07:09:00 test_perplexity 348 model 0 1.168383938247381
20240814-07:09:44 test_accuracy 348 model 1 val 744 / 799
20240814-07:09:46 test_accuracy 348 model 0 val 745 / 784
20240814-07:09:48 wrote gpt_001.pth
20240814-07:09:48 wrote gpt_000.pth
20240814-07:10:01 wrote non_validated_0348_01.png
20240814-07:10:14 wrote non_validated_0348_00.png
20240814-07:10:14 wrote state.pth
20240814-07:10:14 --- epoch 349 ----------------------------------------
20240814-07:10:14 current_test_accuracies 0.9503 0.9312 0.9538 0.9557 0.9551
20240814-07:10:14 training model 1
20240814-07:10:14 training model 0
20240814-07:13:58 train_perplexity 349 model 1 1.1688517601036503
20240814-07:14:00 test_perplexity 349 model 1 1.166882624764893
20240814-07:14:01 train_perplexity 349 model 0 1.1681226701246956
20240814-07:14:04 test_perplexity 349 model 0 1.1688452314513456
20240814-07:14:45 test_accuracy 349 model 1 val 771 / 811
20240814-07:14:47 test_accuracy 349 model 0 val 756 / 801
20240814-07:14:49 wrote gpt_001.pth
20240814-07:14:50 wrote gpt_000.pth
20240814-07:15:03 wrote non_validated_0349_01.png
20240814-07:15:16 wrote non_validated_0349_00.png
20240814-07:15:16 wrote state.pth
20240814-07:15:16 --- epoch 350 ----------------------------------------
20240814-07:15:16 current_test_accuracies 0.9438 0.9507 0.9538 0.9557 0.9551
20240814-07:15:16 training model 0
20240814-07:15:16 training model 1
20240814-07:19:00 train_perplexity 350 model 0 1.1680064454293155
20240814-07:19:02 test_perplexity 350 model 0 1.1681442881618334
20240814-07:19:03 train_perplexity 350 model 1 1.1690343886302208
20240814-07:19:05 test_perplexity 350 model 1 1.1652428721441253
20240814-07:19:48 test_accuracy 350 model 1 val 767 / 807
20240814-07:19:49 test_accuracy 350 model 0 val 755 / 817
20240814-07:19:51 wrote gpt_000.pth
20240814-07:19:51 wrote gpt_001.pth
20240814-07:20:04 wrote non_validated_0350_00.png
20240814-07:20:17 wrote non_validated_0350_01.png
20240814-07:20:17 wrote state.pth
20240814-07:20:17 --- epoch 351 ----------------------------------------
20240814-07:20:17 current_test_accuracies 0.9241 0.9504 0.9538 0.9557 0.9551
20240814-07:20:17 training model 0
20240814-07:20:17 training model 1
20240814-07:24:02 train_perplexity 351 model 0 1.167650073837152
20240814-07:24:04 test_perplexity 351 model 0 1.168529838081357
20240814-07:24:04 train_perplexity 351 model 1 1.169290256822011
20240814-07:24:07 test_perplexity 351 model 1 1.1700109653675483
20240814-07:24:50 test_accuracy 351 model 1 val 762 / 804
20240814-07:24:51 test_accuracy 351 model 0 val 757 / 795
20240814-07:24:53 wrote gpt_000.pth
20240814-07:24:54 wrote gpt_001.pth
20240814-07:25:07 wrote non_validated_0351_00.png
20240814-07:25:20 wrote non_validated_0351_01.png
20240814-07:25:20 wrote state.pth
20240814-07:25:20 --- epoch 352 ----------------------------------------
20240814-07:25:20 current_test_accuracies 0.9522 0.9478 0.9538 0.9557 0.9551
20240814-07:25:20 training model 1
20240814-07:25:20 training model 0
20240814-07:29:04 train_perplexity 352 model 1 1.1693739279320203
20240814-07:29:06 test_perplexity 352 model 1 1.1672251550515758
20240814-07:29:07 train_perplexity 352 model 0 1.1681037937987577
20240814-07:29:09 test_perplexity 352 model 0 1.1695108893428672
20240814-07:29:54 test_accuracy 352 model 1 val 752 / 797
20240814-07:29:56 test_accuracy 352 model 0 val 727 / 784
20240814-07:29:58 wrote gpt_001.pth
20240814-07:29:59 wrote gpt_000.pth
20240814-07:30:12 wrote non_validated_0352_01.png
20240814-07:30:25 wrote non_validated_0352_00.png
20240814-07:30:25 wrote state.pth
20240814-07:30:25 --- epoch 353 ----------------------------------------
20240814-07:30:25 current_test_accuracies 0.9273 0.9435 0.9538 0.9557 0.9551
20240814-07:30:25 training model 0
20240814-07:30:25 training model 1
20240814-07:34:09 train_perplexity 353 model 0 1.1680570170576328
20240814-07:34:11 test_perplexity 353 model 0 1.1684591831012883
20240814-07:34:12 train_perplexity 353 model 1 1.1689644784533695
20240814-07:34:14 test_perplexity 353 model 1 1.168713990570737
20240814-07:35:00 test_accuracy 353 model 0 val 738 / 780
20240814-07:35:02 test_accuracy 353 model 1 val 747 / 788
20240814-07:35:04 wrote gpt_000.pth
20240814-07:35:05 wrote gpt_001.pth
20240814-07:35:18 wrote non_validated_0353_00.png
20240814-07:35:31 wrote non_validated_0353_01.png
20240814-07:35:31 wrote state.pth
20240814-07:35:31 --- epoch 354 ----------------------------------------
20240814-07:35:31 current_test_accuracies 0.9462 0.9480 0.9538 0.9557 0.9551
20240814-07:35:31 training model 0
20240814-07:35:31 training model 1
20240814-07:39:15 train_perplexity 354 model 0 1.1675937444402378
20240814-07:39:16 test_perplexity 354 model 0 1.1693072469248622
20240814-07:39:18 train_perplexity 354 model 1 1.1685622757140282
20240814-07:39:20 test_perplexity 354 model 1 1.1676193076276842
20240814-07:40:00 test_accuracy 354 model 0 val 759 / 813
20240814-07:40:04 test_accuracy 354 model 1 val 745 / 798
20240814-07:40:06 wrote gpt_000.pth
20240814-07:40:06 wrote gpt_001.pth
20240814-07:40:19 wrote non_validated_0354_00.png
20240814-07:40:32 wrote non_validated_0354_01.png
20240814-07:40:32 wrote state.pth
20240814-07:40:32 --- epoch 355 ----------------------------------------
20240814-07:40:32 current_test_accuracies 0.9336 0.9336 0.9538 0.9557 0.9551
20240814-07:40:32 training model 0
20240814-07:40:32 training model 1
20240814-07:44:17 train_perplexity 355 model 0 1.1677043818065886
20240814-07:44:19 test_perplexity 355 model 0 1.170785642260894
20240814-07:44:19 train_perplexity 355 model 1 1.1687726146641508
20240814-07:44:21 test_perplexity 355 model 1 1.1647642261335214
20240814-07:45:05 test_accuracy 355 model 0 val 779 / 823
20240814-07:45:08 test_accuracy 355 model 1 val 731 / 776
20240814-07:45:10 wrote gpt_000.pth
20240814-07:45:11 wrote gpt_001.pth
20240814-07:45:24 wrote non_validated_0355_00.png
20240814-07:45:37 wrote non_validated_0355_01.png
20240814-07:45:37 wrote state.pth
20240814-07:45:37 --- epoch 356 ----------------------------------------
20240814-07:45:37 current_test_accuracies 0.9465 0.9420 0.9538 0.9557 0.9551
20240814-07:45:37 training model 1
20240814-07:45:37 training model 0
20240814-07:49:21 train_perplexity 356 model 1 1.1685663887489808
20240814-07:49:23 test_perplexity 356 model 1 1.1672446136439136
20240814-07:49:23 train_perplexity 356 model 0 1.1684326474952198
20240814-07:49:26 test_perplexity 356 model 0 1.1684604702396413
20240814-07:50:09 test_accuracy 356 model 1 val 777 / 818
20240814-07:50:12 test_accuracy 356 model 0 val 725 / 788
20240814-07:50:14 wrote gpt_001.pth
20240814-07:50:15 wrote gpt_000.pth
20240814-07:50:28 wrote non_validated_0356_01.png
20240814-07:50:41 wrote non_validated_0356_00.png
20240814-07:50:41 wrote state.pth
20240814-07:50:41 --- epoch 357 ----------------------------------------
20240814-07:50:41 current_test_accuracies 0.9201 0.9499 0.9538 0.9557 0.9551
20240814-07:50:41 training model 0
20240814-07:50:41 training model 1
20240814-07:54:25 train_perplexity 357 model 0 1.1682228980619265
20240814-07:54:27 test_perplexity 357 model 0 1.169011457321116
20240814-07:54:28 train_perplexity 357 model 1 1.1685470774877287
20240814-07:54:30 test_perplexity 357 model 1 1.1660672543992272
20240814-07:55:17 test_accuracy 357 model 1 val 738 / 772
20240814-07:55:17 test_accuracy 357 model 0 val 751 / 799
20240814-07:55:19 wrote gpt_000.pth
20240814-07:55:20 wrote gpt_001.pth
20240814-07:55:33 wrote non_validated_0357_00.png
20240814-07:55:46 wrote non_validated_0357_01.png
20240814-07:55:46 wrote state.pth
20240814-07:55:46 --- epoch 358 ----------------------------------------
20240814-07:55:46 current_test_accuracies 0.9399 0.9560 0.9538 0.9557 0.9551
20240814-07:55:46 training model 0
20240814-07:55:46 training model 2
20240814-07:59:30 train_perplexity 358 model 0 1.1675908454944601
20240814-07:59:32 test_perplexity 358 model 0 1.1686482004260035
20240814-07:59:33 train_perplexity 358 model 2 1.1679233351288412
20240814-07:59:35 test_perplexity 358 model 2 1.1656369815008756
20240814-08:00:21 test_accuracy 358 model 0 val 742 / 791
20240814-08:00:22 test_accuracy 358 model 2 val 719 / 769
20240814-08:00:24 wrote gpt_000.pth
20240814-08:00:25 wrote gpt_002.pth
20240814-08:00:38 wrote non_validated_0358_00.png
20240814-08:00:51 wrote non_validated_0358_02.png
20240814-08:00:51 wrote state.pth
20240814-08:00:51 --- epoch 359 ----------------------------------------
20240814-08:00:51 current_test_accuracies 0.9381 0.9560 0.9350 0.9557 0.9551
20240814-08:00:51 training model 2
20240814-08:00:51 training model 0
20240814-08:04:35 train_perplexity 359 model 2 1.1676464262665482
20240814-08:04:37 train_perplexity 359 model 0 1.1678922984887126
20240814-08:04:37 test_perplexity 359 model 2 1.1677192075908018
20240814-08:04:39 test_perplexity 359 model 0 1.1666912926321322
20240814-08:05:21 test_accuracy 359 model 2 val 745 / 804
20240814-08:05:24 test_accuracy 359 model 0 val 772 / 811
20240814-08:05:26 wrote gpt_002.pth
20240814-08:05:26 wrote gpt_000.pth
20240814-08:05:39 wrote non_validated_0359_02.png
20240814-08:05:52 wrote non_validated_0359_00.png
20240814-08:05:52 wrote state.pth
20240814-08:05:52 --- epoch 360 ----------------------------------------
20240814-08:05:52 current_test_accuracies 0.9519 0.9560 0.9266 0.9557 0.9551
20240814-08:05:52 training model 2
20240814-08:05:52 training model 0
20240814-08:09:37 train_perplexity 360 model 2 1.1680858274173247
20240814-08:09:39 test_perplexity 360 model 2 1.168232901666805
20240814-08:09:39 train_perplexity 360 model 0 1.1677083806455009
20240814-08:09:41 test_perplexity 360 model 0 1.1693194594953098
20240814-08:10:27 test_accuracy 360 model 0 val 755 / 798
20240814-08:10:28 test_accuracy 360 model 2 val 752 / 797
20240814-08:10:30 wrote gpt_002.pth
20240814-08:10:31 wrote gpt_000.pth
20240814-08:10:44 wrote non_validated_0360_02.png
20240814-08:10:57 wrote non_validated_0360_00.png
20240814-08:10:57 wrote state.pth
20240814-08:10:57 --- epoch 361 ----------------------------------------
20240814-08:10:57 current_test_accuracies 0.9461 0.9560 0.9435 0.9557 0.9551
20240814-08:10:57 training model 2
20240814-08:10:57 training model 0
20240814-08:14:42 train_perplexity 361 model 2 1.1676695959261023
20240814-08:14:44 train_perplexity 361 model 0 1.167857077920658
20240814-08:14:44 test_perplexity 361 model 2 1.166259456091447
20240814-08:14:46 test_perplexity 361 model 0 1.1677253695138443
20240814-08:15:31 test_accuracy 361 model 0 val 762 / 805
20240814-08:15:32 test_accuracy 361 model 2 val 736 / 789
20240814-08:15:34 wrote gpt_002.pth
20240814-08:15:35 wrote gpt_000.pth
20240814-08:15:48 wrote non_validated_0361_02.png
20240814-08:16:01 wrote non_validated_0361_00.png
20240814-08:16:01 wrote state.pth
20240814-08:16:01 --- epoch 362 ----------------------------------------
20240814-08:16:01 current_test_accuracies 0.9466 0.9560 0.9328 0.9557 0.9551
20240814-08:16:01 training model 2
20240814-08:16:01 training model 0
20240814-08:19:45 train_perplexity 362 model 2 1.1678237610478042
20240814-08:19:47 test_perplexity 362 model 2 1.1665803630007876
20240814-08:19:47 train_perplexity 362 model 0 1.1671976714405017
20240814-08:19:50 test_perplexity 362 model 0 1.1670234240037927
20240814-08:20:32 test_accuracy 362 model 2 val 785 / 815
20240814-08:20:35 test_accuracy 362 model 0 val 753 / 789
20240814-08:20:37 wrote gpt_002.pth
20240814-08:20:38 wrote gpt_000.pth
20240814-08:20:50 wrote non_validated_0362_02.png
20240814-08:21:03 wrote non_validated_0362_00.png
20240814-08:21:04 wrote state.pth
20240814-08:21:04 --- epoch 363 ----------------------------------------
20240814-08:21:04 current_test_accuracies 0.9544 0.9560 0.9632 0.9557 0.9551
20240814-08:22:15 keep c_quizzes model 1 validated 9 / 410 (2.20%) nb_accumulated 9 / 410 (finishes Wed 09:15 -- 450/h)
20240814-08:23:04 keep c_quizzes model 3 validated 8 / 410 (1.95%) nb_accumulated 17 / 410 (finishes Wed 09:09 -- 507/h)
20240814-08:23:53 keep c_quizzes model 0 validated 13 / 410 (3.17%) nb_accumulated 30 / 410 (finishes Wed 08:59 -- 638/h)
20240814-08:24:41 keep c_quizzes model 4 validated 17 / 410 (4.15%) nb_accumulated 47 / 410 (finishes Wed 08:52 -- 777/h)
20240814-08:25:30 keep c_quizzes model 4 validated 9 / 410 (2.20%) nb_accumulated 56 / 410 (finishes Wed 08:53 -- 756/h)
20240814-08:26:19 keep c_quizzes model 2 validated 13 / 410 (3.17%) nb_accumulated 69 / 410 (finishes Wed 08:52 -- 788/h)
20240814-08:27:07 keep c_quizzes model 4 validated 11 / 410 (2.68%) nb_accumulated 80 / 410 (finishes Wed 08:52 -- 791/h)
20240814-08:27:56 keep c_quizzes model 4 validated 12 / 410 (2.93%) nb_accumulated 92 / 410 (finishes Wed 08:51 -- 802/h)
20240814-08:28:45 keep c_quizzes model 3 validated 12 / 410 (2.93%) nb_accumulated 104 / 410 (finishes Wed 08:51 -- 811/h)
20240814-08:29:34 keep c_quizzes model 0 validated 12 / 410 (2.93%) nb_accumulated 116 / 410 (finishes Wed 08:51 -- 818/h)
20240814-08:30:22 keep c_quizzes model 2 validated 15 / 410 (3.66%) nb_accumulated 131 / 410 (finishes Wed 08:50 -- 843/h)
20240814-08:31:11 keep c_quizzes model 1 validated 16 / 410 (3.90%) nb_accumulated 147 / 410 (finishes Wed 08:49 -- 871/h)
20240814-08:31:59 keep c_quizzes model 0 validated 22 / 410 (5.37%) nb_accumulated 169 / 410 (finishes Wed 08:47 -- 927/h)
20240814-08:32:48 keep c_quizzes model 4 validated 8 / 410 (1.95%) nb_accumulated 177 / 410 (finishes Wed 08:48 -- 904/h)
20240814-08:33:37 keep c_quizzes model 3 validated 10 / 410 (2.44%) nb_accumulated 187 / 410 (finishes Wed 08:48 -- 893/h)
20240814-08:34:26 keep c_quizzes model 3 validated 15 / 410 (3.66%) nb_accumulated 202 / 410 (finishes Wed 08:48 -- 906/h)
20240814-08:35:15 keep c_quizzes model 0 validated 12 / 410 (2.93%) nb_accumulated 214 / 410 (finishes Wed 08:48 -- 904/h)
20240814-08:36:04 keep c_quizzes model 4 validated 21 / 410 (5.12%) nb_accumulated 235 / 410 (finishes Wed 08:47 -- 939/h)
20240814-08:36:53 keep c_quizzes model 2 validated 17 / 410 (4.15%) nb_accumulated 252 / 410 (finishes Wed 08:46 -- 955/h)
20240814-08:37:41 keep c_quizzes model 0 validated 15 / 410 (3.66%) nb_accumulated 267 / 410 (finishes Wed 08:46 -- 963/h)
20240814-08:38:30 keep c_quizzes model 2 validated 9 / 410 (2.20%) nb_accumulated 276 / 410 (finishes Wed 08:46 -- 949/h)
20240814-08:39:19 keep c_quizzes model 4 validated 12 / 410 (2.93%) nb_accumulated 288 / 410 (finishes Wed 08:47 -- 946/h)
20240814-08:40:08 keep c_quizzes model 0 validated 20 / 410 (4.88%) nb_accumulated 308 / 410 (finishes Wed 08:46 -- 968/h)
20240814-08:40:57 keep c_quizzes model 2 validated 16 / 410 (3.90%) nb_accumulated 324 / 410 (finishes Wed 08:46 -- 977/h)
20240814-08:41:45 keep c_quizzes model 3 validated 21 / 410 (5.12%) nb_accumulated 345 / 410 (finishes Wed 08:45 -- 1000/h)
20240814-08:42:34 keep c_quizzes model 2 validated 14 / 410 (3.41%) nb_accumulated 359 / 410 (finishes Wed 08:45 -- 1001/h)
20240814-08:43:23 keep c_quizzes model 2 validated 10 / 410 (2.44%) nb_accumulated 369 / 410 (finishes Wed 08:45 -- 991/h)
20240814-08:44:12 keep c_quizzes model 1 validated 17 / 410 (4.15%) nb_accumulated 386 / 410 (finishes Wed 08:45 -- 1000/h)
20240814-08:45:01 keep c_quizzes model 3 validated 9 / 410 (2.20%) nb_accumulated 395 / 410 (finishes Wed 08:45 -- 989/h)
20240814-08:45:49 keep c_quizzes model 4 validated 13 / 410 (3.17%) nb_accumulated 408 / 410 (finishes Wed 08:45 -- 988/h)
20240814-08:46:38 keep c_quizzes model 2 validated 17 / 410 (4.15%) nb_accumulated 425 / 410 (finishes now! -- 997/h)
20240814-08:46:42 wrote c_quizzes.pth
20240814-08:46:42 training model 0
20240814-08:46:42 training model 1
20240814-08:50:25 train_perplexity 363 model 0 1.1695292446358152
20240814-08:50:27 test_perplexity 363 model 0 1.170258148924614
20240814-08:50:27 train_perplexity 363 model 1 1.169603257197966
20240814-08:50:29 test_perplexity 363 model 1 1.168941931120352
20240814-08:51:15 test_accuracy 363 model 0 val 746 / 783
20240814-08:51:16 test_accuracy 363 model 1 val 746 / 797
20240814-08:51:18 wrote gpt_000.pth
20240814-08:51:19 wrote gpt_001.pth
20240814-08:51:32 wrote non_validated_0363_00.png
20240814-08:51:45 wrote non_validated_0363_01.png
20240814-08:51:45 wrote state.pth
20240814-08:51:45 --- epoch 364 ----------------------------------------
20240814-08:51:45 current_test_accuracies 0.9527 0.9360 0.0000 0.0000 0.0000
20240814-08:51:45 training model 2
20240814-08:51:45 training model 3
20240814-08:55:30 train_perplexity 364 model 2 1.1691603935508128
20240814-08:55:31 train_perplexity 364 model 3 1.1684396803320356
20240814-08:55:33 test_perplexity 364 model 2 1.1704662339848064
20240814-08:55:34 test_perplexity 364 model 3 1.1708726084576064
20240814-08:56:22 test_accuracy 364 model 2 val 755 / 799
20240814-08:56:23 test_accuracy 364 model 3 val 754 / 795
20240814-08:56:25 wrote gpt_002.pth
20240814-08:56:26 wrote gpt_003.pth
20240814-08:56:39 wrote non_validated_0364_02.png
20240814-08:56:52 wrote non_validated_0364_03.png
20240814-08:56:52 wrote state.pth
20240814-08:56:52 --- epoch 365 ----------------------------------------
20240814-08:56:52 current_test_accuracies 0.9527 0.9360 0.9449 0.9484 0.0000
20240814-08:56:52 training model 4
20240814-08:56:52 training model 1
20240814-09:00:36 train_perplexity 365 model 4 1.1700240733466103
20240814-09:00:38 test_perplexity 365 model 4 1.170667295878414
20240814-09:00:38 train_perplexity 365 model 1 1.169496687624834
20240814-09:00:40 test_perplexity 365 model 1 1.169818266569701
20240814-09:01:27 test_accuracy 365 model 1 val 751 / 792
20240814-09:01:28 test_accuracy 365 model 4 val 747 / 788
20240814-09:01:30 wrote gpt_004.pth
20240814-09:01:30 wrote gpt_001.pth
20240814-09:01:43 wrote non_validated_0365_04.png
20240814-09:01:56 wrote non_validated_0365_01.png
20240814-09:01:57 wrote state.pth
20240814-09:01:57 --- epoch 366 ----------------------------------------
20240814-09:01:57 current_test_accuracies 0.9527 0.9482 0.9449 0.9484 0.9480
20240814-09:01:57 training model 2
20240814-09:01:57 training model 4
20240814-09:05:41 train_perplexity 366 model 2 1.1695165352153456
20240814-09:05:43 test_perplexity 366 model 2 1.169616465121298
20240814-09:05:43 train_perplexity 366 model 4 1.1701971097027604
20240814-09:05:45 test_perplexity 366 model 4 1.169619304250767
20240814-09:06:29 test_accuracy 366 model 4 val 757 / 803
20240814-09:06:30 test_accuracy 366 model 2 val 735 / 782
20240814-09:06:32 wrote gpt_002.pth
20240814-09:06:33 wrote gpt_004.pth
20240814-09:06:46 wrote non_validated_0366_02.png
20240814-09:06:59 wrote non_validated_0366_04.png
20240814-09:06:59 wrote state.pth
20240814-09:06:59 --- epoch 367 ----------------------------------------
20240814-09:06:59 current_test_accuracies 0.9527 0.9482 0.9399 0.9484 0.9427
20240814-09:06:59 training model 2
20240814-09:06:59 training model 4
20240814-09:10:44 train_perplexity 367 model 2 1.1691324982010685
20240814-09:10:46 train_perplexity 367 model 4 1.1694149895367265
20240814-09:10:47 test_perplexity 367 model 2 1.1698620796648649
20240814-09:10:48 test_perplexity 367 model 4 1.1704821013205133
20240814-09:11:35 test_accuracy 367 model 4 val 761 / 799
20240814-09:11:36 test_accuracy 367 model 2 val 751 / 797
20240814-09:11:38 wrote gpt_002.pth
20240814-09:11:39 wrote gpt_004.pth
20240814-09:11:52 wrote non_validated_0367_02.png
20240814-09:12:05 wrote non_validated_0367_04.png
20240814-09:12:05 wrote state.pth
20240814-09:12:05 --- epoch 368 ----------------------------------------
20240814-09:12:05 current_test_accuracies 0.9527 0.9482 0.9423 0.9484 0.9524
20240814-09:12:05 training model 2
20240814-09:12:05 training model 1
20240814-09:15:51 train_perplexity 368 model 2 1.1691272196062525
20240814-09:15:51 train_perplexity 368 model 1 1.1697473499120545
20240814-09:15:54 test_perplexity 368 model 2 1.1691811024037797
20240814-09:15:55 test_perplexity 368 model 1 1.1699778184521503
20240814-09:16:40 test_accuracy 368 model 2 val 748 / 790
20240814-09:16:43 test_accuracy 368 model 1 val 737 / 782
20240814-09:16:45 wrote gpt_002.pth
20240814-09:16:46 wrote gpt_001.pth
20240814-09:16:59 wrote non_validated_0368_02.png
20240814-09:17:12 wrote non_validated_0368_01.png
20240814-09:17:12 wrote state.pth
20240814-09:17:12 --- epoch 369 ----------------------------------------
20240814-09:17:12 current_test_accuracies 0.9527 0.9425 0.9468 0.9484 0.9524
20240814-09:17:12 training model 1
20240814-09:17:12 training model 2
20240814-09:20:56 train_perplexity 369 model 1 1.169764134332552
20240814-09:20:58 test_perplexity 369 model 1 1.167482690018044
20240814-09:20:59 train_perplexity 369 model 2 1.1690711738542436
20240814-09:21:01 test_perplexity 369 model 2 1.1691195554663683
20240814-09:21:47 test_accuracy 369 model 1 val 730 / 784
20240814-09:21:48 test_accuracy 369 model 2 val 755 / 799
20240814-09:21:50 wrote gpt_001.pth
20240814-09:21:51 wrote gpt_002.pth
20240814-09:22:04 wrote non_validated_0369_01.png
20240814-09:22:17 wrote non_validated_0369_02.png
20240814-09:22:17 wrote state.pth
20240814-09:22:17 --- epoch 370 ----------------------------------------
20240814-09:22:17 current_test_accuracies 0.9527 0.9311 0.9449 0.9484 0.9524
20240814-09:22:17 training model 1
20240814-09:22:17 training model 2
20240814-09:26:01 train_perplexity 370 model 1 1.169969317999626
20240814-09:26:03 test_perplexity 370 model 1 1.1693047674872006
20240814-09:26:03 train_perplexity 370 model 2 1.1693252619702406
20240814-09:26:06 test_perplexity 370 model 2 1.1700193836567778
20240814-09:26:48 test_accuracy 370 model 1 val 779 / 823
20240814-09:26:51 test_accuracy 370 model 2 val 745 / 784
20240814-09:26:53 wrote gpt_001.pth
20240814-09:26:54 wrote gpt_002.pth
20240814-09:27:07 wrote non_validated_0370_01.png
20240814-09:27:20 wrote non_validated_0370_02.png
20240814-09:27:20 wrote state.pth
20240814-09:27:20 --- epoch 371 ----------------------------------------
20240814-09:27:20 current_test_accuracies 0.9527 0.9465 0.9503 0.9484 0.9524
20240814-09:27:20 training model 1
20240814-09:27:20 training model 3
20240814-09:31:04 train_perplexity 371 model 1 1.1697135317697804
20240814-09:31:06 test_perplexity 371 model 1 1.1720123450975761
20240814-09:31:07 train_perplexity 371 model 3 1.16905646213426
20240814-09:31:09 test_perplexity 371 model 3 1.170386559578362
20240814-09:31:55 test_accuracy 371 model 3 val 778 / 820
20240814-09:31:56 test_accuracy 371 model 1 val 755 / 799
20240814-09:31:58 wrote gpt_001.pth
20240814-09:31:59 wrote gpt_003.pth
20240814-09:32:11 wrote non_validated_0371_01.png
20240814-09:32:24 wrote non_validated_0371_03.png
20240814-09:32:25 wrote state.pth
20240814-09:32:25 --- epoch 372 ----------------------------------------
20240814-09:32:25 current_test_accuracies 0.9527 0.9449 0.9503 0.9488 0.9524
20240814-09:32:25 training model 1
20240814-09:32:25 training model 3
20240814-09:36:09 train_perplexity 372 model 1 1.169587293824661
20240814-09:36:11 test_perplexity 372 model 1 1.169007920706458
20240814-09:36:11 train_perplexity 372 model 3 1.1691113897355463
20240814-09:36:13 test_perplexity 372 model 3 1.169882020646702
20240814-09:36:58 test_accuracy 372 model 1 val 746 / 788
20240814-09:36:58 test_accuracy 372 model 3 val 770 / 809
20240814-09:37:00 wrote gpt_001.pth
20240814-09:37:01 wrote gpt_003.pth
20240814-09:37:14 wrote non_validated_0372_01.png
20240814-09:37:27 wrote non_validated_0372_03.png
20240814-09:37:27 wrote state.pth
20240814-09:37:27 --- epoch 373 ----------------------------------------
20240814-09:37:27 current_test_accuracies 0.9527 0.9467 0.9503 0.9518 0.9524
20240814-09:37:27 training model 1
20240814-09:37:27 training model 2
20240814-09:41:12 train_perplexity 373 model 1 1.169781884676893
20240814-09:41:13 test_perplexity 373 model 1 1.169583083209673
20240814-09:41:14 train_perplexity 373 model 2 1.1693231683493965
20240814-09:41:16 test_perplexity 373 model 2 1.17031024672261
20240814-09:41:59 test_accuracy 373 model 2 val 753 / 800
20240814-09:42:02 test_accuracy 373 model 1 val 750 / 788
20240814-09:42:04 wrote gpt_001.pth
20240814-09:42:05 wrote gpt_002.pth
20240814-09:42:18 wrote non_validated_0373_01.png
20240814-09:42:31 wrote non_validated_0373_02.png
20240814-09:42:31 wrote state.pth
20240814-09:42:31 --- epoch 374 ----------------------------------------
20240814-09:42:31 current_test_accuracies 0.9527 0.9518 0.9413 0.9518 0.9524
20240814-09:42:31 training model 2
20240814-09:42:31 training model 1
20240814-09:46:16 train_perplexity 374 model 2 1.1688059121590695
20240814-09:46:17 train_perplexity 374 model 1 1.1690673554789126
20240814-09:46:18 test_perplexity 374 model 2 1.173530431486794
20240814-09:46:20 test_perplexity 374 model 1 1.1696225098261932
20240814-09:47:03 test_accuracy 374 model 2 val 771 / 810
20240814-09:47:06 test_accuracy 374 model 1 val 759 / 799
20240814-09:47:08 wrote gpt_002.pth
20240814-09:47:09 wrote gpt_001.pth
20240814-09:47:22 wrote non_validated_0374_02.png
20240814-09:47:35 wrote non_validated_0374_01.png
20240814-09:47:35 wrote state.pth
20240814-09:47:35 --- epoch 375 ----------------------------------------
20240814-09:47:35 current_test_accuracies 0.9527 0.9499 0.9519 0.9518 0.9524
20240814-09:47:35 training model 1
20240814-09:47:35 training model 3
20240814-09:51:20 train_perplexity 375 model 1 1.1696803521360648
20240814-09:51:21 train_perplexity 375 model 3 1.16907845296414
20240814-09:51:22 test_perplexity 375 model 1 1.1695422140498422
20240814-09:51:24 test_perplexity 375 model 3 1.1701017317019806
20240814-09:52:08 test_accuracy 375 model 3 val 753 / 805
20240814-09:52:10 test_accuracy 375 model 1 val 750 / 793
20240814-09:52:12 wrote gpt_001.pth
20240814-09:52:13 wrote gpt_003.pth
20240814-09:52:26 wrote non_validated_0375_01.png
20240814-09:52:39 wrote non_validated_0375_03.png
20240814-09:52:39 wrote state.pth
20240814-09:52:39 --- epoch 376 ----------------------------------------
20240814-09:52:39 current_test_accuracies 0.9527 0.9458 0.9519 0.9354 0.9524
20240814-09:52:39 training model 3
20240814-09:52:39 training model 1
20240814-09:56:25 train_perplexity 376 model 3 1.1685833650089914
20240814-09:56:26 train_perplexity 376 model 1 1.1692881950022946
20240814-09:56:27 test_perplexity 376 model 3 1.1666564339444638
20240814-09:56:29 test_perplexity 376 model 1 1.1691214678844384
20240814-09:57:12 test_accuracy 376 model 3 val 758 / 800
20240814-09:57:14 test_accuracy 376 model 1 val 775 / 815
20240814-09:57:16 wrote gpt_003.pth
20240814-09:57:17 wrote gpt_001.pth
20240814-09:57:30 wrote non_validated_0376_03.png
20240814-09:57:43 wrote non_validated_0376_01.png
20240814-09:57:43 wrote state.pth
20240814-09:57:43 --- epoch 377 ----------------------------------------
20240814-09:57:43 current_test_accuracies 0.9527 0.9509 0.9519 0.9475 0.9524
20240814-09:57:43 training model 3
20240814-09:57:43 training model 1
20240814-10:01:28 train_perplexity 377 model 3 1.1685835090601033
20240814-10:01:29 train_perplexity 377 model 1 1.1700379821929556
20240814-10:01:30 test_perplexity 377 model 3 1.17191685569643
20240814-10:01:32 test_perplexity 377 model 1 1.1713230481175725
20240814-10:02:16 test_accuracy 377 model 3 val 773 / 809
20240814-10:02:17 test_accuracy 377 model 1 val 756 / 803
20240814-10:02:19 wrote gpt_003.pth
20240814-10:02:19 wrote gpt_001.pth
20240814-10:02:32 wrote non_validated_0377_03.png
20240814-10:02:45 wrote non_validated_0377_01.png
20240814-10:02:46 wrote state.pth
20240814-10:02:46 --- epoch 378 ----------------------------------------
20240814-10:02:46 current_test_accuracies 0.9527 0.9415 0.9519 0.9555 0.9524
20240814-10:02:46 training model 1
20240814-10:02:46 training model 2
20240814-10:06:30 train_perplexity 378 model 1 1.1692493269822022
20240814-10:06:32 test_perplexity 378 model 1 1.170753998578632
20240814-10:06:32 train_perplexity 378 model 2 1.1687747477154915
20240814-10:06:34 test_perplexity 378 model 2 1.1696665360714555
20240814-10:07:17 test_accuracy 378 model 1 val 770 / 812
20240814-10:07:18 test_accuracy 378 model 2 val 769 / 810
20240814-10:07:20 wrote gpt_001.pth
20240814-10:07:21 wrote gpt_002.pth
20240814-10:07:34 wrote non_validated_0378_01.png
20240814-10:07:47 wrote non_validated_0378_02.png
20240814-10:07:47 wrote state.pth
20240814-10:07:47 --- epoch 379 ----------------------------------------
20240814-10:07:47 current_test_accuracies 0.9527 0.9483 0.9494 0.9555 0.9524
20240814-10:07:47 training model 1
20240814-10:07:47 training model 2
20240814-10:11:32 train_perplexity 379 model 1 1.169287203988712
20240814-10:11:33 test_perplexity 379 model 1 1.1688121162554428
20240814-10:11:33 train_perplexity 379 model 2 1.1687996101497424
20240814-10:11:36 test_perplexity 379 model 2 1.1692366599305735
20240814-10:12:20 test_accuracy 379 model 2 val 747 / 806
20240814-10:12:22 test_accuracy 379 model 1 val 746 / 787
20240814-10:12:24 wrote gpt_001.pth
20240814-10:12:25 wrote gpt_002.pth
20240814-10:12:38 wrote non_validated_0379_01.png
20240814-10:12:51 wrote non_validated_0379_02.png
20240814-10:12:51 wrote state.pth
20240814-10:12:51 --- epoch 380 ----------------------------------------
20240814-10:12:51 current_test_accuracies 0.9527 0.9479 0.9268 0.9555 0.9524
20240814-10:12:51 training model 2
20240814-10:12:51 training model 1
20240814-10:16:36 train_perplexity 380 model 2 1.1688733248591905
20240814-10:16:37 train_perplexity 380 model 1 1.1694232579238257
20240814-10:16:39 test_perplexity 380 model 2 1.1700129921324856
20240814-10:16:40 test_perplexity 380 model 1 1.169992037731847
20240814-10:17:26 test_accuracy 380 model 2 val 765 / 811
20240814-10:17:28 test_accuracy 380 model 1 val 755 / 798
20240814-10:17:30 wrote gpt_002.pth
20240814-10:17:31 wrote gpt_001.pth
20240814-10:17:44 wrote non_validated_0380_02.png
20240814-10:17:57 wrote non_validated_0380_01.png
20240814-10:17:57 wrote state.pth
20240814-10:17:57 --- epoch 381 ----------------------------------------
20240814-10:17:57 current_test_accuracies 0.9527 0.9461 0.9433 0.9555 0.9524
20240814-10:17:57 training model 2
20240814-10:17:57 training model 1
20240814-10:21:42 train_perplexity 381 model 2 1.1690098690767101
20240814-10:21:43 train_perplexity 381 model 1 1.1689166505226598
20240814-10:21:44 test_perplexity 381 model 2 1.1703823770093484
20240814-10:21:46 test_perplexity 381 model 1 1.1710415281115656
20240814-10:22:32 test_accuracy 381 model 1 val 792 / 825
20240814-10:22:33 test_accuracy 381 model 2 val 743 / 792
20240814-10:22:35 wrote gpt_002.pth
20240814-10:22:35 wrote gpt_001.pth
20240814-10:22:48 wrote non_validated_0381_02.png
20240814-10:23:01 wrote non_validated_0381_01.png
20240814-10:23:01 wrote state.pth
20240814-10:23:01 --- epoch 382 ----------------------------------------
20240814-10:23:01 current_test_accuracies 0.9527 0.9600 0.9381 0.9555 0.9524
20240814-10:23:01 training model 2
20240814-10:23:01 training model 4
20240814-10:26:46 train_perplexity 382 model 2 1.1687682041454883
20240814-10:26:48 train_perplexity 382 model 4 1.169761945156782
20240814-10:26:49 test_perplexity 382 model 2 1.1711260051481254
20240814-10:26:50 test_perplexity 382 model 4 1.171390216372828
20240814-10:27:36 test_accuracy 382 model 4 val 763 / 809
20240814-10:27:37 test_accuracy 382 model 2 val 738 / 775
20240814-10:27:39 wrote gpt_002.pth
20240814-10:27:40 wrote gpt_004.pth
20240814-10:27:53 wrote non_validated_0382_02.png
20240814-10:28:06 wrote non_validated_0382_04.png
20240814-10:28:06 wrote state.pth
20240814-10:28:06 --- epoch 383 ----------------------------------------
20240814-10:28:06 current_test_accuracies 0.9527 0.9600 0.9523 0.9555 0.9431
20240814-10:28:06 training model 4
20240814-10:28:06 training model 2
20240814-10:31:51 train_perplexity 383 model 4 1.1693638062336564
20240814-10:31:52 train_perplexity 383 model 2 1.168397125480704
20240814-10:31:54 test_perplexity 383 model 4 1.169234930265122
20240814-10:31:55 test_perplexity 383 model 2 1.1694269997424347
20240814-10:32:39 test_accuracy 383 model 4 val 772 / 818
20240814-10:32:41 test_accuracy 383 model 2 val 750 / 803
20240814-10:32:43 wrote gpt_004.pth
20240814-10:32:44 wrote gpt_002.pth
20240814-10:32:57 wrote non_validated_0383_04.png
20240814-10:33:10 wrote non_validated_0383_02.png
20240814-10:33:10 wrote state.pth
20240814-10:33:10 --- epoch 384 ----------------------------------------
20240814-10:33:10 current_test_accuracies 0.9527 0.9600 0.9340 0.9555 0.9438
20240814-10:33:10 training model 2
20240814-10:33:10 training model 4
20240814-10:36:54 train_perplexity 384 model 2 1.1687746667469527
20240814-10:36:56 test_perplexity 384 model 2 1.169272932532317
20240814-10:36:56 train_perplexity 384 model 4 1.1694315892550606
20240814-10:36:59 test_perplexity 384 model 4 1.170026786431498
20240814-10:37:40 test_accuracy 384 model 2 val 769 / 807
20240814-10:37:44 test_accuracy 384 model 4 val 746 / 791
20240814-10:37:46 wrote gpt_002.pth
20240814-10:37:47 wrote gpt_004.pth
20240814-10:38:00 wrote non_validated_0384_02.png
20240814-10:38:13 wrote non_validated_0384_04.png
20240814-10:38:13 wrote state.pth
20240814-10:38:13 --- epoch 385 ----------------------------------------
20240814-10:38:13 current_test_accuracies 0.9527 0.9600 0.9529 0.9555 0.9431
20240814-10:38:13 training model 4
20240814-10:38:13 training model 0
20240814-10:41:57 train_perplexity 385 model 4 1.1691738605259268
20240814-10:41:59 test_perplexity 385 model 4 1.168190939501496
20240814-10:41:59 train_perplexity 385 model 0 1.1690448029061866
20240814-10:42:02 test_perplexity 385 model 0 1.1688469439939921
20240814-10:42:46 test_accuracy 385 model 4 val 725 / 774
20240814-10:42:49 test_accuracy 385 model 0 val 749 / 788
20240814-10:42:51 wrote gpt_004.pth
20240814-10:42:51 wrote gpt_000.pth
20240814-10:43:04 wrote non_validated_0385_04.png
20240814-10:43:18 wrote non_validated_0385_00.png
20240814-10:43:18 wrote state.pth
20240814-10:43:18 --- epoch 386 ----------------------------------------
20240814-10:43:18 current_test_accuracies 0.9505 0.9600 0.9529 0.9555 0.9367
20240814-10:43:18 training model 4
20240814-10:43:18 training model 0
20240814-10:47:02 train_perplexity 386 model 4 1.1695527683718419
20240814-10:47:04 test_perplexity 386 model 4 1.168367916549455
20240814-10:47:04 train_perplexity 386 model 0 1.1685850573658045
20240814-10:47:07 test_perplexity 386 model 0 1.1696318708364455
20240814-10:47:50 test_accuracy 386 model 0 val 767 / 807
20240814-10:47:52 test_accuracy 386 model 4 val 736 / 795
20240814-10:47:54 wrote gpt_004.pth
20240814-10:47:55 wrote gpt_000.pth
20240814-10:48:08 wrote non_validated_0386_04.png
20240814-10:48:21 wrote non_validated_0386_00.png
20240814-10:48:21 wrote state.pth
20240814-10:48:21 --- epoch 387 ----------------------------------------
20240814-10:48:21 current_test_accuracies 0.9504 0.9600 0.9529 0.9555 0.9258
20240814-10:48:21 training model 4
20240814-10:48:21 training model 0
20240814-10:52:06 train_perplexity 387 model 4 1.1697328850107762
20240814-10:52:07 train_perplexity 387 model 0 1.169253654884531
20240814-10:52:08 test_perplexity 387 model 4 1.171261267999098
20240814-10:52:10 test_perplexity 387 model 0 1.1700358320546516
20240814-10:52:54 test_accuracy 387 model 4 val 770 / 818
20240814-10:52:55 test_accuracy 387 model 0 val 761 / 812
20240814-10:52:57 wrote gpt_004.pth
20240814-10:52:58 wrote gpt_000.pth
20240814-10:53:11 wrote non_validated_0387_04.png
20240814-10:53:24 wrote non_validated_0387_00.png
20240814-10:53:24 wrote state.pth
20240814-10:53:24 --- epoch 388 ----------------------------------------
20240814-10:53:24 current_test_accuracies 0.9372 0.9600 0.9529 0.9555 0.9413
20240814-10:53:24 training model 0
20240814-10:53:24 training model 4
20240814-10:57:08 train_perplexity 388 model 0 1.168917867904143
20240814-10:57:10 test_perplexity 388 model 0 1.1704664847036073
20240814-10:57:11 train_perplexity 388 model 4 1.1692573805448325
20240814-10:57:13 test_perplexity 388 model 4 1.1719961068622025
20240814-10:57:58 test_accuracy 388 model 4 val 763 / 808
20240814-10:57:59 test_accuracy 388 model 0 val 761 / 797
20240814-10:58:01 wrote gpt_000.pth
20240814-10:58:02 wrote gpt_004.pth
20240814-10:58:15 wrote non_validated_0388_00.png
20240814-10:58:28 wrote non_validated_0388_04.png
20240814-10:58:28 wrote state.pth
20240814-10:58:28 --- epoch 389 ----------------------------------------
20240814-10:58:28 current_test_accuracies 0.9548 0.9600 0.9529 0.9555 0.9443
20240814-10:58:28 training model 4
20240814-10:58:28 training model 2
20240814-11:02:13 train_perplexity 389 model 4 1.1694848999936667
20240814-11:02:14 train_perplexity 389 model 2 1.1690368437761331
20240814-11:02:14 test_perplexity 389 model 4 1.1689229676529087
20240814-11:02:17 test_perplexity 389 model 2 1.1703555043708636
20240814-11:03:01 test_accuracy 389 model 2 val 786 / 827
20240814-11:03:03 test_accuracy 389 model 4 val 727 / 775
20240814-11:03:05 wrote gpt_004.pth
20240814-11:03:06 wrote gpt_002.pth
20240814-11:03:19 wrote non_validated_0389_04.png
20240814-11:03:31 wrote non_validated_0389_02.png
20240814-11:03:32 wrote state.pth
20240814-11:03:32 --- epoch 390 ----------------------------------------
20240814-11:03:32 current_test_accuracies 0.9548 0.9600 0.9504 0.9555 0.9381
20240814-11:03:32 training model 4
20240814-11:03:32 training model 2
20240814-11:07:16 train_perplexity 390 model 4 1.1693559455379656
20240814-11:07:18 test_perplexity 390 model 4 1.1708346854868519
20240814-11:07:19 train_perplexity 390 model 2 1.1684168742066934
20240814-11:07:21 test_perplexity 390 model 2 1.1690592621131248
20240814-11:08:05 test_accuracy 390 model 4 val 741 / 793
20240814-11:08:07 test_accuracy 390 model 2 val 735 / 787
20240814-11:08:09 wrote gpt_004.pth
20240814-11:08:10 wrote gpt_002.pth
20240814-11:08:23 wrote non_validated_0390_04.png
20240814-11:08:36 wrote non_validated_0390_02.png
20240814-11:08:36 wrote state.pth
20240814-11:08:36 --- epoch 391 ----------------------------------------
20240814-11:08:36 current_test_accuracies 0.9548 0.9600 0.9339 0.9555 0.9344
20240814-11:08:36 training model 2
20240814-11:08:36 training model 4
20240814-11:12:20 train_perplexity 391 model 2 1.1687467411429715
20240814-11:12:22 test_perplexity 391 model 2 1.169260718269887
20240814-11:12:23 train_perplexity 391 model 4 1.1692673101813997
20240814-11:12:25 test_perplexity 391 model 4 1.1683596872884132
20240814-11:13:09 test_accuracy 391 model 4 val 744 / 800
20240814-11:13:11 test_accuracy 391 model 2 val 755 / 795
20240814-11:13:13 wrote gpt_002.pth
20240814-11:13:13 wrote gpt_004.pth
20240814-11:13:26 wrote non_validated_0391_02.png
20240814-11:13:39 wrote non_validated_0391_04.png
20240814-11:13:39 wrote state.pth
20240814-11:13:39 --- epoch 392 ----------------------------------------
20240814-11:13:39 current_test_accuracies 0.9548 0.9600 0.9497 0.9555 0.9300
20240814-11:13:39 training model 4
20240814-11:13:39 training model 2
20240814-11:17:24 train_perplexity 392 model 4 1.1692869802897288
20240814-11:17:26 train_perplexity 392 model 2 1.168783033030351
20240814-11:17:26 test_perplexity 392 model 4 1.1693804767773746
20240814-11:17:28 test_perplexity 392 model 2 1.170637184783633
20240814-11:18:10 test_accuracy 392 model 4 val 756 / 803
20240814-11:18:14 test_accuracy 392 model 2 val 737 / 779
20240814-11:18:16 wrote gpt_004.pth
20240814-11:18:17 wrote gpt_002.pth
20240814-11:18:30 wrote non_validated_0392_04.png
20240814-11:18:43 wrote non_validated_0392_02.png
20240814-11:18:43 wrote state.pth
20240814-11:18:43 --- epoch 393 ----------------------------------------
20240814-11:18:43 current_test_accuracies 0.9548 0.9600 0.9461 0.9555 0.9415
20240814-11:18:43 training model 4
20240814-11:18:43 training model 2
20240814-11:22:27 train_perplexity 393 model 4 1.16942851865415
20240814-11:22:29 test_perplexity 393 model 4 1.1703988810871409
20240814-11:22:30 train_perplexity 393 model 2 1.1687416465332714
20240814-11:22:32 test_perplexity 393 model 2 1.1696206401602955
20240814-11:23:16 test_accuracy 393 model 4 val 738 / 782
20240814-11:23:19 test_accuracy 393 model 2 val 757 / 792
20240814-11:23:21 wrote gpt_004.pth
20240814-11:23:21 wrote gpt_002.pth
20240814-11:23:34 wrote non_validated_0393_04.png
20240814-11:23:48 wrote non_validated_0393_02.png
20240814-11:23:48 wrote state.pth
20240814-11:23:48 --- epoch 394 ----------------------------------------
20240814-11:23:48 current_test_accuracies 0.9548 0.9600 0.9558 0.9555 0.9437
20240814-11:23:48 training model 4
20240814-11:23:48 training model 0
20240814-11:27:32 train_perplexity 394 model 4 1.1690034924192434
20240814-11:27:34 test_perplexity 394 model 4 1.1687663583662495
20240814-11:27:34 train_perplexity 394 model 0 1.1687656642418511
20240814-11:27:37 test_perplexity 394 model 0 1.1706724014006582
20240814-11:28:21 test_accuracy 394 model 4 val 770 / 814
20240814-11:28:24 test_accuracy 394 model 0 val 742 / 790
20240814-11:28:26 wrote gpt_004.pth
20240814-11:28:26 wrote gpt_000.pth
20240814-11:28:39 wrote non_validated_0394_04.png
20240814-11:28:52 wrote non_validated_0394_00.png
20240814-11:28:52 wrote state.pth
20240814-11:28:52 --- epoch 395 ----------------------------------------
20240814-11:28:52 current_test_accuracies 0.9392 0.9600 0.9558 0.9555 0.9459
20240814-11:28:52 training model 0
20240814-11:28:52 training model 4
20240814-11:32:37 train_perplexity 395 model 0 1.1689566294345006
20240814-11:32:39 test_perplexity 395 model 0 1.1674306772114358
20240814-11:32:39 train_perplexity 395 model 4 1.169102728782958
20240814-11:32:41 test_perplexity 395 model 4 1.1689648738086706
20240814-11:33:24 test_accuracy 395 model 0 val 768 / 802
20240814-11:33:27 test_accuracy 395 model 4 val 742 / 786
20240814-11:33:29 wrote gpt_000.pth
20240814-11:33:29 wrote gpt_004.pth
20240814-11:33:42 wrote non_validated_0395_00.png
20240814-11:33:55 wrote non_validated_0395_04.png
20240814-11:33:56 wrote state.pth
20240814-11:33:56 --- epoch 396 ----------------------------------------
20240814-11:33:56 current_test_accuracies 0.9576 0.9600 0.9558 0.9555 0.9440
20240814-11:33:56 training model 4
20240814-11:33:56 training model 3
20240814-11:37:40 train_perplexity 396 model 4 1.1690563346612306
20240814-11:37:41 test_perplexity 396 model 4 1.1699058207467183
20240814-11:37:42 train_perplexity 396 model 3 1.1686692718599103
20240814-11:37:44 test_perplexity 396 model 3 1.1678053034558302
20240814-11:38:29 test_accuracy 396 model 3 val 762 / 809
20240814-11:38:30 test_accuracy 396 model 4 val 747 / 791
20240814-11:38:32 wrote gpt_004.pth
20240814-11:38:33 wrote gpt_003.pth
20240814-11:38:46 wrote non_validated_0396_04.png
20240814-11:38:59 wrote non_validated_0396_03.png
20240814-11:38:59 wrote state.pth
20240814-11:38:59 --- epoch 397 ----------------------------------------
20240814-11:38:59 current_test_accuracies 0.9576 0.9600 0.9558 0.9419 0.9444
20240814-11:38:59 training model 3
20240814-11:38:59 training model 4
20240814-11:42:44 train_perplexity 397 model 3 1.1690330259919783
20240814-11:42:45 test_perplexity 397 model 3 1.1686110129610976
20240814-11:42:46 train_perplexity 397 model 4 1.1687941612887445
20240814-11:42:49 test_perplexity 397 model 4 1.1712150067128337
20240814-11:43:33 test_accuracy 397 model 4 val 776 / 825
20240814-11:43:35 test_accuracy 397 model 3 val 740 / 783
20240814-11:43:37 wrote gpt_003.pth
20240814-11:43:38 wrote gpt_004.pth
20240814-11:43:51 wrote non_validated_0397_03.png
20240814-11:44:04 wrote non_validated_0397_04.png
20240814-11:44:04 wrote state.pth
20240814-11:44:04 --- epoch 398 ----------------------------------------
20240814-11:44:04 current_test_accuracies 0.9576 0.9600 0.9558 0.9451 0.9406
20240814-11:44:04 training model 4
20240814-11:44:04 training model 3
20240814-11:47:48 train_perplexity 398 model 4 1.1686926742283468
20240814-11:47:50 test_perplexity 398 model 4 1.1714693668999392
20240814-11:47:51 train_perplexity 398 model 3 1.168582773203546
20240814-11:47:53 test_perplexity 398 model 3 1.1691746087486907
20240814-11:48:34 test_accuracy 398 model 4 val 754 / 806
20240814-11:48:38 test_accuracy 398 model 3 val 750 / 791
20240814-11:48:40 wrote gpt_004.pth
20240814-11:48:41 wrote gpt_003.pth
20240814-11:48:54 wrote non_validated_0398_04.png
20240814-11:49:07 wrote non_validated_0398_03.png
20240814-11:49:07 wrote state.pth
20240814-11:49:07 --- epoch 399 ----------------------------------------
20240814-11:49:07 current_test_accuracies 0.9576 0.9600 0.9558 0.9482 0.9355
20240814-11:49:07 training model 4
20240814-11:49:07 training model 3
20240814-11:52:51 train_perplexity 399 model 4 1.1690835877595096
20240814-11:52:53 test_perplexity 399 model 4 1.1703931973063935
20240814-11:52:54 train_perplexity 399 model 3 1.168855148900958
20240814-11:52:56 test_perplexity 399 model 3 1.1725191817500729
20240814-11:53:39 test_accuracy 399 model 4 val 756 / 808
20240814-11:53:42 test_accuracy 399 model 3 val 751 / 794
20240814-11:53:44 wrote gpt_004.pth
20240814-11:53:44 wrote gpt_003.pth
20240814-11:53:57 wrote non_validated_0399_04.png
20240814-11:54:10 wrote non_validated_0399_03.png
20240814-11:54:10 wrote state.pth
20240814-11:54:10 --- epoch 400 ----------------------------------------
20240814-11:54:10 current_test_accuracies 0.9576 0.9600 0.9558 0.9458 0.9356
20240814-11:54:10 training model 4
20240814-11:54:10 training model 3
20240814-11:57:55 train_perplexity 400 model 4 1.168512509164015
20240814-11:57:57 test_perplexity 400 model 4 1.168443419797863
20240814-11:57:57 train_perplexity 400 model 3 1.1685748162668184
20240814-11:57:59 test_perplexity 400 model 3 1.1680365543212314
20240814-11:58:42 test_accuracy 400 model 3 val 760 / 804
20240814-11:58:45 test_accuracy 400 model 4 val 745 / 786
20240814-11:58:47 wrote gpt_004.pth
20240814-11:58:48 wrote gpt_003.pth
20240814-11:59:01 wrote non_validated_0400_04.png
20240814-11:59:14 wrote non_validated_0400_03.png
20240814-11:59:14 wrote state.pth
20240814-11:59:14 --- epoch 401 ----------------------------------------
20240814-11:59:14 current_test_accuracies 0.9576 0.9600 0.9558 0.9453 0.9478
20240814-11:59:14 training model 3
20240814-11:59:14 training model 4
20240814-12:02:58 train_perplexity 401 model 3 1.1684347507354202
20240814-12:03:00 test_perplexity 401 model 3 1.1694646266144337
20240814-12:03:01 train_perplexity 401 model 4 1.1691450139117805
20240814-12:03:03 test_perplexity 401 model 4 1.167226885657372
20240814-12:03:49 test_accuracy 401 model 3 val 739 / 791
20240814-12:03:50 test_accuracy 401 model 4 val 748 / 795
20240814-12:03:52 wrote gpt_003.pth
20240814-12:03:53 wrote gpt_004.pth
20240814-12:04:06 wrote non_validated_0401_03.png
20240814-12:04:19 wrote non_validated_0401_04.png
20240814-12:04:19 wrote state.pth
20240814-12:04:19 --- epoch 402 ----------------------------------------
20240814-12:04:19 current_test_accuracies 0.9576 0.9600 0.9558 0.9343 0.9409
20240814-12:04:19 training model 3
20240814-12:04:19 training model 4
20240814-12:08:03 train_perplexity 402 model 3 1.168441849856047
20240814-12:08:05 test_perplexity 402 model 3 1.1702405050814841
20240814-12:08:05 train_perplexity 402 model 4 1.1688796016783407
20240814-12:08:08 test_perplexity 402 model 4 1.170469185057506
20240814-12:08:49 test_accuracy 402 model 3 val 774 / 815
20240814-12:08:51 test_accuracy 402 model 4 val 759 / 812
20240814-12:08:53 wrote gpt_003.pth
20240814-12:08:54 wrote gpt_004.pth
20240814-12:09:07 wrote non_validated_0402_03.png
20240814-12:09:20 wrote non_validated_0402_04.png
20240814-12:09:20 wrote state.pth
20240814-12:09:20 --- epoch 403 ----------------------------------------
20240814-12:09:20 current_test_accuracies 0.9576 0.9600 0.9558 0.9497 0.9347
20240814-12:09:20 training model 4
20240814-12:09:20 training model 3
20240814-12:13:04 train_perplexity 403 model 4 1.1689857931884482
20240814-12:13:06 test_perplexity 403 model 4 1.1712211299256967
20240814-12:13:07 train_perplexity 403 model 3 1.168398929582607
20240814-12:13:09 test_perplexity 403 model 3 1.1710241355105038
20240814-12:13:53 test_accuracy 403 model 4 val 743 / 796
20240814-12:13:54 test_accuracy 403 model 3 val 775 / 813
20240814-12:13:56 wrote gpt_004.pth
20240814-12:13:57 wrote gpt_003.pth
20240814-12:14:10 wrote non_validated_0403_04.png
20240814-12:14:23 wrote non_validated_0403_03.png
20240814-12:14:23 wrote state.pth
20240814-12:14:23 --- epoch 404 ----------------------------------------
20240814-12:14:23 current_test_accuracies 0.9576 0.9600 0.9558 0.9533 0.9334
20240814-12:14:23 training model 4
20240814-12:14:23 training model 3
20240814-12:18:08 train_perplexity 404 model 4 1.169049736687965
20240814-12:18:10 train_perplexity 404 model 3 1.1689244321417485
20240814-12:18:10 test_perplexity 404 model 4 1.1691666107441698
20240814-12:18:12 test_perplexity 404 model 3 1.1726835811146545
20240814-12:18:55 test_accuracy 404 model 3 val 774 / 813
20240814-12:18:57 test_accuracy 404 model 4 val 766 / 811
20240814-12:18:59 wrote gpt_004.pth
20240814-12:18:59 wrote gpt_003.pth
20240814-12:19:12 wrote non_validated_0404_04.png
20240814-12:19:25 wrote non_validated_0404_03.png
20240814-12:19:25 wrote state.pth
20240814-12:19:25 --- epoch 405 ----------------------------------------
20240814-12:19:25 current_test_accuracies 0.9576 0.9600 0.9558 0.9520 0.9445
20240814-12:19:25 training model 4
20240814-12:19:25 training model 3
20240814-12:23:10 train_perplexity 405 model 4 1.1694168872232729
20240814-12:23:12 train_perplexity 405 model 3 1.1688008173295394
20240814-12:23:13 test_perplexity 405 model 4 1.1687061232826212
20240814-12:23:15 test_perplexity 405 model 3 1.1711535298417293
20240814-12:23:58 test_accuracy 405 model 3 val 767 / 813
20240814-12:24:00 test_accuracy 405 model 4 val 723 / 782
20240814-12:24:02 wrote gpt_004.pth
20240814-12:24:03 wrote gpt_003.pth
20240814-12:24:16 wrote non_validated_0405_04.png
20240814-12:24:29 wrote non_validated_0405_03.png
20240814-12:24:29 wrote state.pth
20240814-12:24:29 --- epoch 406 ----------------------------------------
20240814-12:24:29 current_test_accuracies 0.9576 0.9600 0.9558 0.9434 0.9246
20240814-12:24:29 training model 4
20240814-12:24:29 training model 3
20240814-12:28:13 train_perplexity 406 model 4 1.16816454878634
20240814-12:28:15 test_perplexity 406 model 4 1.169740566696303
20240814-12:28:15 train_perplexity 406 model 3 1.1683080599215703
20240814-12:28:17 test_perplexity 406 model 3 1.1700063718158835
20240814-12:29:04 test_accuracy 406 model 3 val 742 / 786
20240814-12:29:05 test_accuracy 406 model 4 val 747 / 795
20240814-12:29:07 wrote gpt_004.pth
20240814-12:29:07 wrote gpt_003.pth
20240814-12:29:20 wrote non_validated_0406_04.png
20240814-12:29:33 wrote non_validated_0406_03.png
20240814-12:29:33 wrote state.pth
20240814-12:29:33 --- epoch 407 ----------------------------------------
20240814-12:29:33 current_test_accuracies 0.9576 0.9600 0.9558 0.9440 0.9396
20240814-12:29:33 training model 4
20240814-12:29:33 training model 3
20240814-12:33:18 train_perplexity 407 model 4 1.1684498762615279
20240814-12:33:20 train_perplexity 407 model 3 1.1683479679274995
20240814-12:33:21 test_perplexity 407 model 4 1.1707086758025878
20240814-12:33:23 test_perplexity 407 model 3 1.1696058201900166
20240814-12:34:06 test_accuracy 407 model 4 val 765 / 815
20240814-12:34:09 test_accuracy 407 model 3 val 744 / 798
20240814-12:34:11 wrote gpt_004.pth
20240814-12:34:12 wrote gpt_003.pth
20240814-12:34:25 wrote non_validated_0407_04.png
20240814-12:34:38 wrote non_validated_0407_03.png
20240814-12:34:38 wrote state.pth
20240814-12:34:38 --- epoch 408 ----------------------------------------
20240814-12:34:38 current_test_accuracies 0.9576 0.9600 0.9558 0.9323 0.9387
20240814-12:34:38 training model 3
20240814-12:34:38 training model 4
20240814-12:38:22 train_perplexity 408 model 3 1.1685313690123007
20240814-12:38:24 test_perplexity 408 model 3 1.166598706110825
20240814-12:38:24 train_perplexity 408 model 4 1.1682015075229069
20240814-12:38:26 test_perplexity 408 model 4 1.166240643886861
20240814-12:39:12 test_accuracy 408 model 3 val 737 / 778
20240814-12:39:13 test_accuracy 408 model 4 val 718 / 762
20240814-12:39:15 wrote gpt_003.pth
20240814-12:39:16 wrote gpt_004.pth
20240814-12:39:29 wrote non_validated_0408_03.png
20240814-12:39:42 wrote non_validated_0408_04.png
20240814-12:39:42 wrote state.pth
20240814-12:39:42 --- epoch 409 ----------------------------------------
20240814-12:39:42 current_test_accuracies 0.9576 0.9600 0.9558 0.9473 0.9423
20240814-12:39:42 training model 4
20240814-12:39:42 training model 3
20240814-12:43:27 train_perplexity 409 model 4 1.1690127431897817
20240814-12:43:29 train_perplexity 409 model 3 1.168408455319918
20240814-12:43:29 test_perplexity 409 model 4 1.1691679709629366
20240814-12:43:31 test_perplexity 409 model 3 1.1722157354763456
20240814-12:44:15 test_accuracy 409 model 3 val 754 / 801
20240814-12:44:16 test_accuracy 409 model 4 val 754 / 803
20240814-12:44:18 wrote gpt_004.pth
20240814-12:44:19 wrote gpt_003.pth
20240814-12:44:32 wrote non_validated_0409_04.png
20240814-12:44:45 wrote non_validated_0409_03.png
20240814-12:44:45 wrote state.pth
20240814-12:44:45 --- epoch 410 ----------------------------------------
20240814-12:44:45 current_test_accuracies 0.9576 0.9600 0.9558 0.9413 0.9390
20240814-12:44:45 training model 4
20240814-12:44:45 training model 3
20240814-12:48:30 train_perplexity 410 model 4 1.1685305018659613
20240814-12:48:31 train_perplexity 410 model 3 1.1683229629969882
20240814-12:48:33 test_perplexity 410 model 4 1.1684603583712871
20240814-12:48:34 test_perplexity 410 model 3 1.1699125939052504
20240814-12:49:20 test_accuracy 410 model 4 val 756 / 798
20240814-12:49:21 test_accuracy 410 model 3 val 771 / 812
20240814-12:49:23 wrote gpt_004.pth
20240814-12:49:24 wrote gpt_003.pth
20240814-12:49:37 wrote non_validated_0410_04.png
20240814-12:49:50 wrote non_validated_0410_03.png
20240814-12:49:50 wrote state.pth
20240814-12:49:50 --- epoch 411 ----------------------------------------
20240814-12:49:50 current_test_accuracies 0.9576 0.9600 0.9558 0.9495 0.9474
20240814-12:49:50 training model 4
20240814-12:49:50 training model 3
20240814-12:53:35 train_perplexity 411 model 4 1.1682406181700802
20240814-12:53:36 train_perplexity 411 model 3 1.1680878604967961
20240814-12:53:37 test_perplexity 411 model 4 1.168017120817403
20240814-12:53:39 test_perplexity 411 model 3 1.1689447220176097
20240814-12:54:27 test_accuracy 411 model 4 val 755 / 790
20240814-12:54:28 test_accuracy 411 model 3 val 734 / 787
20240814-12:54:30 wrote gpt_004.pth
20240814-12:54:30 wrote gpt_003.pth
20240814-12:54:43 wrote non_validated_0411_04.png
20240814-12:54:56 wrote non_validated_0411_03.png
20240814-12:54:56 wrote state.pth
20240814-12:54:56 --- epoch 412 ----------------------------------------
20240814-12:54:56 current_test_accuracies 0.9576 0.9600 0.9558 0.9327 0.9557
20240814-12:54:56 training model 3
20240814-12:54:56 training model 4
20240814-12:58:42 train_perplexity 412 model 3 1.1684413008829206
20240814-12:58:43 train_perplexity 412 model 4 1.1684749755206858
20240814-12:58:45 test_perplexity 412 model 3 1.169122957403754
20240814-12:58:46 test_perplexity 412 model 4 1.1694098332572809
20240814-12:59:30 test_accuracy 412 model 3 val 766 / 808
20240814-12:59:31 test_accuracy 412 model 4 val 761 / 801
20240814-12:59:33 wrote gpt_003.pth
20240814-12:59:34 wrote gpt_004.pth
20240814-12:59:47 wrote non_validated_0412_03.png
20240814-13:00:00 wrote non_validated_0412_04.png
20240814-13:00:00 wrote state.pth
20240814-13:00:00 --- epoch 413 ----------------------------------------
20240814-13:00:00 current_test_accuracies 0.9576 0.9600 0.9558 0.9480 0.9501
20240814-13:00:00 training model 3
20240814-13:00:00 training model 4
20240814-13:03:44 train_perplexity 413 model 3 1.1683953812735262
20240814-13:03:46 train_perplexity 413 model 4 1.1687754813036624
20240814-13:03:46 test_perplexity 413 model 3 1.1725891216569473
20240814-13:03:49 test_perplexity 413 model 4 1.1704250771504934
20240814-13:04:31 test_accuracy 413 model 3 val 754 / 804
20240814-13:04:34 test_accuracy 413 model 4 val 733 / 795
20240814-13:04:36 wrote gpt_003.pth
20240814-13:04:37 wrote gpt_004.pth
20240814-13:04:50 wrote non_validated_0413_03.png
20240814-13:05:03 wrote non_validated_0413_04.png
20240814-13:05:03 wrote state.pth
20240814-13:05:03 --- epoch 414 ----------------------------------------
20240814-13:05:03 current_test_accuracies 0.9576 0.9600 0.9558 0.9378 0.9220
20240814-13:05:03 training model 4
20240814-13:05:03 training model 3
20240814-13:08:48 train_perplexity 414 model 4 1.1683455516537513
20240814-13:08:50 test_perplexity 414 model 4 1.1695445998820984
20240814-13:08:50 train_perplexity 414 model 3 1.168105072566006
20240814-13:08:52 test_perplexity 414 model 3 1.170315377718229
20240814-13:09:35 test_accuracy 414 model 4 val 774 / 818
20240814-13:09:38 test_accuracy 414 model 3 val 740 / 791
20240814-13:09:40 wrote gpt_004.pth
20240814-13:09:40 wrote gpt_003.pth
20240814-13:09:53 wrote non_validated_0414_04.png
20240814-13:10:06 wrote non_validated_0414_03.png
20240814-13:10:07 wrote state.pth
20240814-13:10:07 --- epoch 415 ----------------------------------------
20240814-13:10:07 current_test_accuracies 0.9576 0.9600 0.9558 0.9355 0.9462
20240814-13:10:07 training model 3
20240814-13:10:07 training model 4
20240814-13:13:52 train_perplexity 415 model 3 1.1676212378831654
20240814-13:13:53 train_perplexity 415 model 4 1.1682965239760978
20240814-13:13:54 test_perplexity 415 model 3 1.1685083787378916
20240814-13:13:56 test_perplexity 415 model 4 1.170729703660298
20240814-13:14:41 test_accuracy 415 model 4 val 780 / 824
20240814-13:14:42 test_accuracy 415 model 3 val 746 / 782
20240814-13:14:44 wrote gpt_003.pth
20240814-13:14:45 wrote gpt_004.pth
20240814-13:14:58 wrote non_validated_0415_03.png
20240814-13:15:11 wrote non_validated_0415_04.png
20240814-13:15:11 wrote state.pth
20240814-13:15:11 --- epoch 416 ----------------------------------------
20240814-13:15:11 current_test_accuracies 0.9576 0.9600 0.9558 0.9540 0.9466
20240814-13:15:11 training model 4
20240814-13:15:11 training model 3
20240814-13:18:55 train_perplexity 416 model 4 1.1687424032090155
20240814-13:18:57 test_perplexity 416 model 4 1.1724086977346042
20240814-13:18:58 train_perplexity 416 model 3 1.1681958400053647
20240814-13:19:00 test_perplexity 416 model 3 1.1713913596807615
20240814-13:19:44 test_accuracy 416 model 4 val 766 / 816
20240814-13:19:44 test_accuracy 416 model 3 val 789 / 833
20240814-13:19:46 wrote gpt_004.pth
20240814-13:19:47 wrote gpt_003.pth
20240814-13:20:00 wrote non_validated_0416_04.png
20240814-13:20:13 wrote non_validated_0416_03.png
20240814-13:20:13 wrote state.pth
20240814-13:20:13 --- epoch 417 ----------------------------------------
20240814-13:20:13 current_test_accuracies 0.9576 0.9600 0.9558 0.9472 0.9387
20240814-13:20:13 training model 4
20240814-13:20:13 training model 3
20240814-13:23:57 train_perplexity 417 model 4 1.1684158341477144
20240814-13:23:59 test_perplexity 417 model 4 1.1696940151341382
20240814-13:24:00 train_perplexity 417 model 3 1.1676334692411956
20240814-13:24:02 test_perplexity 417 model 3 1.1705156514803483
20240814-13:24:44 test_accuracy 417 model 4 val 761 / 802
20240814-13:24:48 test_accuracy 417 model 3 val 744 / 792
20240814-13:24:50 wrote gpt_004.pth
20240814-13:24:51 wrote gpt_003.pth
20240814-13:25:04 wrote non_validated_0417_04.png
20240814-13:25:17 wrote non_validated_0417_03.png
20240814-13:25:17 wrote state.pth
20240814-13:25:17 --- epoch 418 ----------------------------------------
20240814-13:25:17 current_test_accuracies 0.9576 0.9600 0.9558 0.9394 0.9489
20240814-13:25:17 training model 3
20240814-13:25:17 training model 4
20240814-13:29:03 train_perplexity 418 model 3 1.167468014086029
20240814-13:29:04 train_perplexity 418 model 4 1.1684216821077247
20240814-13:29:06 test_perplexity 418 model 3 1.1666777536644706
20240814-13:29:07 test_perplexity 418 model 4 1.166571860809835
20240814-13:29:54 test_accuracy 418 model 4 val 732 / 777
20240814-13:29:55 test_accuracy 418 model 3 val 750 / 783
20240814-13:29:57 wrote gpt_003.pth
20240814-13:29:58 wrote gpt_004.pth
20240814-13:30:11 wrote non_validated_0418_03.png
20240814-13:30:24 wrote non_validated_0418_04.png
20240814-13:30:24 wrote state.pth
20240814-13:30:24 --- epoch 419 ----------------------------------------
20240814-13:30:24 current_test_accuracies 0.9576 0.9600 0.9558 0.9579 0.9421
20240814-13:30:24 training model 4
20240814-13:30:24 training model 2
20240814-13:34:08 train_perplexity 419 model 4 1.1679841463393188
20240814-13:34:10 test_perplexity 419 model 4 1.16928341936312
20240814-13:34:11 train_perplexity 419 model 2 1.1683124256649744
20240814-13:34:13 test_perplexity 419 model 2 1.1709651598994846
20240814-13:34:59 test_accuracy 419 model 4 val 734 / 782
20240814-13:35:00 test_accuracy 419 model 2 val 741 / 790
20240814-13:35:02 wrote gpt_004.pth
20240814-13:35:03 wrote gpt_002.pth
20240814-13:35:16 wrote non_validated_0419_04.png
20240814-13:35:29 wrote non_validated_0419_02.png
20240814-13:35:29 wrote state.pth
20240814-13:35:29 --- epoch 420 ----------------------------------------
20240814-13:35:29 current_test_accuracies 0.9576 0.9600 0.9380 0.9579 0.9386
20240814-13:35:29 training model 2
20240814-13:35:29 training model 4
20240814-13:39:13 train_perplexity 420 model 2 1.1681520658848883
20240814-13:39:15 test_perplexity 420 model 2 1.168547933241036
20240814-13:39:16 train_perplexity 420 model 4 1.1683644221205338
20240814-13:39:18 test_perplexity 420 model 4 1.1721997808840237
20240814-13:40:01 test_accuracy 420 model 2 val 722 / 767
20240814-13:40:04 test_accuracy 420 model 4 val 737 / 797
20240814-13:40:06 wrote gpt_002.pth
20240814-13:40:06 wrote gpt_004.pth
20240814-13:40:19 wrote non_validated_0420_02.png
20240814-13:40:32 wrote non_validated_0420_04.png
20240814-13:40:32 wrote state.pth
20240814-13:40:32 --- epoch 421 ----------------------------------------
20240814-13:40:32 current_test_accuracies 0.9576 0.9600 0.9413 0.9579 0.9247
20240814-13:40:32 training model 4
20240814-13:40:32 training model 2
20240814-13:44:17 train_perplexity 421 model 4 1.1677675026317793
20240814-13:44:19 train_perplexity 421 model 2 1.168741544880551
20240814-13:44:19 test_perplexity 421 model 4 1.1697179212193403
20240814-13:44:21 test_perplexity 421 model 2 1.1690732089209286
20240814-13:45:05 test_accuracy 421 model 4 val 760 / 805
20240814-13:45:08 test_accuracy 421 model 2 val 760 / 793
20240814-13:45:10 wrote gpt_004.pth
20240814-13:45:11 wrote gpt_002.pth
20240814-13:45:24 wrote non_validated_0421_04.png
20240814-13:45:37 wrote non_validated_0421_02.png
20240814-13:45:37 wrote state.pth
20240814-13:45:37 --- epoch 422 ----------------------------------------
20240814-13:45:37 current_test_accuracies 0.9576 0.9600 0.9584 0.9579 0.9441
20240814-13:45:37 training model 4
20240814-13:45:37 training model 0
20240814-13:49:21 train_perplexity 422 model 4 1.168078923957124
20240814-13:49:23 test_perplexity 422 model 4 1.1710800572047853
20240814-13:49:24 train_perplexity 422 model 0 1.1681064336167493
20240814-13:49:26 test_perplexity 422 model 0 1.1700112669848177
20240814-13:50:10 test_accuracy 422 model 4 val 765 / 802
20240814-13:50:11 test_accuracy 422 model 0 val 750 / 801
20240814-13:50:13 wrote gpt_004.pth
20240814-13:50:13 wrote gpt_000.pth
20240814-13:50:26 wrote non_validated_0422_04.png
20240814-13:50:39 wrote non_validated_0422_00.png
20240814-13:50:40 wrote state.pth
20240814-13:50:40 --- epoch 423 ----------------------------------------
20240814-13:50:40 current_test_accuracies 0.9363 0.9600 0.9584 0.9579 0.9539
20240814-13:50:40 training model 0
20240814-13:50:40 training model 4
20240814-13:54:24 train_perplexity 423 model 0 1.1691842512122863
20240814-13:54:26 test_perplexity 423 model 0 1.1678041801795356
20240814-13:54:26 train_perplexity 423 model 4 1.1678887638241107
20240814-13:54:28 test_perplexity 423 model 4 1.16871581786156
20240814-13:55:15 test_accuracy 423 model 0 val 741 / 793
20240814-13:55:16 test_accuracy 423 model 4 val 737 / 791
20240814-13:55:18 wrote gpt_000.pth
20240814-13:55:19 wrote gpt_004.pth
20240814-13:55:32 wrote non_validated_0423_00.png
20240814-13:55:45 wrote non_validated_0423_04.png
20240814-13:55:45 wrote state.pth
20240814-13:55:45 --- epoch 424 ----------------------------------------
20240814-13:55:45 current_test_accuracies 0.9344 0.9600 0.9584 0.9579 0.9317
20240814-13:55:45 training model 4
20240814-13:55:45 training model 0
20240814-13:59:29 train_perplexity 424 model 4 1.1683135618886145
20240814-13:59:31 test_perplexity 424 model 4 1.1714834602912758
20240814-13:59:32 train_perplexity 424 model 0 1.1684589903843265
20240814-13:59:34 test_perplexity 424 model 0 1.169516803669798
20240814-14:00:14 test_accuracy 424 model 4 val 765 / 804
20240814-14:00:19 test_accuracy 424 model 0 val 748 / 799
20240814-14:00:21 wrote gpt_004.pth
20240814-14:00:22 wrote gpt_000.pth
20240814-14:00:35 wrote non_validated_0424_04.png
20240814-14:00:48 wrote non_validated_0424_00.png
20240814-14:00:48 wrote state.pth
20240814-14:00:48 --- epoch 425 ----------------------------------------
20240814-14:00:48 current_test_accuracies 0.9362 0.9600 0.9584 0.9579 0.9515
20240814-14:00:48 training model 0
20240814-14:00:48 training model 4
20240814-14:04:32 train_perplexity 425 model 0 1.1687398501310482
20240814-14:04:34 test_perplexity 425 model 0 1.1686095911365355
20240814-14:04:35 train_perplexity 425 model 4 1.1681442110229288
20240814-14:04:37 test_perplexity 425 model 4 1.1678999392305716
20240814-14:05:22 test_accuracy 425 model 0 val 743 / 786
20240814-14:05:24 test_accuracy 425 model 4 val 750 / 799
20240814-14:05:26 wrote gpt_000.pth
20240814-14:05:27 wrote gpt_004.pth
20240814-14:05:40 wrote non_validated_0425_00.png
20240814-14:05:53 wrote non_validated_0425_04.png
20240814-14:05:53 wrote state.pth
20240814-14:05:53 --- epoch 426 ----------------------------------------
20240814-14:05:53 current_test_accuracies 0.9453 0.9600 0.9584 0.9579 0.9387
20240814-14:05:53 training model 4
20240814-14:05:53 training model 0
20240814-14:09:37 train_perplexity 426 model 4 1.1678793894585922
20240814-14:09:39 test_perplexity 426 model 4 1.1681086232353457
20240814-14:09:39 train_perplexity 426 model 0 1.1683799256205876
20240814-14:09:42 test_perplexity 426 model 0 1.170127683109496
20240814-14:10:25 test_accuracy 426 model 0 val 743 / 800
20240814-14:10:27 test_accuracy 426 model 4 val 745 / 791
20240814-14:10:29 wrote gpt_004.pth
20240814-14:10:30 wrote gpt_000.pth
20240814-14:10:43 wrote non_validated_0426_04.png
20240814-14:10:56 wrote non_validated_0426_00.png
20240814-14:10:56 wrote state.pth
20240814-14:10:56 --- epoch 427 ----------------------------------------
20240814-14:10:56 current_test_accuracies 0.9287 0.9600 0.9584 0.9579 0.9418
20240814-14:10:56 training model 0
20240814-14:10:56 training model 4
20240814-14:14:40 train_perplexity 427 model 0 1.168539445517134
20240814-14:14:42 test_perplexity 427 model 0 1.169805345865872
20240814-14:14:43 train_perplexity 427 model 4 1.1676099633554478
20240814-14:14:45 test_perplexity 427 model 4 1.1692777553738303
20240814-14:15:27 test_accuracy 427 model 0 val 750 / 804
20240814-14:15:31 test_accuracy 427 model 4 val 750 / 797
20240814-14:15:33 wrote gpt_000.pth
20240814-14:15:33 wrote gpt_004.pth
20240814-14:15:46 wrote non_validated_0427_00.png
20240814-14:15:59 wrote non_validated_0427_04.png
20240814-14:15:59 wrote state.pth
20240814-14:15:59 --- epoch 428 ----------------------------------------
20240814-14:15:59 current_test_accuracies 0.9328 0.9600 0.9584 0.9579 0.9410
20240814-14:15:59 training model 0
20240814-14:15:59 training model 4
20240814-14:19:43 train_perplexity 428 model 0 1.168459203831735
20240814-14:19:45 test_perplexity 428 model 0 1.1695179033240108
20240814-14:19:46 train_perplexity 428 model 4 1.1682498367314436
20240814-14:19:48 test_perplexity 428 model 4 1.1697200324488057
20240814-14:20:32 test_accuracy 428 model 4 val 760 / 806
20240814-14:20:34 test_accuracy 428 model 0 val 746 / 794
20240814-14:20:36 wrote gpt_000.pth
20240814-14:20:36 wrote gpt_004.pth
20240814-14:20:49 wrote non_validated_0428_00.png
20240814-14:21:02 wrote non_validated_0428_04.png
20240814-14:21:03 wrote state.pth
20240814-14:21:03 --- epoch 429 ----------------------------------------
20240814-14:21:03 current_test_accuracies 0.9395 0.9600 0.9584 0.9579 0.9429
20240814-14:21:03 training model 0
20240814-14:21:03 training model 4
20240814-14:24:46 train_perplexity 429 model 0 1.1682731692374408
20240814-14:24:48 test_perplexity 429 model 0 1.1701898201838536
20240814-14:24:49 train_perplexity 429 model 4 1.167914597685131
20240814-14:24:52 test_perplexity 429 model 4 1.1691259303506116
20240814-14:25:34 test_accuracy 429 model 0 val 757 / 806
20240814-14:25:36 test_accuracy 429 model 4 val 754 / 809
20240814-14:25:38 wrote gpt_000.pth
20240814-14:25:38 wrote gpt_004.pth
20240814-14:25:51 wrote non_validated_0429_00.png
20240814-14:26:04 wrote non_validated_0429_04.png
20240814-14:26:04 wrote state.pth
20240814-14:26:04 --- epoch 430 ----------------------------------------
20240814-14:26:04 current_test_accuracies 0.9392 0.9600 0.9584 0.9579 0.9320
20240814-14:26:04 training model 4
20240814-14:26:04 training model 0
20240814-14:29:48 train_perplexity 430 model 4 1.168078777292081
20240814-14:29:50 test_perplexity 430 model 4 1.1693267925003443
20240814-14:29:51 train_perplexity 430 model 0 1.1684392763291078
20240814-14:29:54 test_perplexity 430 model 0 1.172324182327229
20240814-14:30:33 test_accuracy 430 model 4 val 754 / 804
20240814-14:30:37 test_accuracy 430 model 0 val 754 / 810
20240814-14:30:39 wrote gpt_004.pth
20240814-14:30:39 wrote gpt_000.pth
20240814-14:30:52 wrote non_validated_0430_04.png
20240814-14:31:05 wrote non_validated_0430_00.png
20240814-14:31:05 wrote state.pth
20240814-14:31:05 --- epoch 431 ----------------------------------------
20240814-14:31:05 current_test_accuracies 0.9309 0.9600 0.9584 0.9579 0.9378
20240814-14:31:05 training model 0
20240814-14:31:05 training model 4
20240814-14:34:50 train_perplexity 431 model 0 1.168230406707551
20240814-14:34:52 test_perplexity 431 model 0 1.1699647761284493
20240814-14:34:52 train_perplexity 431 model 4 1.1679810214685415
20240814-14:34:55 test_perplexity 431 model 4 1.1703787712832299
20240814-14:35:38 test_accuracy 431 model 4 val 760 / 800
20240814-14:35:39 test_accuracy 431 model 0 val 784 / 824
20240814-14:35:42 wrote gpt_000.pth
20240814-14:35:42 wrote gpt_004.pth
20240814-14:35:55 wrote non_validated_0431_00.png
20240814-14:36:08 wrote non_validated_0431_04.png
20240814-14:36:08 wrote state.pth
20240814-14:36:08 --- epoch 432 ----------------------------------------
20240814-14:36:08 current_test_accuracies 0.9515 0.9600 0.9584 0.9579 0.9500
20240814-14:37:19 keep c_quizzes model 1 validated 17 / 410 (4.15%) nb_accumulated 17 / 410 (finishes Wed 15:04 -- 866/h)
20240814-14:38:07 keep c_quizzes model 3 validated 22 / 410 (5.37%) nb_accumulated 39 / 410 (finishes Wed 14:57 -- 1177/h)
20240814-14:38:56 keep c_quizzes model 3 validated 22 / 410 (5.37%) nb_accumulated 61 / 410 (finishes Wed 14:54 -- 1310/h)
20240814-14:39:45 keep c_quizzes model 4 validated 23 / 410 (5.61%) nb_accumulated 84 / 410 (finishes Wed 14:53 -- 1397/h)
20240814-14:40:33 keep c_quizzes model 2 validated 24 / 410 (5.85%) nb_accumulated 108 / 410 (finishes Wed 14:52 -- 1466/h)
20240814-14:41:22 keep c_quizzes model 3 validated 19 / 410 (4.63%) nb_accumulated 127 / 410 (finishes Wed 14:53 -- 1457/h)
20240814-14:42:10 keep c_quizzes model 3 validated 19 / 410 (4.63%) nb_accumulated 146 / 410 (finishes Wed 14:53 -- 1450/h)
20240814-14:42:59 keep c_quizzes model 2 validated 30 / 410 (7.32%) nb_accumulated 176 / 410 (finishes Wed 14:52 -- 1542/h)
20240814-14:43:48 keep c_quizzes model 3 validated 22 / 410 (5.37%) nb_accumulated 198 / 410 (finishes Wed 14:52 -- 1551/h)
20240814-14:44:36 keep c_quizzes model 3 validated 22 / 410 (5.37%) nb_accumulated 220 / 410 (finishes Wed 14:51 -- 1558/h)
20240814-14:45:25 keep c_quizzes model 3 validated 21 / 410 (5.12%) nb_accumulated 241 / 410 (finishes Wed 14:51 -- 1558/h)
20240814-14:46:14 keep c_quizzes model 2 validated 24 / 410 (5.85%) nb_accumulated 265 / 410 (finishes Wed 14:51 -- 1575/h)
20240814-14:47:02 keep c_quizzes model 2 validated 19 / 410 (4.63%) nb_accumulated 284 / 410 (finishes Wed 14:51 -- 1562/h)
20240814-14:47:51 keep c_quizzes model 0 validated 25 / 410 (6.10%) nb_accumulated 309 / 410 (finishes Wed 14:51 -- 1582/h)
20240814-14:48:40 keep c_quizzes model 4 validated 19 / 410 (4.63%) nb_accumulated 328 / 410 (finishes Wed 14:51 -- 1570/h)
20240814-14:49:29 keep c_quizzes model 3 validated 21 / 410 (5.12%) nb_accumulated 349 / 410 (finishes Wed 14:51 -- 1569/h)
20240814-14:50:18 keep c_quizzes model 1 validated 14 / 410 (3.41%) nb_accumulated 363 / 410 (finishes Wed 14:52 -- 1538/h)
20240814-14:51:06 keep c_quizzes model 4 validated 23 / 410 (5.61%) nb_accumulated 386 / 410 (finishes Wed 14:52 -- 1547/h)
20240814-14:51:55 keep c_quizzes model 1 validated 21 / 410 (5.12%) nb_accumulated 407 / 410 (finishes Wed 14:52 -- 1547/h)
20240814-14:52:44 keep c_quizzes model 0 validated 20 / 410 (4.88%) nb_accumulated 427 / 410 (finishes now! -- 1543/h)
20240814-14:52:47 wrote c_quizzes.pth
20240814-14:52:47 training model 0
20240814-14:52:47 training model 1
20240814-14:56:31 train_perplexity 432 model 0 1.1699870908039605
20240814-14:56:33 train_perplexity 432 model 1 1.1704550924443393
20240814-14:56:33 test_perplexity 432 model 0 1.1725487240430372
20240814-14:56:35 test_perplexity 432 model 1 1.1720295611385905
20240814-14:57:20 test_accuracy 432 model 0 val 751 / 806
20240814-14:57:22 test_accuracy 432 model 1 val 751 / 791
20240814-14:57:24 wrote gpt_000.pth
20240814-14:57:24 wrote gpt_001.pth
20240814-14:57:37 wrote non_validated_0432_00.png
20240814-14:57:50 wrote non_validated_0432_01.png
20240814-14:57:50 wrote state.pth
20240814-14:57:50 --- epoch 433 ----------------------------------------
20240814-14:57:50 current_test_accuracies 0.9318 0.9494 0.0000 0.0000 0.0000
20240814-14:57:50 training model 2
20240814-14:57:50 training model 3
20240814-15:01:36 train_perplexity 433 model 2 1.1701517571780036
20240814-15:01:37 train_perplexity 433 model 3 1.168960606558665
20240814-15:01:38 test_perplexity 433 model 2 1.169085369397938
20240814-15:01:40 test_perplexity 433 model 3 1.1716358594595793
20240814-15:02:27 test_accuracy 433 model 2 val 747 / 791
20240814-15:02:28 test_accuracy 433 model 3 val 744 / 793
20240814-15:02:30 wrote gpt_002.pth
20240814-15:02:31 wrote gpt_003.pth
20240814-15:02:44 wrote non_validated_0433_02.png
20240814-15:02:57 wrote non_validated_0433_03.png
20240814-15:02:57 wrote state.pth
20240814-15:02:57 --- epoch 434 ----------------------------------------
20240814-15:02:57 current_test_accuracies 0.9318 0.9494 0.9444 0.9382 0.0000
20240814-15:02:57 training model 4
20240814-15:02:57 training model 0
20240814-15:06:42 train_perplexity 434 model 4 1.169168545631886
20240814-15:06:43 train_perplexity 434 model 0 1.1698439120445254
20240814-15:06:45 test_perplexity 434 model 4 1.1720836288621141
20240814-15:06:46 test_perplexity 434 model 0 1.1720457522457823
20240814-15:07:31 test_accuracy 434 model 4 val 758 / 816
20240814-15:07:31 test_accuracy 434 model 0 val 735 / 808
20240814-15:07:33 wrote gpt_004.pth
20240814-15:07:34 wrote gpt_000.pth
20240814-15:07:47 wrote non_validated_0434_04.png
20240814-15:08:00 wrote non_validated_0434_00.png
20240814-15:08:00 wrote state.pth
20240814-15:08:00 --- epoch 435 ----------------------------------------
20240814-15:08:00 current_test_accuracies 0.9097 0.9494 0.9444 0.9382 0.9289
20240814-15:08:00 training model 0
20240814-15:08:00 training model 4
20240814-15:11:45 train_perplexity 435 model 0 1.1697542958282188
20240814-15:11:47 train_perplexity 435 model 4 1.1691201372814526
20240814-15:11:48 test_perplexity 435 model 0 1.1690221347309606
20240814-15:11:49 test_perplexity 435 model 4 1.1689924461290173
20240814-15:12:34 test_accuracy 435 model 4 val 757 / 803
20240814-15:12:35 test_accuracy 435 model 0 val 724 / 780
20240814-15:12:37 wrote gpt_000.pth
20240814-15:12:38 wrote gpt_004.pth
20240814-15:12:51 wrote non_validated_0435_00.png
20240814-15:13:04 wrote non_validated_0435_04.png
20240814-15:13:04 wrote state.pth
20240814-15:13:04 --- epoch 436 ----------------------------------------
20240814-15:13:04 current_test_accuracies 0.9282 0.9494 0.9444 0.9382 0.9427
20240814-15:13:04 training model 0
20240814-15:13:04 training model 3
20240814-15:16:49 train_perplexity 436 model 0 1.1699675183974343
20240814-15:16:50 train_perplexity 436 model 3 1.1693199239542613
20240814-15:16:51 test_perplexity 436 model 0 1.1709404850229463
20240814-15:16:53 test_perplexity 436 model 3 1.1693633588935468
20240814-15:17:37 test_accuracy 436 model 0 val 743 / 805
20240814-15:17:40 test_accuracy 436 model 3 val 758 / 794
20240814-15:17:42 wrote gpt_000.pth
20240814-15:17:43 wrote gpt_003.pth
20240814-15:17:55 wrote non_validated_0436_00.png
20240814-15:18:08 wrote non_validated_0436_03.png
20240814-15:18:09 wrote state.pth
20240814-15:18:09 --- epoch 437 ----------------------------------------
20240814-15:18:09 current_test_accuracies 0.9230 0.9494 0.9444 0.9547 0.9427
20240814-15:18:09 training model 0
20240814-15:18:09 training model 4
20240814-15:21:53 train_perplexity 437 model 0 1.170011779451043
20240814-15:21:55 test_perplexity 437 model 0 1.1702832501824991
20240814-15:21:55 train_perplexity 437 model 4 1.1691746972146446
20240814-15:21:57 test_perplexity 437 model 4 1.1712206936119067
20240814-15:22:41 test_accuracy 437 model 4 val 772 / 815
20240814-15:22:44 test_accuracy 437 model 0 val 759 / 795
20240814-15:22:46 wrote gpt_000.pth
20240814-15:22:46 wrote gpt_004.pth
20240814-15:22:59 wrote non_validated_0437_00.png
20240814-15:23:12 wrote non_validated_0437_04.png
20240814-15:23:12 wrote state.pth
20240814-15:23:12 --- epoch 438 ----------------------------------------
20240814-15:23:12 current_test_accuracies 0.9547 0.9494 0.9444 0.9547 0.9472
20240814-15:23:12 training model 2
20240814-15:23:12 training model 4
20240814-15:26:57 train_perplexity 438 model 2 1.169704835124123
20240814-15:26:59 train_perplexity 438 model 4 1.1689586866523431
20240814-15:26:59 test_perplexity 438 model 2 1.1716482661386862
20240814-15:27:01 test_perplexity 438 model 4 1.172250203045348
20240814-15:27:47 test_accuracy 438 model 4 val 739 / 786
20240814-15:27:49 test_accuracy 438 model 2 val 747 / 798
20240814-15:27:51 wrote gpt_002.pth
20240814-15:27:52 wrote gpt_004.pth
20240814-15:28:05 wrote non_validated_0438_02.png
20240814-15:28:18 wrote non_validated_0438_04.png
20240814-15:28:18 wrote state.pth
20240814-15:28:18 --- epoch 439 ----------------------------------------
20240814-15:28:18 current_test_accuracies 0.9547 0.9494 0.9361 0.9547 0.9402
20240814-15:28:18 training model 2
20240814-15:28:18 training model 4
20240814-15:32:03 train_perplexity 439 model 2 1.1700571345053836
20240814-15:32:04 test_perplexity 439 model 2 1.1712930161509254
20240814-15:32:05 train_perplexity 439 model 4 1.1690610846632328
20240814-15:32:07 test_perplexity 439 model 4 1.1715831156266268
20240814-15:32:51 test_accuracy 439 model 2 val 773 / 812
20240814-15:32:53 test_accuracy 439 model 4 val 731 / 786
20240814-15:32:55 wrote gpt_002.pth
20240814-15:32:56 wrote gpt_004.pth
20240814-15:33:09 wrote non_validated_0439_02.png
20240814-15:33:22 wrote non_validated_0439_04.png
20240814-15:33:22 wrote state.pth
20240814-15:33:22 --- epoch 440 ----------------------------------------
20240814-15:33:22 current_test_accuracies 0.9547 0.9494 0.9520 0.9547 0.9300
20240814-15:33:22 training model 4
20240814-15:33:22 training model 1
20240814-15:37:07 train_perplexity 440 model 4 1.1687941104873123
20240814-15:37:09 test_perplexity 440 model 4 1.1728963519009745
20240814-15:37:09 train_perplexity 440 model 1 1.1712295309721685
20240814-15:37:11 test_perplexity 440 model 1 1.1684947416359146
20240814-15:37:54 test_accuracy 440 model 4 val 766 / 817
20240814-15:37:58 test_accuracy 440 model 1 val 761 / 799
20240814-15:38:00 wrote gpt_004.pth
20240814-15:38:01 wrote gpt_001.pth
20240814-15:38:14 wrote non_validated_0440_04.png
20240814-15:38:27 wrote non_validated_0440_01.png
20240814-15:38:27 wrote state.pth
20240814-15:38:27 --- epoch 441 ----------------------------------------
20240814-15:38:27 current_test_accuracies 0.9547 0.9524 0.9520 0.9547 0.9376
20240814-15:38:27 training model 4
20240814-15:38:27 training model 2
20240814-15:42:11 train_perplexity 441 model 4 1.1693421850343422
20240814-15:42:13 test_perplexity 441 model 4 1.1708864643617063
20240814-15:42:13 train_perplexity 441 model 2 1.1700060692246366
20240814-15:42:15 test_perplexity 441 model 2 1.169656407025549
20240814-15:43:00 test_accuracy 441 model 4 val 756 / 807
20240814-15:43:02 test_accuracy 441 model 2 val 747 / 794
20240814-15:43:04 wrote gpt_004.pth
20240814-15:43:05 wrote gpt_002.pth
20240814-15:43:18 wrote non_validated_0441_04.png
20240814-15:43:31 wrote non_validated_0441_02.png
20240814-15:43:31 wrote state.pth
20240814-15:43:31 --- epoch 442 ----------------------------------------
20240814-15:43:31 current_test_accuracies 0.9547 0.9524 0.9408 0.9547 0.9368
20240814-15:43:31 training model 4
20240814-15:43:31 training model 2
20240814-15:47:16 train_perplexity 442 model 4 1.1688807236812089
20240814-15:47:18 train_perplexity 442 model 2 1.1702692543403288
20240814-15:47:18 test_perplexity 442 model 4 1.1706805662703281
20240814-15:47:20 test_perplexity 442 model 2 1.1708848203657707
20240814-15:48:08 test_accuracy 442 model 4 val 722 / 771
20240814-15:48:09 test_accuracy 442 model 2 val 750 / 789
20240814-15:48:11 wrote gpt_004.pth
20240814-15:48:12 wrote gpt_002.pth
20240814-15:48:25 wrote non_validated_0442_04.png
20240814-15:48:38 wrote non_validated_0442_02.png
20240814-15:48:38 wrote state.pth
20240814-15:48:38 --- epoch 443 ----------------------------------------
20240814-15:48:38 current_test_accuracies 0.9547 0.9524 0.9506 0.9547 0.9364
20240814-15:48:38 training model 4
20240814-15:48:38 training model 2
20240814-15:52:22 train_perplexity 443 model 4 1.168531074752405
20240814-15:52:24 train_perplexity 443 model 2 1.1693371359859894
20240814-15:52:24 test_perplexity 443 model 4 1.1714449262174496
20240814-15:52:26 test_perplexity 443 model 2 1.167831111700597
20240814-15:53:09 test_accuracy 443 model 4 val 753 / 803
20240814-15:53:12 test_accuracy 443 model 2 val 732 / 774
20240814-15:53:14 wrote gpt_004.pth
20240814-15:53:14 wrote gpt_002.pth
20240814-15:53:27 wrote non_validated_0443_04.png
20240814-15:53:40 wrote non_validated_0443_02.png
20240814-15:53:40 wrote state.pth
20240814-15:53:40 --- epoch 444 ----------------------------------------
20240814-15:53:40 current_test_accuracies 0.9547 0.9524 0.9457 0.9547 0.9377
20240814-15:53:40 training model 4
20240814-15:53:40 training model 2
20240814-15:57:25 train_perplexity 444 model 4 1.1688817537197185
20240814-15:57:27 test_perplexity 444 model 4 1.1719285912753281
20240814-15:57:27 train_perplexity 444 model 2 1.1698918381892143
20240814-15:57:29 test_perplexity 444 model 2 1.1720327506157635
20240814-15:58:13 test_accuracy 444 model 4 val 760 / 806
20240814-15:58:16 test_accuracy 444 model 2 val 744 / 798
20240814-15:58:18 wrote gpt_004.pth
20240814-15:58:19 wrote gpt_002.pth
20240814-15:58:32 wrote non_validated_0444_04.png
20240814-15:58:45 wrote non_validated_0444_02.png
20240814-15:58:45 wrote state.pth
20240814-15:58:45 --- epoch 445 ----------------------------------------
20240814-15:58:45 current_test_accuracies 0.9547 0.9524 0.9323 0.9547 0.9429
20240814-15:58:45 training model 2
20240814-15:58:45 training model 4
20240814-16:02:29 train_perplexity 445 model 2 1.1696124874432243
20240814-16:02:31 test_perplexity 445 model 2 1.1718655542471696
20240814-16:02:31 train_perplexity 445 model 4 1.168795671764259
20240814-16:02:33 test_perplexity 445 model 4 1.1697055667905103
20240814-16:03:19 test_accuracy 445 model 2 val 743 / 796
20240814-16:03:20 test_accuracy 445 model 4 val 743 / 788
20240814-16:03:22 wrote gpt_002.pth
20240814-16:03:23 wrote gpt_004.pth
20240814-16:03:36 wrote non_validated_0445_02.png
20240814-16:03:49 wrote non_validated_0445_04.png
20240814-16:03:49 wrote state.pth
20240814-16:03:49 --- epoch 446 ----------------------------------------
20240814-16:03:49 current_test_accuracies 0.9547 0.9524 0.9334 0.9547 0.9429
20240814-16:03:49 training model 2
20240814-16:03:49 training model 4
20240814-16:07:33 train_perplexity 446 model 2 1.1696125086135079
20240814-16:07:35 train_perplexity 446 model 4 1.1685443415028054
20240814-16:07:35 test_perplexity 446 model 2 1.1696764747873631
20240814-16:07:37 test_perplexity 446 model 4 1.1732383227226575
20240814-16:08:22 test_accuracy 446 model 4 val 758 / 817
20240814-16:08:22 test_accuracy 446 model 2 val 756 / 801
20240814-16:08:25 wrote gpt_002.pth
20240814-16:08:25 wrote gpt_004.pth
20240814-16:08:38 wrote non_validated_0446_02.png
20240814-16:08:51 wrote non_validated_0446_04.png
20240814-16:08:51 wrote state.pth
20240814-16:08:51 --- epoch 447 ----------------------------------------
20240814-16:08:51 current_test_accuracies 0.9547 0.9524 0.9438 0.9547 0.9278
20240814-16:08:51 training model 4
20240814-16:08:51 training model 2
20240814-16:12:37 train_perplexity 447 model 4 1.1686252145627773
20240814-16:12:38 train_perplexity 447 model 2 1.1696540074739175
20240814-16:12:40 test_perplexity 447 model 4 1.1717326896038485
20240814-16:12:41 test_perplexity 447 model 2 1.170194966780955
20240814-16:13:26 test_accuracy 447 model 4 val 747 / 806
20240814-16:13:27 test_accuracy 447 model 2 val 765 / 814
20240814-16:13:29 wrote gpt_004.pth
20240814-16:13:30 wrote gpt_002.pth
20240814-16:13:43 wrote non_validated_0447_04.png
20240814-16:13:56 wrote non_validated_0447_02.png
20240814-16:13:56 wrote state.pth
20240814-16:13:56 --- epoch 448 ----------------------------------------
20240814-16:13:56 current_test_accuracies 0.9547 0.9524 0.9398 0.9547 0.9268
20240814-16:13:56 training model 4
20240814-16:13:56 training model 2
20240814-16:17:41 train_perplexity 448 model 4 1.1686684358049886
20240814-16:17:43 train_perplexity 448 model 2 1.1698441551560368
20240814-16:17:43 test_perplexity 448 model 4 1.1695112391913554
20240814-16:17:45 test_perplexity 448 model 2 1.1693961268242676
20240814-16:18:28 test_accuracy 448 model 4 val 752 / 804
20240814-16:18:31 test_accuracy 448 model 2 val 728 / 780
20240814-16:18:33 wrote gpt_004.pth
20240814-16:18:34 wrote gpt_002.pth
20240814-16:18:47 wrote non_validated_0448_04.png
20240814-16:19:00 wrote non_validated_0448_02.png
20240814-16:19:00 wrote state.pth
20240814-16:19:00 --- epoch 449 ----------------------------------------
20240814-16:19:00 current_test_accuracies 0.9547 0.9524 0.9333 0.9547 0.9353
20240814-16:19:00 training model 2
20240814-16:19:00 training model 4
20240814-16:22:44 train_perplexity 449 model 2 1.169654167196233
20240814-16:22:46 test_perplexity 449 model 2 1.1704095184119139
20240814-16:22:47 train_perplexity 449 model 4 1.1683206082951842
20240814-16:22:49 test_perplexity 449 model 4 1.1704160939201544
20240814-16:23:33 test_accuracy 449 model 4 val 752 / 807
20240814-16:23:35 test_accuracy 449 model 2 val 742 / 788
20240814-16:23:37 wrote gpt_002.pth
20240814-16:23:38 wrote gpt_004.pth
20240814-16:23:51 wrote non_validated_0449_02.png
20240814-16:24:04 wrote non_validated_0449_04.png
20240814-16:24:04 wrote state.pth
20240814-16:24:04 --- epoch 450 ----------------------------------------
20240814-16:24:04 current_test_accuracies 0.9547 0.9524 0.9416 0.9547 0.9318
20240814-16:24:04 training model 4
20240814-16:24:04 training model 2
20240814-16:27:49 train_perplexity 450 model 4 1.1682733768734153
20240814-16:27:51 train_perplexity 450 model 2 1.1691742662963875
20240814-16:27:51 test_perplexity 450 model 4 1.170489558911791
20240814-16:27:53 test_perplexity 450 model 2 1.169363706519793
20240814-16:28:41 test_accuracy 450 model 4 val 729 / 783
20240814-16:28:42 test_accuracy 450 model 2 val 733 / 791
20240814-16:28:44 wrote gpt_004.pth
20240814-16:28:45 wrote gpt_002.pth
20240814-16:28:58 wrote non_validated_0450_04.png
20240814-16:29:11 wrote non_validated_0450_02.png
20240814-16:29:11 wrote state.pth
20240814-16:29:11 --- epoch 451 ----------------------------------------
20240814-16:29:11 current_test_accuracies 0.9547 0.9524 0.9267 0.9547 0.9310
20240814-16:29:11 training model 2
20240814-16:29:11 training model 4
20240814-16:32:56 train_perplexity 451 model 2 1.1695618215385755
20240814-16:32:57 train_perplexity 451 model 4 1.1683129785707906
20240814-16:32:59 test_perplexity 451 model 2 1.1731377250853525
20240814-16:33:00 test_perplexity 451 model 4 1.1694800917584294
20240814-16:33:44 test_accuracy 451 model 4 val 766 / 806
20240814-16:33:47 test_accuracy 451 model 2 val 756 / 791
20240814-16:33:49 wrote gpt_002.pth
20240814-16:33:50 wrote gpt_004.pth
20240814-16:34:03 wrote non_validated_0451_02.png
20240814-16:34:16 wrote non_validated_0451_04.png
20240814-16:34:16 wrote state.pth
20240814-16:34:16 --- epoch 452 ----------------------------------------
20240814-16:34:16 current_test_accuracies 0.9547 0.9524 0.9558 0.9547 0.9504
20240814-16:35:28 keep c_quizzes model 1 validated 23 / 410 (5.61%) nb_accumulated 23 / 410 (finishes Wed 16:55 -- 1142/h)
20240814-16:36:17 keep c_quizzes model 1 validated 19 / 410 (4.63%) nb_accumulated 42 / 410 (finishes Wed 16:54 -- 1245/h)
20240814-16:37:06 keep c_quizzes model 2 validated 14 / 410 (3.41%) nb_accumulated 56 / 410 (finishes Wed 16:55 -- 1184/h)
20240814-16:37:55 keep c_quizzes model 2 validated 20 / 410 (4.88%) nb_accumulated 76 / 410 (finishes Wed 16:53 -- 1248/h)
20240814-16:38:44 keep c_quizzes model 0 validated 18 / 410 (4.39%) nb_accumulated 94 / 410 (finishes Wed 16:53 -- 1262/h)
20240814-16:39:33 keep c_quizzes model 3 validated 16 / 410 (3.90%) nb_accumulated 110 / 410 (finishes Wed 16:53 -- 1249/h)
20240814-16:40:22 keep c_quizzes model 1 validated 12 / 410 (2.93%) nb_accumulated 122 / 410 (finishes Wed 16:54 -- 1200/h)
20240814-16:41:11 keep c_quizzes model 4 validated 6 / 410 (1.46%) nb_accumulated 128 / 410 (finishes Wed 16:56 -- 1110/h)
20240814-16:42:00 keep c_quizzes model 2 validated 16 / 410 (3.90%) nb_accumulated 144 / 410 (finishes Wed 16:56 -- 1117/h)
20240814-16:42:49 keep c_quizzes model 4 validated 14 / 410 (3.41%) nb_accumulated 158 / 410 (finishes Wed 16:56 -- 1109/h)
20240814-16:43:38 keep c_quizzes model 3 validated 16 / 410 (3.90%) nb_accumulated 174 / 410 (finishes Wed 16:56 -- 1115/h)
20240814-16:44:27 keep c_quizzes model 1 validated 15 / 410 (3.66%) nb_accumulated 189 / 410 (finishes Wed 16:56 -- 1114/h)
20240814-16:45:16 keep c_quizzes model 3 validated 13 / 410 (3.17%) nb_accumulated 202 / 410 (finishes Wed 16:56 -- 1102/h)
20240814-16:46:05 keep c_quizzes model 4 validated 11 / 410 (2.68%) nb_accumulated 213 / 410 (finishes Wed 16:57 -- 1082/h)
20240814-16:46:54 keep c_quizzes model 2 validated 23 / 410 (5.61%) nb_accumulated 236 / 410 (finishes Wed 16:56 -- 1121/h)
20240814-16:47:42 keep c_quizzes model 3 validated 16 / 410 (3.90%) nb_accumulated 252 / 410 (finishes Wed 16:56 -- 1124/h)
20240814-16:48:31 keep c_quizzes model 1 validated 21 / 410 (5.12%) nb_accumulated 273 / 410 (finishes Wed 16:55 -- 1148/h)
20240814-16:49:20 keep c_quizzes model 2 validated 21 / 410 (5.12%) nb_accumulated 294 / 410 (finishes Wed 16:55 -- 1170/h)
20240814-16:50:09 keep c_quizzes model 1 validated 14 / 410 (3.41%) nb_accumulated 308 / 410 (finishes Wed 16:55 -- 1163/h)
20240814-16:50:58 keep c_quizzes model 0 validated 18 / 410 (4.39%) nb_accumulated 326 / 410 (finishes Wed 16:55 -- 1171/h)
20240814-16:51:47 keep c_quizzes model 1 validated 17 / 410 (4.15%) nb_accumulated 343 / 410 (finishes Wed 16:55 -- 1174/h)
20240814-16:52:36 keep c_quizzes model 4 validated 15 / 410 (3.66%) nb_accumulated 358 / 410 (finishes Wed 16:55 -- 1171/h)
20240814-16:53:25 keep c_quizzes model 2 validated 21 / 410 (5.12%) nb_accumulated 379 / 410 (finishes Wed 16:54 -- 1187/h)
20240814-16:54:14 keep c_quizzes model 3 validated 22 / 410 (5.37%) nb_accumulated 401 / 410 (finishes Wed 16:54 -- 1205/h)
20240814-16:55:03 keep c_quizzes model 0 validated 9 / 410 (2.20%) nb_accumulated 410 / 410 (finishes now! -- 1183/h)
20240814-16:55:06 wrote c_quizzes.pth
20240814-16:55:06 training model 0
20240814-16:55:06 training model 1
20240814-16:58:50 train_perplexity 452 model 0 1.1709416819274139
20240814-16:58:51 train_perplexity 452 model 1 1.172097999099643
20240814-16:58:52 test_perplexity 452 model 0 1.1715964780168837
20240814-16:58:54 test_perplexity 452 model 1 1.174580498000202
20240814-16:59:38 test_accuracy 452 model 1 val 756 / 800
20240814-16:59:41 test_accuracy 452 model 0 val 756 / 799
20240814-16:59:43 wrote gpt_000.pth
20240814-16:59:44 wrote gpt_001.pth
20240814-16:59:56 wrote non_validated_0452_00.png
20240814-17:00:09 wrote non_validated_0452_01.png
20240814-17:00:09 wrote state.pth
20240814-17:00:09 --- epoch 453 ----------------------------------------
20240814-17:00:09 current_test_accuracies 0.9462 0.9450 0.0000 0.0000 0.0000
20240814-17:00:09 training model 2
20240814-17:00:09 training model 3
20240814-17:03:54 train_perplexity 453 model 2 1.1705511783093878
20240814-17:03:55 test_perplexity 453 model 2 1.1724660316958817
20240814-17:03:56 train_perplexity 453 model 3 1.170607952041369
20240814-17:03:59 test_perplexity 453 model 3 1.173050390940931
20240814-17:04:41 test_accuracy 453 model 2 val 755 / 807
20240814-17:04:45 test_accuracy 453 model 3 val 740 / 790
20240814-17:04:47 wrote gpt_002.pth
20240814-17:04:47 wrote gpt_003.pth
20240814-17:05:00 wrote non_validated_0453_02.png
20240814-17:05:13 wrote non_validated_0453_03.png
20240814-17:05:13 wrote state.pth
20240814-17:05:13 --- epoch 454 ----------------------------------------
20240814-17:05:13 current_test_accuracies 0.9462 0.9450 0.9356 0.9367 0.0000
20240814-17:05:13 training model 4
20240814-17:05:13 training model 2
20240814-17:08:58 train_perplexity 454 model 4 1.1702147427015401
20240814-17:09:00 test_perplexity 454 model 4 1.1713285828173714
20240814-17:09:00 train_perplexity 454 model 2 1.1713056978824472
20240814-17:09:02 test_perplexity 454 model 2 1.1707114573981774
20240814-17:09:47 test_accuracy 454 model 2 val 770 / 812
20240814-17:09:48 test_accuracy 454 model 4 val 743 / 790
20240814-17:09:50 wrote gpt_004.pth
20240814-17:09:51 wrote gpt_002.pth
20240814-17:10:04 wrote non_validated_0454_04.png
20240814-17:10:17 wrote non_validated_0454_02.png
20240814-17:10:17 wrote state.pth
20240814-17:10:17 --- epoch 455 ----------------------------------------
20240814-17:10:17 current_test_accuracies 0.9462 0.9450 0.9483 0.9367 0.9405
20240814-17:10:17 training model 3
20240814-17:10:17 training model 4
20240814-17:14:03 train_perplexity 455 model 3 1.1704422907829901
20240814-17:14:04 train_perplexity 455 model 4 1.1696577079609862
20240814-17:14:07 test_perplexity 455 model 3 1.1717035065897832
20240814-17:14:07 test_perplexity 455 model 4 1.171768676019158
20240814-17:14:55 test_accuracy 455 model 3 val 736 / 793
20240814-17:14:56 test_accuracy 455 model 4 val 747 / 789
20240814-17:14:58 wrote gpt_003.pth
20240814-17:14:59 wrote gpt_004.pth
20240814-17:15:12 wrote non_validated_0455_03.png
20240814-17:15:25 wrote non_validated_0455_04.png
20240814-17:15:25 wrote state.pth
20240814-17:15:25 --- epoch 456 ----------------------------------------
20240814-17:15:25 current_test_accuracies 0.9462 0.9450 0.9483 0.9281 0.9468
20240814-17:15:25 training model 3
20240814-17:15:25 training model 1
20240814-17:19:09 train_perplexity 456 model 3 1.1701859017438645
20240814-17:19:11 test_perplexity 456 model 3 1.1714755171907285
20240814-17:19:12 train_perplexity 456 model 1 1.1720001181879487
20240814-17:19:14 test_perplexity 456 model 1 1.1724145013663476
20240814-17:19:56 test_accuracy 456 model 3 val 772 / 826
20240814-17:20:00 test_accuracy 456 model 1 val 751 / 795
20240814-17:20:02 wrote gpt_003.pth
20240814-17:20:03 wrote gpt_001.pth
20240814-17:20:16 wrote non_validated_0456_03.png
20240814-17:20:29 wrote non_validated_0456_01.png
20240814-17:20:29 wrote state.pth
20240814-17:20:29 --- epoch 457 ----------------------------------------
20240814-17:20:29 current_test_accuracies 0.9462 0.9447 0.9483 0.9346 0.9468
20240814-17:20:29 training model 3
20240814-17:20:29 training model 1
20240814-17:24:13 train_perplexity 457 model 3 1.1703995019293698
20240814-17:24:15 test_perplexity 457 model 3 1.1696658563254587
20240814-17:24:16 train_perplexity 457 model 1 1.1719764416068557
20240814-17:24:18 test_perplexity 457 model 1 1.1701606306966454
20240814-17:25:00 test_accuracy 457 model 3 val 769 / 815
20240814-17:25:02 test_accuracy 457 model 1 val 751 / 805
20240814-17:25:04 wrote gpt_003.pth
20240814-17:25:05 wrote gpt_001.pth
20240814-17:25:18 wrote non_validated_0457_03.png
20240814-17:25:31 wrote non_validated_0457_01.png
20240814-17:25:31 wrote state.pth
20240814-17:25:31 --- epoch 458 ----------------------------------------
20240814-17:25:31 current_test_accuracies 0.9462 0.9329 0.9483 0.9436 0.9468
20240814-17:25:31 training model 1
20240814-17:25:31 training model 3
20240814-17:29:15 train_perplexity 458 model 1 1.171291859592421
20240814-17:29:17 test_perplexity 458 model 1 1.1720057379179252
20240814-17:29:18 train_perplexity 458 model 3 1.1708187163467525
20240814-17:29:20 test_perplexity 458 model 3 1.1705205954377085
20240814-17:30:06 test_accuracy 458 model 1 val 753 / 792
20240814-17:30:07 test_accuracy 458 model 3 val 730 / 787
20240814-17:30:09 wrote gpt_001.pth
20240814-17:30:10 wrote gpt_003.pth
20240814-17:30:23 wrote non_validated_0458_01.png
20240814-17:30:36 wrote non_validated_0458_03.png
20240814-17:30:36 wrote state.pth
20240814-17:30:36 --- epoch 459 ----------------------------------------
20240814-17:30:36 current_test_accuracies 0.9462 0.9508 0.9483 0.9276 0.9468
20240814-17:30:36 training model 3
20240814-17:30:36 training model 0
20240814-17:34:20 train_perplexity 459 model 3 1.1702805973307226
20240814-17:34:22 test_perplexity 459 model 3 1.1692018179664199
20240814-17:34:23 train_perplexity 459 model 0 1.171245397169252
20240814-17:34:25 test_perplexity 459 model 0 1.1735770404231638
20240814-17:35:07 test_accuracy 459 model 3 val 750 / 804
20240814-17:35:09 test_accuracy 459 model 0 val 756 / 803
20240814-17:35:11 wrote gpt_003.pth
20240814-17:35:12 wrote gpt_000.pth
20240814-17:35:25 wrote non_validated_0459_03.png
20240814-17:35:38 wrote non_validated_0459_00.png
20240814-17:35:38 wrote state.pth
20240814-17:35:38 --- epoch 460 ----------------------------------------
20240814-17:35:38 current_test_accuracies 0.9415 0.9508 0.9483 0.9328 0.9468
20240814-17:35:38 training model 3
20240814-17:35:38 training model 0
20240814-17:39:22 train_perplexity 460 model 3 1.1705975508773594
20240814-17:39:24 test_perplexity 460 model 3 1.1732840109257372
20240814-17:39:24 train_perplexity 460 model 0 1.1707757491350255
20240814-17:39:27 test_perplexity 460 model 0 1.174123670637042
20240814-17:40:09 test_accuracy 460 model 3 val 759 / 805
20240814-17:40:11 test_accuracy 460 model 0 val 757 / 810
20240814-17:40:13 wrote gpt_003.pth
20240814-17:40:14 wrote gpt_000.pth
20240814-17:40:27 wrote non_validated_0460_03.png
20240814-17:40:40 wrote non_validated_0460_00.png
20240814-17:40:40 wrote state.pth
20240814-17:40:40 --- epoch 461 ----------------------------------------
20240814-17:40:40 current_test_accuracies 0.9346 0.9508 0.9483 0.9429 0.9468
20240814-17:40:40 training model 0
20240814-17:40:40 training model 3
20240814-17:44:24 train_perplexity 461 model 0 1.171065960813932
20240814-17:44:26 test_perplexity 461 model 0 1.1702317612938813
20240814-17:44:27 train_perplexity 461 model 3 1.1706114752300383
20240814-17:44:29 test_perplexity 461 model 3 1.1748580189623996
20240814-17:45:13 test_accuracy 461 model 0 val 756 / 804
20240814-17:45:13 test_accuracy 461 model 3 val 748 / 806
20240814-17:45:15 wrote gpt_000.pth
20240814-17:45:16 wrote gpt_003.pth
20240814-17:45:29 wrote non_validated_0461_00.png
20240814-17:45:42 wrote non_validated_0461_03.png
20240814-17:45:42 wrote state.pth
20240814-17:45:42 --- epoch 462 ----------------------------------------
20240814-17:45:42 current_test_accuracies 0.9403 0.9508 0.9483 0.9280 0.9468
20240814-17:45:42 training model 3
20240814-17:45:42 training model 0
20240814-17:49:27 train_perplexity 462 model 3 1.170141452758569
20240814-17:49:29 train_perplexity 462 model 0 1.170715202575435
20240814-17:49:29 test_perplexity 462 model 3 1.1735234826242031
20240814-17:49:31 test_perplexity 462 model 0 1.1728524286631226
20240814-17:50:15 test_accuracy 462 model 3 val 746 / 800
20240814-17:50:16 test_accuracy 462 model 0 val 746 / 804
20240814-17:50:18 wrote gpt_003.pth
20240814-17:50:19 wrote gpt_000.pth
20240814-17:50:32 wrote non_validated_0462_03.png
20240814-17:50:45 wrote non_validated_0462_00.png
20240814-17:50:45 wrote state.pth
20240814-17:50:45 --- epoch 463 ----------------------------------------
20240814-17:50:45 current_test_accuracies 0.9279 0.9508 0.9483 0.9325 0.9468
20240814-17:50:45 training model 0
20240814-17:50:45 training model 3
20240814-17:54:29 train_perplexity 463 model 0 1.1709398251147634
20240814-17:54:31 test_perplexity 463 model 0 1.1725314715470623
20240814-17:54:31 train_perplexity 463 model 3 1.1702571019788306
20240814-17:54:34 test_perplexity 463 model 3 1.1741569301980654
20240814-17:55:16 test_accuracy 463 model 0 val 740 / 803
20240814-17:55:20 test_accuracy 463 model 3 val 738 / 790
20240814-17:55:22 wrote gpt_000.pth
20240814-17:55:23 wrote gpt_003.pth
20240814-17:55:36 wrote non_validated_0463_00.png
20240814-17:55:49 wrote non_validated_0463_03.png
20240814-17:55:49 wrote state.pth
20240814-17:55:49 --- epoch 464 ----------------------------------------
20240814-17:55:49 current_test_accuracies 0.9215 0.9508 0.9483 0.9342 0.9468
20240814-17:55:49 training model 0
20240814-17:55:49 training model 3
20240814-17:59:33 train_perplexity 464 model 0 1.1706929749031916
20240814-17:59:34 test_perplexity 464 model 0 1.1741792032013585
20240814-17:59:36 train_perplexity 464 model 3 1.170109182630653
20240814-17:59:38 test_perplexity 464 model 3 1.1697581498380043
20240814-18:00:22 test_accuracy 464 model 0 val 722 / 794
20240814-18:00:25 test_accuracy 464 model 3 val 750 / 790
20240814-18:00:27 wrote gpt_000.pth
20240814-18:00:27 wrote gpt_003.pth
20240814-18:00:40 wrote non_validated_0464_00.png
20240814-18:00:53 wrote non_validated_0464_03.png
20240814-18:00:53 wrote state.pth
20240814-18:00:53 --- epoch 465 ----------------------------------------
20240814-18:00:53 current_test_accuracies 0.9093 0.9508 0.9483 0.9494 0.9468
20240814-18:00:53 training model 0
20240814-18:00:53 training model 4
20240814-18:04:38 train_perplexity 465 model 0 1.1702582829699262
20240814-18:04:39 test_perplexity 465 model 0 1.173248478853785
20240814-18:04:41 train_perplexity 465 model 4 1.170113193600745
20240814-18:04:43 test_perplexity 465 model 4 1.1721515996477512
20240814-18:05:24 test_accuracy 465 model 0 val 761 / 803
20240814-18:05:29 test_accuracy 465 model 4 val 737 / 787
20240814-18:05:31 wrote gpt_000.pth
20240814-18:05:31 wrote gpt_004.pth
20240814-18:05:44 wrote non_validated_0465_00.png
20240814-18:05:57 wrote non_validated_0465_04.png
20240814-18:05:57 wrote state.pth
20240814-18:05:57 --- epoch 466 ----------------------------------------
20240814-18:05:57 current_test_accuracies 0.9477 0.9508 0.9483 0.9494 0.9365
20240814-18:05:57 training model 4
20240814-18:05:57 training model 0
20240814-18:09:41 train_perplexity 466 model 4 1.170130968280085
20240814-18:09:43 test_perplexity 466 model 4 1.177686528807135
20240814-18:09:44 train_perplexity 466 model 0 1.170750185490446
20240814-18:09:46 test_perplexity 466 model 0 1.1717856470829529
20240814-18:10:28 test_accuracy 466 model 4 val 761 / 808
20240814-18:10:30 test_accuracy 466 model 0 val 750 / 801
20240814-18:10:32 wrote gpt_004.pth
20240814-18:10:33 wrote gpt_000.pth
20240814-18:10:46 wrote non_validated_0466_04.png
20240814-18:10:59 wrote non_validated_0466_00.png
20240814-18:10:59 wrote state.pth
20240814-18:10:59 --- epoch 467 ----------------------------------------
20240814-18:10:59 current_test_accuracies 0.9363 0.9508 0.9483 0.9494 0.9418
20240814-18:10:59 training model 0
20240814-18:10:59 training model 4
20240814-18:14:43 train_perplexity 467 model 0 1.1707165600819442
20240814-18:14:45 test_perplexity 467 model 0 1.1755856185085647
20240814-18:14:46 train_perplexity 467 model 4 1.1699225698616225
20240814-18:14:48 test_perplexity 467 model 4 1.172003688927005
20240814-18:15:32 test_accuracy 467 model 0 val 755 / 822
20240814-18:15:32 test_accuracy 467 model 4 val 777 / 804
20240814-18:15:35 wrote gpt_000.pth
20240814-18:15:35 wrote gpt_004.pth
20240814-18:15:48 wrote non_validated_0467_00.png
20240814-18:16:01 wrote non_validated_0467_04.png
20240814-18:16:01 wrote state.pth
20240814-18:16:01 --- epoch 468 ----------------------------------------
20240814-18:16:01 current_test_accuracies 0.9185 0.9508 0.9483 0.9494 0.9664
20240814-18:16:01 training model 0
20240814-18:16:01 training model 2
20240814-18:19:46 train_perplexity 468 model 0 1.1707866639356515
20240814-18:19:48 train_perplexity 468 model 2 1.1706497177687747
20240814-18:19:48 test_perplexity 468 model 0 1.1730356026753845
20240814-18:19:50 test_perplexity 468 model 2 1.170098085866299
20240814-18:20:37 test_accuracy 468 model 2 val 721 / 779
20240814-18:20:38 test_accuracy 468 model 0 val 750 / 799
20240814-18:20:40 wrote gpt_000.pth
20240814-18:20:41 wrote gpt_002.pth
20240814-18:20:54 wrote non_validated_0468_00.png
20240814-18:21:07 wrote non_validated_0468_02.png
20240814-18:21:07 wrote state.pth
20240814-18:21:07 --- epoch 469 ----------------------------------------
20240814-18:21:07 current_test_accuracies 0.9387 0.9508 0.9255 0.9494 0.9664
20240814-18:21:07 training model 2
20240814-18:21:07 training model 0
20240814-18:24:51 train_perplexity 469 model 2 1.1705071651671404
20240814-18:24:53 test_perplexity 469 model 2 1.1726605654411295
20240814-18:24:53 train_perplexity 469 model 0 1.1703945549627275
20240814-18:24:56 test_perplexity 469 model 0 1.1724616936284529
20240814-18:25:39 test_accuracy 469 model 2 val 766 / 803
20240814-18:25:42 test_accuracy 469 model 0 val 741 / 787
20240814-18:25:44 wrote gpt_002.pth
20240814-18:25:45 wrote gpt_000.pth
20240814-18:25:58 wrote non_validated_0469_02.png
20240814-18:26:11 wrote non_validated_0469_00.png
20240814-18:26:11 wrote state.pth
20240814-18:26:11 --- epoch 470 ----------------------------------------
20240814-18:26:11 current_test_accuracies 0.9416 0.9508 0.9539 0.9494 0.9664
20240814-18:26:11 training model 0
20240814-18:26:11 training model 3
20240814-18:29:55 train_perplexity 470 model 0 1.1704505933855642
20240814-18:29:57 test_perplexity 470 model 0 1.1736877801379837
20240814-18:29:57 train_perplexity 470 model 3 1.1701192424147953
20240814-18:30:00 test_perplexity 470 model 3 1.1733817785203464
20240814-18:30:41 test_accuracy 470 model 0 val 754 / 811
20240814-18:30:43 test_accuracy 470 model 3 val 759 / 806
20240814-18:30:45 wrote gpt_000.pth
20240814-18:30:46 wrote gpt_003.pth
20240814-18:30:59 wrote non_validated_0470_00.png
20240814-18:31:12 wrote non_validated_0470_03.png
20240814-18:31:12 wrote state.pth
20240814-18:31:12 --- epoch 471 ----------------------------------------
20240814-18:31:12 current_test_accuracies 0.9297 0.9508 0.9539 0.9417 0.9664
20240814-18:31:12 training model 0
20240814-18:31:12 training model 3
20240814-18:34:57 train_perplexity 471 model 0 1.1706844208460636
20240814-18:34:59 test_perplexity 471 model 0 1.1711661931893684
20240814-18:34:59 train_perplexity 471 model 3 1.169794530840101
20240814-18:35:01 test_perplexity 471 model 3 1.1704252284485126
20240814-18:35:46 test_accuracy 471 model 0 val 729 / 788
20240814-18:35:49 test_accuracy 471 model 3 val 745 / 792
20240814-18:35:51 wrote gpt_000.pth
20240814-18:35:51 wrote gpt_003.pth
20240814-18:36:04 wrote non_validated_0471_00.png
20240814-18:36:17 wrote non_validated_0471_03.png
20240814-18:36:17 wrote state.pth
20240814-18:36:17 --- epoch 472 ----------------------------------------
20240814-18:36:17 current_test_accuracies 0.9251 0.9508 0.9539 0.9407 0.9664
20240814-18:36:17 training model 0
20240814-18:36:17 training model 3
20240814-18:40:02 train_perplexity 472 model 0 1.170590907155337
20240814-18:40:04 test_perplexity 472 model 0 1.1745052606133157
20240814-18:40:04 train_perplexity 472 model 3 1.1698851545639806
20240814-18:40:06 test_perplexity 472 model 3 1.1742074592923182
20240814-18:40:54 test_accuracy 472 model 0 val 740 / 789
20240814-18:40:55 test_accuracy 472 model 3 val 751 / 797
20240814-18:40:57 wrote gpt_000.pth
20240814-18:40:58 wrote gpt_003.pth
20240814-18:41:11 wrote non_validated_0472_00.png
20240814-18:41:24 wrote non_validated_0472_03.png
20240814-18:41:24 wrote state.pth
20240814-18:41:24 --- epoch 473 ----------------------------------------
20240814-18:41:24 current_test_accuracies 0.9379 0.9508 0.9539 0.9423 0.9664
20240814-18:41:24 training model 0
20240814-18:41:24 training model 3
20240814-18:45:08 train_perplexity 473 model 0 1.1706861815047465
20240814-18:45:10 test_perplexity 473 model 0 1.1750304945420031
20240814-18:45:10 train_perplexity 473 model 3 1.1700282527718202
20240814-18:45:13 test_perplexity 473 model 3 1.1756837381912155
20240814-18:45:56 test_accuracy 473 model 0 val 751 / 807
20240814-18:45:57 test_accuracy 473 model 3 val 764 / 804
20240814-18:45:59 wrote gpt_000.pth
20240814-18:46:00 wrote gpt_003.pth
20240814-18:46:13 wrote non_validated_0473_00.png
20240814-18:46:26 wrote non_validated_0473_03.png
20240814-18:46:26 wrote state.pth
20240814-18:46:26 --- epoch 474 ----------------------------------------
20240814-18:46:26 current_test_accuracies 0.9306 0.9508 0.9539 0.9502 0.9664
20240814-18:46:26 training model 0
20240814-18:46:26 training model 3
20240814-18:50:11 train_perplexity 474 model 0 1.1704278145140217
20240814-18:50:13 test_perplexity 474 model 0 1.1721498704734536
20240814-18:50:13 train_perplexity 474 model 3 1.169870059176438
20240814-18:50:15 test_perplexity 474 model 3 1.1717800539121075
20240814-18:51:01 test_accuracy 474 model 0 val 747 / 793
20240814-18:51:02 test_accuracy 474 model 3 val 742 / 786
20240814-18:51:04 wrote gpt_000.pth
20240814-18:51:05 wrote gpt_003.pth
20240814-18:51:18 wrote non_validated_0474_00.png
20240814-18:51:31 wrote non_validated_0474_03.png
20240814-18:51:31 wrote state.pth
20240814-18:51:31 --- epoch 475 ----------------------------------------
20240814-18:51:31 current_test_accuracies 0.9420 0.9508 0.9539 0.9440 0.9664
20240814-18:51:31 training model 0
20240814-18:51:31 training model 3
20240814-18:55:16 train_perplexity 475 model 0 1.1706198640757075
20240814-18:55:17 test_perplexity 475 model 0 1.1701005085760225
20240814-18:55:18 train_perplexity 475 model 3 1.1698666972514606
20240814-18:55:20 test_perplexity 475 model 3 1.1740736533798306
20240814-18:56:04 test_accuracy 475 model 0 val 741 / 787
20240814-18:56:05 test_accuracy 475 model 3 val 768 / 818
20240814-18:56:08 wrote gpt_000.pth
20240814-18:56:08 wrote gpt_003.pth
20240814-18:56:21 wrote non_validated_0475_00.png
20240814-18:56:34 wrote non_validated_0475_03.png
20240814-18:56:35 wrote state.pth
20240814-18:56:35 --- epoch 476 ----------------------------------------
20240814-18:56:35 current_test_accuracies 0.9416 0.9508 0.9539 0.9389 0.9664
20240814-18:56:35 training model 3
20240814-18:56:35 training model 0
20240814-19:00:20 train_perplexity 476 model 3 1.1694364951267628
20240814-19:00:21 train_perplexity 476 model 0 1.1700473208008022
20240814-19:00:22 test_perplexity 476 model 3 1.1754172689987799
20240814-19:00:24 test_perplexity 476 model 0 1.1738341839816193
20240814-19:01:11 test_accuracy 476 model 0 val 737 / 794
20240814-19:01:12 test_accuracy 476 model 3 val 753 / 797
20240814-19:01:14 wrote gpt_003.pth
20240814-19:01:15 wrote gpt_000.pth
20240814-19:01:28 wrote non_validated_0476_03.png
20240814-19:01:41 wrote non_validated_0476_00.png
20240814-19:01:41 wrote state.pth
20240814-19:01:41 --- epoch 477 ----------------------------------------
20240814-19:01:41 current_test_accuracies 0.9282 0.9508 0.9539 0.9448 0.9664
20240814-19:01:41 training model 0
20240814-19:01:41 training model 3
20240814-19:05:24 train_perplexity 477 model 0 1.1703282369197852
20240814-19:05:26 test_perplexity 477 model 0 1.1738825747554462
20240814-19:05:27 train_perplexity 477 model 3 1.1696488174881965
20240814-19:05:30 test_perplexity 477 model 3 1.171172815705698
20240814-19:06:14 test_accuracy 477 model 3 val 766 / 811
20240814-19:06:16 test_accuracy 477 model 0 val 742 / 784
20240814-19:06:18 wrote gpt_000.pth
20240814-19:06:18 wrote gpt_003.pth
20240814-19:06:31 wrote non_validated_0477_00.png
20240814-19:06:44 wrote non_validated_0477_03.png
20240814-19:06:44 wrote state.pth
20240814-19:06:44 --- epoch 478 ----------------------------------------
20240814-19:06:44 current_test_accuracies 0.9464 0.9508 0.9539 0.9445 0.9664
20240814-19:06:44 training model 3
20240814-19:06:44 training model 0
20240814-19:10:29 train_perplexity 478 model 3 1.1696729137203634
20240814-19:10:31 test_perplexity 478 model 3 1.174377640540598
20240814-19:10:31 train_perplexity 478 model 0 1.1704854749230238
20240814-19:10:33 test_perplexity 478 model 0 1.1729922318010517
20240814-19:11:16 test_accuracy 478 model 0 val 751 / 802
20240814-19:11:18 test_accuracy 478 model 3 val 753 / 816
20240814-19:11:19 wrote gpt_003.pth
20240814-19:11:20 wrote gpt_000.pth
20240814-19:11:33 wrote non_validated_0478_03.png
20240814-19:11:46 wrote non_validated_0478_00.png
20240814-19:11:46 wrote state.pth
20240814-19:11:46 --- epoch 479 ----------------------------------------
20240814-19:11:46 current_test_accuracies 0.9364 0.9508 0.9539 0.9228 0.9664
20240814-19:11:46 training model 3
20240814-19:11:46 training model 0
20240814-19:15:31 train_perplexity 479 model 3 1.1693019389657724
20240814-19:15:32 test_perplexity 479 model 3 1.1728704561859522
20240814-19:15:33 train_perplexity 479 model 0 1.1702485834541592
20240814-19:15:35 test_perplexity 479 model 0 1.1734718245089628
20240814-19:16:19 test_accuracy 479 model 3 val 756 / 813
20240814-19:16:20 test_accuracy 479 model 0 val 767 / 818
20240814-19:16:22 wrote gpt_003.pth
20240814-19:16:22 wrote gpt_000.pth
20240814-19:16:35 wrote non_validated_0479_03.png
20240814-19:16:48 wrote non_validated_0479_00.png
20240814-19:16:48 wrote state.pth
20240814-19:16:48 --- epoch 480 ----------------------------------------
20240814-19:16:48 current_test_accuracies 0.9377 0.9508 0.9539 0.9299 0.9664
20240814-19:16:48 training model 3
20240814-19:16:48 training model 0
20240814-19:20:32 train_perplexity 480 model 3 1.169397375183183
20240814-19:20:34 test_perplexity 480 model 3 1.170940976194747
20240814-19:20:35 train_perplexity 480 model 0 1.1702027524688665
20240814-19:20:37 test_perplexity 480 model 0 1.1711269078085542
20240814-19:21:24 test_accuracy 480 model 3 val 741 / 789
20240814-19:21:25 test_accuracy 480 model 0 val 744 / 798
20240814-19:21:26 wrote gpt_003.pth
20240814-19:21:27 wrote gpt_000.pth
20240814-19:21:40 wrote non_validated_0480_03.png
20240814-19:21:53 wrote non_validated_0480_00.png
20240814-19:21:53 wrote state.pth
20240814-19:21:53 --- epoch 481 ----------------------------------------
20240814-19:21:53 current_test_accuracies 0.9323 0.9508 0.9539 0.9392 0.9664
20240814-19:21:53 training model 0
20240814-19:21:53 training model 3
20240814-19:25:37 train_perplexity 481 model 0 1.169737151207131
20240814-19:25:39 test_perplexity 481 model 0 1.1732798188763658
20240814-19:25:40 train_perplexity 481 model 3 1.1693558727242461
20240814-19:25:42 test_perplexity 481 model 3 1.1727531048652908
20240814-19:26:25 test_accuracy 481 model 0 val 767 / 812
20240814-19:26:27 test_accuracy 481 model 3 val 787 / 822
20240814-19:26:29 wrote gpt_000.pth
20240814-19:26:29 wrote gpt_003.pth
20240814-19:26:42 wrote non_validated_0481_00.png
20240814-19:26:55 wrote non_validated_0481_03.png
20240814-19:26:56 wrote state.pth
20240814-19:26:56 --- epoch 482 ----------------------------------------
20240814-19:26:56 current_test_accuracies 0.9446 0.9508 0.9539 0.9574 0.9664
20240814-19:26:56 training model 0
20240814-19:26:56 training model 1
20240814-19:30:40 train_perplexity 482 model 0 1.1703159666244696
20240814-19:30:42 test_perplexity 482 model 0 1.1731935068992627
20240814-19:30:42 train_perplexity 482 model 1 1.1716108722446528
20240814-19:30:44 test_perplexity 482 model 1 1.172643268052034
20240814-19:31:31 test_accuracy 482 model 0 val 744 / 798
20240814-19:31:32 test_accuracy 482 model 1 val 760 / 798
20240814-19:31:34 wrote gpt_000.pth
20240814-19:31:35 wrote gpt_001.pth
20240814-19:31:47 wrote non_validated_0482_00.png
20240814-19:32:00 wrote non_validated_0482_01.png
20240814-19:32:00 wrote state.pth
20240814-19:32:00 --- epoch 483 ----------------------------------------
20240814-19:32:00 current_test_accuracies 0.9323 0.9524 0.9539 0.9574 0.9664
20240814-19:32:00 training model 0
20240814-19:32:00 training model 1
20240814-19:35:45 train_perplexity 483 model 0 1.1695948164683103
20240814-19:35:47 test_perplexity 483 model 0 1.171228217429666
20240814-19:35:47 train_perplexity 483 model 1 1.1717622335245137
20240814-19:35:49 test_perplexity 483 model 1 1.170795302623411
20240814-19:36:32 test_accuracy 483 model 0 val 773 / 812
20240814-19:36:35 test_accuracy 483 model 1 val 737 / 784
20240814-19:36:37 wrote gpt_000.pth
20240814-19:36:38 wrote gpt_001.pth
20240814-19:36:50 wrote non_validated_0483_00.png
20240814-19:37:03 wrote non_validated_0483_01.png
20240814-19:37:04 wrote state.pth
20240814-19:37:04 --- epoch 484 ----------------------------------------
20240814-19:37:04 current_test_accuracies 0.9520 0.9401 0.9539 0.9574 0.9664
20240814-19:37:04 training model 1
20240814-19:37:04 training model 0
20240814-19:40:48 train_perplexity 484 model 1 1.1717494356489773
20240814-19:40:50 test_perplexity 484 model 1 1.1712239179746524
20240814-19:40:50 train_perplexity 484 model 0 1.1693767143173375
20240814-19:40:53 test_perplexity 484 model 0 1.1708477837424993
20240814-19:41:38 test_accuracy 484 model 1 val 727 / 782
20240814-19:41:40 test_accuracy 484 model 0 val 730 / 778
20240814-19:41:42 wrote gpt_001.pth
20240814-19:41:43 wrote gpt_000.pth
20240814-19:41:56 wrote non_validated_0484_01.png
20240814-19:42:09 wrote non_validated_0484_00.png
20240814-19:42:09 wrote state.pth
20240814-19:42:09 --- epoch 485 ----------------------------------------
20240814-19:42:09 current_test_accuracies 0.9383 0.9297 0.9539 0.9574 0.9664
20240814-19:42:09 training model 1
20240814-19:42:09 training model 0
20240814-19:45:53 train_perplexity 485 model 1 1.1716026826263688
20240814-19:45:55 test_perplexity 485 model 1 1.1725998557696462
20240814-19:45:57 train_perplexity 485 model 0 1.169631930737305
20240814-19:45:59 test_perplexity 485 model 0 1.1746826074336856
20240814-19:46:41 test_accuracy 485 model 1 val 774 / 821
20240814-19:46:44 test_accuracy 485 model 0 val 749 / 792
20240814-19:46:46 wrote gpt_001.pth
20240814-19:46:47 wrote gpt_000.pth
20240814-19:47:00 wrote non_validated_0485_01.png
20240814-19:47:13 wrote non_validated_0485_00.png
20240814-19:47:13 wrote state.pth
20240814-19:47:13 --- epoch 486 ----------------------------------------
20240814-19:47:13 current_test_accuracies 0.9457 0.9428 0.9539 0.9574 0.9664
20240814-19:47:13 training model 1
20240814-19:47:13 training model 0
20240814-19:50:57 train_perplexity 486 model 1 1.1713558256245307
20240814-19:50:59 test_perplexity 486 model 1 1.1721423237054902
20240814-19:51:00 train_perplexity 486 model 0 1.1699796035127494
20240814-19:51:02 test_perplexity 486 model 0 1.1726726365452977
20240814-19:51:44 test_accuracy 486 model 1 val 757 / 801
20240814-19:51:48 test_accuracy 486 model 0 val 740 / 787
20240814-19:51:50 wrote gpt_001.pth
20240814-19:51:50 wrote gpt_000.pth
20240814-19:52:03 wrote non_validated_0486_01.png
20240814-19:52:16 wrote non_validated_0486_00.png
20240814-19:52:16 wrote state.pth
20240814-19:52:16 --- epoch 487 ----------------------------------------
20240814-19:52:16 current_test_accuracies 0.9403 0.9451 0.9539 0.9574 0.9664
20240814-19:52:16 training model 0
20240814-19:52:16 training model 1
20240814-19:56:01 train_perplexity 487 model 0 1.1699302310937834
20240814-19:56:02 test_perplexity 487 model 0 1.171380329424016
20240814-19:56:03 train_perplexity 487 model 1 1.1717646209608858
20240814-19:56:05 test_perplexity 487 model 1 1.168578491224867
20240814-19:56:53 test_accuracy 487 model 0 val 755 / 799
20240814-19:56:54 test_accuracy 487 model 1 val 749 / 790
20240814-19:56:56 wrote gpt_000.pth
20240814-19:56:57 wrote gpt_001.pth
20240814-19:57:09 wrote non_validated_0487_00.png
20240814-19:57:22 wrote non_validated_0487_01.png
20240814-19:57:22 wrote state.pth
20240814-19:57:22 --- epoch 488 ----------------------------------------
20240814-19:57:22 current_test_accuracies 0.9449 0.9481 0.9539 0.9574 0.9664
20240814-19:57:22 training model 0
20240814-19:57:22 training model 1
20240814-20:01:07 train_perplexity 488 model 0 1.1698578304832512
20240814-20:01:08 test_perplexity 488 model 0 1.1722221560645258
20240814-20:01:09 train_perplexity 488 model 1 1.1714562234946133
20240814-20:01:11 test_perplexity 488 model 1 1.1718345326983863
20240814-20:01:56 test_accuracy 488 model 0 val 730 / 778
20240814-20:01:59 test_accuracy 488 model 1 val 755 / 791
20240814-20:02:01 wrote gpt_000.pth
20240814-20:02:01 wrote gpt_001.pth
20240814-20:02:14 wrote non_validated_0488_00.png
20240814-20:02:27 wrote non_validated_0488_01.png
20240814-20:02:27 wrote state.pth
20240814-20:02:27 --- epoch 489 ----------------------------------------
20240814-20:02:27 current_test_accuracies 0.9383 0.9545 0.9539 0.9574 0.9664
20240814-20:02:27 training model 0
20240814-20:02:27 training model 2
20240814-20:06:11 train_perplexity 489 model 0 1.1697332935298912
20240814-20:06:13 test_perplexity 489 model 0 1.17298460576156
20240814-20:06:14 train_perplexity 489 model 2 1.170300809993626
20240814-20:06:16 test_perplexity 489 model 2 1.1693283785507873
20240814-20:06:59 test_accuracy 489 model 0 val 734 / 805
20240814-20:07:03 test_accuracy 489 model 2 val 739 / 797
20240814-20:07:05 wrote gpt_000.pth
20240814-20:07:05 wrote gpt_002.pth
20240814-20:07:18 wrote non_validated_0489_00.png
20240814-20:07:31 wrote non_validated_0489_02.png
20240814-20:07:31 wrote state.pth
20240814-20:07:31 --- epoch 490 ----------------------------------------
20240814-20:07:31 current_test_accuracies 0.9118 0.9545 0.9272 0.9574 0.9664
20240814-20:07:31 training model 0
20240814-20:07:31 training model 2
20240814-20:11:16 train_perplexity 490 model 0 1.1693500310443674
20240814-20:11:17 test_perplexity 490 model 0 1.172039295947847
20240814-20:11:18 train_perplexity 490 model 2 1.170734429316062
20240814-20:11:20 test_perplexity 490 model 2 1.173738593807058
20240814-20:12:04 test_accuracy 490 model 0 val 736 / 777
20240814-20:12:07 test_accuracy 490 model 2 val 744 / 796
20240814-20:12:09 wrote gpt_000.pth
20240814-20:12:10 wrote gpt_002.pth
20240814-20:12:23 wrote non_validated_0490_00.png
20240814-20:12:36 wrote non_validated_0490_02.png
20240814-20:12:36 wrote state.pth
20240814-20:12:36 --- epoch 491 ----------------------------------------
20240814-20:12:36 current_test_accuracies 0.9472 0.9545 0.9347 0.9574 0.9664
20240814-20:12:36 training model 2
20240814-20:12:36 training model 0
20240814-20:16:20 train_perplexity 491 model 2 1.1705104371170776
20240814-20:16:22 test_perplexity 491 model 2 1.1728432861147493
20240814-20:16:23 train_perplexity 491 model 0 1.1697019512753846
20240814-20:16:25 test_perplexity 491 model 0 1.1694886033820573
20240814-20:17:10 test_accuracy 491 model 2 val 734 / 783
20240814-20:17:12 test_accuracy 491 model 0 val 744 / 789
20240814-20:17:14 wrote gpt_002.pth
20240814-20:17:14 wrote gpt_000.pth
20240814-20:17:27 wrote non_validated_0491_02.png
20240814-20:17:40 wrote non_validated_0491_00.png
20240814-20:17:40 wrote state.pth
20240814-20:17:40 --- epoch 492 ----------------------------------------
20240814-20:17:40 current_test_accuracies 0.9430 0.9545 0.9374 0.9574 0.9664
20240814-20:17:40 training model 2
20240814-20:17:40 training model 0
20240814-20:21:25 train_perplexity 492 model 2 1.1698380205443724
20240814-20:21:26 test_perplexity 492 model 2 1.1730044465893155
20240814-20:21:27 train_perplexity 492 model 0 1.169700454100913
20240814-20:21:29 test_perplexity 492 model 0 1.1734906925919477
20240814-20:22:14 test_accuracy 492 model 0 val 761 / 801
20240814-20:22:16 test_accuracy 492 model 2 val 732 / 787
20240814-20:22:18 wrote gpt_002.pth
20240814-20:22:18 wrote gpt_000.pth
20240814-20:22:31 wrote non_validated_0492_02.png
20240814-20:22:44 wrote non_validated_0492_00.png
20240814-20:22:44 wrote state.pth
20240814-20:22:44 --- epoch 493 ----------------------------------------
20240814-20:22:44 current_test_accuracies 0.9501 0.9545 0.9301 0.9574 0.9664
20240814-20:22:44 training model 2
20240814-20:22:44 training model 0
20240814-20:26:29 train_perplexity 493 model 2 1.1704736657979509
20240814-20:26:31 test_perplexity 493 model 2 1.1706444942171197
20240814-20:26:31 train_perplexity 493 model 0 1.169165782592539
20240814-20:26:34 test_perplexity 493 model 0 1.1738614141782313
20240814-20:27:17 test_accuracy 493 model 2 val 768 / 805
20240814-20:27:18 test_accuracy 493 model 0 val 750 / 805
20240814-20:27:20 wrote gpt_002.pth
20240814-20:27:21 wrote gpt_000.pth
20240814-20:27:34 wrote non_validated_0493_02.png
20240814-20:27:47 wrote non_validated_0493_00.png
20240814-20:27:47 wrote state.pth
20240814-20:27:47 --- epoch 494 ----------------------------------------
20240814-20:27:47 current_test_accuracies 0.9317 0.9545 0.9540 0.9574 0.9664
20240814-20:27:47 training model 0
20240814-20:27:47 training model 2
20240814-20:31:31 train_perplexity 494 model 0 1.1697132999223734
20240814-20:31:33 test_perplexity 494 model 0 1.173306537055271
20240814-20:31:33 train_perplexity 494 model 2 1.1707959042451974
20240814-20:31:36 test_perplexity 494 model 2 1.1719101468975839
20240814-20:32:24 test_accuracy 494 model 0 val 751 / 798
20240814-20:32:24 test_accuracy 494 model 2 val 730 / 775
20240814-20:32:26 wrote gpt_000.pth
20240814-20:32:27 wrote gpt_002.pth
20240814-20:32:40 wrote non_validated_0494_00.png
20240814-20:32:53 wrote non_validated_0494_02.png
20240814-20:32:53 wrote state.pth
20240814-20:32:53 --- epoch 495 ----------------------------------------
20240814-20:32:53 current_test_accuracies 0.9411 0.9545 0.9419 0.9574 0.9664
20240814-20:32:53 training model 0
20240814-20:32:53 training model 2
20240814-20:36:37 train_perplexity 495 model 0 1.1695829467799752
20240814-20:36:39 test_perplexity 495 model 0 1.1735470923120372
20240814-20:36:40 train_perplexity 495 model 2 1.1702850257581976
20240814-20:36:42 test_perplexity 495 model 2 1.173097894605471
20240814-20:37:24 test_accuracy 495 model 0 val 744 / 803
20240814-20:37:28 test_accuracy 495 model 2 val 743 / 793
20240814-20:37:30 wrote gpt_000.pth
20240814-20:37:31 wrote gpt_002.pth
20240814-20:37:44 wrote non_validated_0495_00.png
20240814-20:37:57 wrote non_validated_0495_02.png
20240814-20:37:57 wrote state.pth
20240814-20:37:57 --- epoch 496 ----------------------------------------
20240814-20:37:57 current_test_accuracies 0.9265 0.9545 0.9369 0.9574 0.9664
20240814-20:37:57 training model 0
20240814-20:37:57 training model 2
20240814-20:41:42 train_perplexity 496 model 0 1.1697819506318514
20240814-20:41:43 test_perplexity 496 model 0 1.1741925667687152
20240814-20:41:44 train_perplexity 496 model 2 1.1702541132894577
20240814-20:41:46 test_perplexity 496 model 2 1.174710362317844
20240814-20:42:30 test_accuracy 496 model 2 val 756 / 809
20240814-20:42:33 test_accuracy 496 model 0 val 739 / 783
20240814-20:42:34 wrote gpt_000.pth
20240814-20:42:35 wrote gpt_002.pth
20240814-20:42:48 wrote non_validated_0496_00.png
20240814-20:43:01 wrote non_validated_0496_02.png
20240814-20:43:01 wrote state.pth
20240814-20:43:01 --- epoch 497 ----------------------------------------
20240814-20:43:01 current_test_accuracies 0.9438 0.9545 0.9345 0.9574 0.9664
20240814-20:43:01 training model 2
20240814-20:43:01 training model 0
20240814-20:46:45 train_perplexity 497 model 2 1.1702816823571733
20240814-20:46:47 test_perplexity 497 model 2 1.17420184318864
20240814-20:46:48 train_perplexity 497 model 0 1.169254729397841
20240814-20:46:50 test_perplexity 497 model 0 1.172694069701531
20240814-20:47:36 test_accuracy 497 model 2 val 744 / 797
20240814-20:47:38 test_accuracy 497 model 0 val 746 / 798
20240814-20:47:39 wrote gpt_002.pth
20240814-20:47:40 wrote gpt_000.pth
20240814-20:47:53 wrote non_validated_0497_02.png
20240814-20:48:06 wrote non_validated_0497_00.png
20240814-20:48:06 wrote state.pth
20240814-20:48:06 --- epoch 498 ----------------------------------------
20240814-20:48:06 current_test_accuracies 0.9348 0.9545 0.9335 0.9574 0.9664
20240814-20:48:06 training model 2
20240814-20:48:06 training model 0
20240814-20:51:50 train_perplexity 498 model 2 1.1699859600408296
20240814-20:51:52 test_perplexity 498 model 2 1.174586469469486
20240814-20:51:53 train_perplexity 498 model 0 1.1688672020877906
20240814-20:51:55 test_perplexity 498 model 0 1.1733373444896753
20240814-20:52:39 test_accuracy 498 model 2 val 773 / 815
20240814-20:52:40 test_accuracy 498 model 0 val 764 / 802
20240814-20:52:42 wrote gpt_002.pth
20240814-20:52:42 wrote gpt_000.pth
20240814-20:52:55 wrote non_validated_0498_02.png
20240814-20:53:09 wrote non_validated_0498_00.png
20240814-20:53:09 wrote state.pth
20240814-20:53:09 --- epoch 499 ----------------------------------------
20240814-20:53:09 current_test_accuracies 0.9526 0.9545 0.9485 0.9574 0.9664
20240814-20:53:09 training model 2
20240814-20:53:09 training model 0
20240814-20:56:53 train_perplexity 499 model 2 1.1701826940903437
20240814-20:56:55 train_perplexity 499 model 0 1.1690843486851759
20240814-20:56:55 test_perplexity 499 model 2 1.1701535596790817
20240814-20:56:58 test_perplexity 499 model 0 1.173734652864105
20240814-20:57:43 test_accuracy 499 model 0 val 760 / 820
20240814-20:57:45 test_accuracy 499 model 2 val 742 / 791
20240814-20:57:47 wrote gpt_002.pth
20240814-20:57:47 wrote gpt_000.pth
20240814-20:58:00 wrote non_validated_0499_02.png
20240814-20:58:13 wrote non_validated_0499_00.png
20240814-20:58:14 wrote state.pth
20240814-20:58:14 --- epoch 500 ----------------------------------------
20240814-20:58:14 current_test_accuracies 0.9268 0.9545 0.9381 0.9574 0.9664
20240814-20:58:14 training model 0
20240814-20:58:14 training model 2
20240814-21:01:59 train_perplexity 500 model 0 1.1691262985505624
20240814-21:02:00 train_perplexity 500 model 2 1.169351868853331
20240814-21:02:01 test_perplexity 500 model 0 1.1729427141173852
20240814-21:02:03 test_perplexity 500 model 2 1.1713934599665257
20240814-21:02:49 test_accuracy 500 model 0 val 737 / 782
20240814-21:02:51 test_accuracy 500 model 2 val 739 / 796
20240814-21:02:53 wrote gpt_000.pth
20240814-21:02:54 wrote gpt_002.pth
20240814-21:03:07 wrote non_validated_0500_00.png
20240814-21:03:20 wrote non_validated_0500_02.png
20240814-21:03:20 wrote state.pth
20240814-21:03:20 --- epoch 501 ----------------------------------------
20240814-21:03:20 current_test_accuracies 0.9425 0.9545 0.9284 0.9574 0.9664
20240814-21:03:20 training model 2
20240814-21:03:20 training model 0
20240814-21:07:04 train_perplexity 501 model 2 1.169934804178263
20240814-21:07:06 test_perplexity 501 model 2 1.171337453925763
20240814-21:07:07 train_perplexity 501 model 0 1.1689366917828767
20240814-21:07:09 test_perplexity 501 model 0 1.172067868184725
20240814-21:07:55 test_accuracy 501 model 2 val 745 / 791
20240814-21:07:57 test_accuracy 501 model 0 val 746 / 793
20240814-21:07:59 wrote gpt_002.pth
20240814-21:07:59 wrote gpt_000.pth
20240814-21:08:12 wrote non_validated_0501_02.png
20240814-21:08:25 wrote non_validated_0501_00.png
20240814-21:08:25 wrote state.pth
20240814-21:08:25 --- epoch 502 ----------------------------------------
20240814-21:08:25 current_test_accuracies 0.9407 0.9545 0.9418 0.9574 0.9664
20240814-21:08:25 training model 0
20240814-21:08:25 training model 2
20240814-21:12:09 train_perplexity 502 model 0 1.1690015432866299
20240814-21:12:11 test_perplexity 502 model 0 1.174942753806408
20240814-21:12:12 train_perplexity 502 model 2 1.1702163622976463
20240814-21:12:15 test_perplexity 502 model 2 1.1746407247240074
20240814-21:12:58 test_accuracy 502 model 0 val 754 / 810
20240814-21:13:00 test_accuracy 502 model 2 val 752 / 794
20240814-21:13:02 wrote gpt_000.pth
20240814-21:13:03 wrote gpt_002.pth
20240814-21:13:16 wrote non_validated_0502_00.png
20240814-21:13:29 wrote non_validated_0502_02.png
20240814-21:13:29 wrote state.pth
20240814-21:13:29 --- epoch 503 ----------------------------------------
20240814-21:13:29 current_test_accuracies 0.9309 0.9545 0.9471 0.9574 0.9664
20240814-21:13:29 training model 0
20240814-21:13:29 training model 2
20240814-21:17:13 train_perplexity 503 model 0 1.1687706551675279
20240814-21:17:15 test_perplexity 503 model 0 1.174159904573119
20240814-21:17:16 train_perplexity 503 model 2 1.1697969293127468
20240814-21:17:18 test_perplexity 503 model 2 1.1717937638414868
20240814-21:18:02 test_accuracy 503 model 0 val 778 / 822
20240814-21:18:04 test_accuracy 503 model 2 val 747 / 797
20240814-21:18:06 wrote gpt_000.pth
20240814-21:18:07 wrote gpt_002.pth
20240814-21:18:20 wrote non_validated_0503_00.png
20240814-21:18:33 wrote non_validated_0503_02.png
20240814-21:18:33 wrote state.pth
20240814-21:18:33 --- epoch 504 ----------------------------------------
20240814-21:18:33 current_test_accuracies 0.9465 0.9545 0.9373 0.9574 0.9664
20240814-21:18:33 training model 2
20240814-21:18:33 training model 0
20240814-21:22:17 train_perplexity 504 model 2 1.1696537155620383
20240814-21:22:19 test_perplexity 504 model 2 1.173099223125806
20240814-21:22:19 train_perplexity 504 model 0 1.1691328370044127
20240814-21:22:22 test_perplexity 504 model 0 1.1728626282047745
20240814-21:23:09 test_accuracy 504 model 0 val 730 / 786
20240814-21:23:09 test_accuracy 504 model 2 val 753 / 795
20240814-21:23:11 wrote gpt_002.pth
20240814-21:23:12 wrote gpt_000.pth
20240814-21:23:25 wrote non_validated_0504_02.png
20240814-21:23:38 wrote non_validated_0504_00.png
20240814-21:23:38 wrote state.pth
20240814-21:23:38 --- epoch 505 ----------------------------------------
20240814-21:23:38 current_test_accuracies 0.9288 0.9545 0.9472 0.9574 0.9664
20240814-21:23:38 training model 0
20240814-21:23:38 training model 2
20240814-21:27:23 train_perplexity 505 model 0 1.169227235990875
20240814-21:27:25 test_perplexity 505 model 0 1.1733022417723729
20240814-21:27:25 train_perplexity 505 model 2 1.1697475416104728
20240814-21:27:27 test_perplexity 505 model 2 1.1722011380814232
20240814-21:28:11 test_accuracy 505 model 2 val 762 / 805
20240814-21:28:13 test_accuracy 505 model 0 val 737 / 793
20240814-21:28:15 wrote gpt_000.pth
20240814-21:28:16 wrote gpt_002.pth
20240814-21:28:29 wrote non_validated_0505_00.png
20240814-21:28:42 wrote non_validated_0505_02.png
20240814-21:28:42 wrote state.pth
20240814-21:28:42 --- epoch 506 ----------------------------------------
20240814-21:28:42 current_test_accuracies 0.9294 0.9545 0.9466 0.9574 0.9664
20240814-21:28:42 training model 0
20240814-21:28:42 training model 2
20240814-21:32:26 train_perplexity 506 model 0 1.1687730082401668
20240814-21:32:28 test_perplexity 506 model 0 1.1748660891636082
20240814-21:32:28 train_perplexity 506 model 2 1.1698300383369467
20240814-21:32:31 test_perplexity 506 model 2 1.173776443361685
20240814-21:33:13 test_accuracy 506 model 0 val 764 / 809
20240814-21:33:14 test_accuracy 506 model 2 val 751 / 800
20240814-21:33:16 wrote gpt_000.pth
20240814-21:33:17 wrote gpt_002.pth
20240814-21:33:30 wrote non_validated_0506_00.png
20240814-21:33:43 wrote non_validated_0506_02.png
20240814-21:33:43 wrote state.pth
20240814-21:33:43 --- epoch 507 ----------------------------------------
20240814-21:33:43 current_test_accuracies 0.9444 0.9545 0.9388 0.9574 0.9664
20240814-21:33:43 training model 2
20240814-21:33:43 training model 0
20240814-21:37:28 train_perplexity 507 model 2 1.1693782811753186
20240814-21:37:29 test_perplexity 507 model 2 1.1738505600683122
20240814-21:37:30 train_perplexity 507 model 0 1.1689917195574813
20240814-21:37:32 test_perplexity 507 model 0 1.1749676338293824
20240814-21:38:18 test_accuracy 507 model 2 val 733 / 781
20240814-21:38:19 test_accuracy 507 model 0 val 729 / 782
20240814-21:38:21 wrote gpt_002.pth
20240814-21:38:21 wrote gpt_000.pth
20240814-21:38:34 wrote non_validated_0507_02.png
20240814-21:38:47 wrote non_validated_0507_00.png
20240814-21:38:48 wrote state.pth
20240814-21:38:48 --- epoch 508 ----------------------------------------
20240814-21:38:48 current_test_accuracies 0.9322 0.9545 0.9385 0.9574 0.9664
20240814-21:38:48 training model 0
20240814-21:38:48 training model 2
20240814-21:42:31 train_perplexity 508 model 0 1.1686977052232592
20240814-21:42:33 test_perplexity 508 model 0 1.1723269974586072
20240814-21:42:34 train_perplexity 508 model 2 1.1701072248653466
20240814-21:42:37 test_perplexity 508 model 2 1.1718645881537029
20240814-21:43:21 test_accuracy 508 model 2 val 754 / 804
20240814-21:43:22 test_accuracy 508 model 0 val 744 / 793
20240814-21:43:24 wrote gpt_000.pth
20240814-21:43:25 wrote gpt_002.pth
20240814-21:43:38 wrote non_validated_0508_00.png
20240814-21:43:51 wrote non_validated_0508_02.png
20240814-21:43:51 wrote state.pth
20240814-21:43:51 --- epoch 509 ----------------------------------------
20240814-21:43:51 current_test_accuracies 0.9382 0.9545 0.9378 0.9574 0.9664
20240814-21:43:51 training model 2
20240814-21:43:51 training model 0
20240814-21:47:35 train_perplexity 509 model 2 1.1696873630920266
20240814-21:47:37 test_perplexity 509 model 2 1.1707659811462257
20240814-21:47:38 train_perplexity 509 model 0 1.16835263469417
20240814-21:47:40 test_perplexity 509 model 0 1.1728496581466725
20240814-21:48:23 test_accuracy 509 model 0 val 763 / 804
20240814-21:48:25 test_accuracy 509 model 2 val 749 / 790
20240814-21:48:27 wrote gpt_002.pth
20240814-21:48:27 wrote gpt_000.pth
20240814-21:48:40 wrote non_validated_0509_02.png
20240814-21:48:53 wrote non_validated_0509_00.png
20240814-21:48:53 wrote state.pth
20240814-21:48:53 --- epoch 510 ----------------------------------------
20240814-21:48:53 current_test_accuracies 0.9490 0.9545 0.9481 0.9574 0.9664
20240814-21:48:53 training model 2
20240814-21:48:53 training model 0
20240814-21:52:38 train_perplexity 510 model 2 1.1693698967346524
20240814-21:52:40 train_perplexity 510 model 0 1.1678414260002985
20240814-21:52:40 test_perplexity 510 model 2 1.1730868063265039
20240814-21:52:42 test_perplexity 510 model 0 1.1732320080197036
20240814-21:53:26 test_accuracy 510 model 2 val 760 / 806
20240814-21:53:29 test_accuracy 510 model 0 val 725 / 776
20240814-21:53:31 wrote gpt_002.pth
20240814-21:53:32 wrote gpt_000.pth
20240814-21:53:45 wrote non_validated_0510_02.png
20240814-21:53:58 wrote non_validated_0510_00.png
20240814-21:53:58 wrote state.pth
20240814-21:53:58 --- epoch 511 ----------------------------------------
20240814-21:53:58 current_test_accuracies 0.9343 0.9545 0.9429 0.9574 0.9664
20240814-21:53:58 training model 0
20240814-21:53:58 training model 2
20240814-21:57:42 train_perplexity 511 model 0 1.1687586153687461
20240814-21:57:44 train_perplexity 511 model 2 1.1698483183967583
20240814-21:57:44 test_perplexity 511 model 0 1.1731207283210041
20240814-21:57:46 test_perplexity 511 model 2 1.1710523017161563
20240814-21:58:29 test_accuracy 511 model 0 val 750 / 802
20240814-21:58:32 test_accuracy 511 model 2 val 734 / 778
20240814-21:58:34 wrote gpt_000.pth
20240814-21:58:35 wrote gpt_002.pth
20240814-21:58:48 wrote non_validated_0511_00.png
20240814-21:59:01 wrote non_validated_0511_02.png
20240814-21:59:01 wrote state.pth
20240814-21:59:01 --- epoch 512 ----------------------------------------
20240814-21:59:01 current_test_accuracies 0.9352 0.9545 0.9434 0.9574 0.9664
20240814-21:59:01 training model 0
20240814-21:59:01 training model 2
20240814-22:02:46 train_perplexity 512 model 0 1.1683788999143896
20240814-22:02:47 train_perplexity 512 model 2 1.1695060919035432
20240814-22:02:48 test_perplexity 512 model 0 1.1728210559288605
20240814-22:02:50 test_perplexity 512 model 2 1.169847588716586
20240814-22:03:35 test_accuracy 512 model 0 val 750 / 802
20240814-22:03:37 test_accuracy 512 model 2 val 744 / 793
20240814-22:03:39 wrote gpt_000.pth
20240814-22:03:39 wrote gpt_002.pth
20240814-22:03:52 wrote non_validated_0512_00.png
20240814-22:04:05 wrote non_validated_0512_02.png
20240814-22:04:05 wrote state.pth
20240814-22:04:05 --- epoch 513 ----------------------------------------
20240814-22:04:05 current_test_accuracies 0.9352 0.9545 0.9382 0.9574 0.9664
20240814-22:04:05 training model 0
20240814-22:04:05 training model 2
20240814-22:07:50 train_perplexity 513 model 0 1.1685959983350778
20240814-22:07:52 train_perplexity 513 model 2 1.169454122278809
20240814-22:07:52 test_perplexity 513 model 0 1.1753020017647806
20240814-22:07:54 test_perplexity 513 model 2 1.170398283320929
20240814-22:08:39 test_accuracy 513 model 0 val 757 / 818
20240814-22:08:41 test_accuracy 513 model 2 val 746 / 787
20240814-22:08:43 wrote gpt_000.pth
20240814-22:08:44 wrote gpt_002.pth
20240814-22:08:57 wrote non_validated_0513_00.png
20240814-22:09:10 wrote non_validated_0513_02.png
20240814-22:09:10 wrote state.pth
20240814-22:09:10 --- epoch 514 ----------------------------------------
20240814-22:09:10 current_test_accuracies 0.9254 0.9545 0.9479 0.9574 0.9664
20240814-22:09:10 training model 0
20240814-22:09:10 training model 2
20240814-22:12:55 train_perplexity 514 model 0 1.168370816064416
20240814-22:12:57 test_perplexity 514 model 0 1.1742283365260662
20240814-22:12:57 train_perplexity 514 model 2 1.1691184599050495
20240814-22:12:59 test_perplexity 514 model 2 1.171428454082969
20240814-22:13:43 test_accuracy 514 model 2 val 753 / 800
20240814-22:13:46 test_accuracy 514 model 0 val 755 / 796
20240814-22:13:48 wrote gpt_000.pth
20240814-22:13:48 wrote gpt_002.pth
20240814-22:14:01 wrote non_validated_0514_00.png
20240814-22:14:14 wrote non_validated_0514_02.png
20240814-22:14:14 wrote state.pth
20240814-22:14:14 --- epoch 515 ----------------------------------------
20240814-22:14:14 current_test_accuracies 0.9485 0.9545 0.9413 0.9574 0.9664
20240814-22:14:14 training model 2
20240814-22:14:14 training model 0
20240814-22:17:58 train_perplexity 515 model 2 1.1689964935425796
20240814-22:18:00 test_perplexity 515 model 2 1.173794665680801
20240814-22:18:01 train_perplexity 515 model 0 1.1686060058041843
20240814-22:18:03 test_perplexity 515 model 0 1.1753461170067379
20240814-22:18:45 test_accuracy 515 model 2 val 753 / 804
20240814-22:18:49 test_accuracy 515 model 0 val 740 / 793
20240814-22:18:51 wrote gpt_002.pth
20240814-22:18:52 wrote gpt_000.pth
20240814-22:19:05 wrote non_validated_0515_02.png
20240814-22:19:18 wrote non_validated_0515_00.png
20240814-22:19:18 wrote state.pth
20240814-22:19:18 --- epoch 516 ----------------------------------------
20240814-22:19:18 current_test_accuracies 0.9332 0.9545 0.9366 0.9574 0.9664
20240814-22:19:18 training model 0
20240814-22:19:18 training model 2
20240814-22:23:02 train_perplexity 516 model 0 1.1681305377226205
20240814-22:23:04 train_perplexity 516 model 2 1.1693242884312085
20240814-22:23:04 test_perplexity 516 model 0 1.1718639132420654
20240814-22:23:07 test_perplexity 516 model 2 1.1753596987713797
20240814-22:23:52 test_accuracy 516 model 2 val 770 / 819
20240814-22:23:54 test_accuracy 516 model 0 val 732 / 774
20240814-22:23:56 wrote gpt_000.pth
20240814-22:23:56 wrote gpt_002.pth
20240814-22:24:09 wrote non_validated_0516_00.png
20240814-22:24:22 wrote non_validated_0516_02.png
20240814-22:24:23 wrote state.pth
20240814-22:24:23 --- epoch 517 ----------------------------------------
20240814-22:24:23 current_test_accuracies 0.9457 0.9545 0.9402 0.9574 0.9664
20240814-22:24:23 training model 2
20240814-22:24:23 training model 0
20240814-22:28:07 train_perplexity 517 model 2 1.1691112817246243
20240814-22:28:09 test_perplexity 517 model 2 1.1725659632516028
20240814-22:28:09 train_perplexity 517 model 0 1.1679316415467724
20240814-22:28:11 test_perplexity 517 model 0 1.1743774445452004
20240814-22:28:58 test_accuracy 517 model 0 val 743 / 798
20240814-22:28:59 test_accuracy 517 model 2 val 739 / 790
20240814-22:29:01 wrote gpt_002.pth
20240814-22:29:02 wrote gpt_000.pth
20240814-22:29:15 wrote non_validated_0517_02.png
20240814-22:29:28 wrote non_validated_0517_00.png
20240814-22:29:28 wrote state.pth
20240814-22:29:28 --- epoch 518 ----------------------------------------
20240814-22:29:28 current_test_accuracies 0.9311 0.9545 0.9354 0.9574 0.9664
20240814-22:29:28 training model 0
20240814-22:29:28 training model 2
20240814-22:33:13 train_perplexity 518 model 0 1.1680789948909247
20240814-22:33:15 test_perplexity 518 model 0 1.1732519260229797
20240814-22:33:15 train_perplexity 518 model 2 1.1687467012991535
20240814-22:33:17 test_perplexity 518 model 2 1.1734869732460986
20240814-22:34:03 test_accuracy 518 model 0 val 749 / 795
20240814-22:34:04 test_accuracy 518 model 2 val 751 / 796
20240814-22:34:06 wrote gpt_000.pth
20240814-22:34:07 wrote gpt_002.pth
20240814-22:34:20 wrote non_validated_0518_00.png
20240814-22:34:33 wrote non_validated_0518_02.png
20240814-22:34:33 wrote state.pth
20240814-22:34:33 --- epoch 519 ----------------------------------------
20240814-22:34:33 current_test_accuracies 0.9421 0.9545 0.9435 0.9574 0.9664
20240814-22:34:33 training model 0
20240814-22:34:33 training model 2
20240814-22:38:18 train_perplexity 519 model 0 1.1677642591162762
20240814-22:38:19 test_perplexity 519 model 0 1.1737403030251963
20240814-22:38:20 train_perplexity 519 model 2 1.1684074927239638
20240814-22:38:22 test_perplexity 519 model 2 1.170921084774025
20240814-22:39:05 test_accuracy 519 model 0 val 773 / 811
20240814-22:39:08 test_accuracy 519 model 2 val 716 / 779
20240814-22:39:10 wrote gpt_000.pth
20240814-22:39:11 wrote gpt_002.pth
20240814-22:39:24 wrote non_validated_0519_00.png
20240814-22:39:37 wrote non_validated_0519_02.png
20240814-22:39:37 wrote state.pth
20240814-22:39:37 --- epoch 520 ----------------------------------------
20240814-22:39:37 current_test_accuracies 0.9531 0.9545 0.9191 0.9574 0.9664
20240814-22:39:37 training model 2
20240814-22:39:37 training model 0
20240814-22:43:21 train_perplexity 520 model 2 1.1688196656553074
20240814-22:43:23 test_perplexity 520 model 2 1.1734079381850724
20240814-22:43:24 train_perplexity 520 model 0 1.1680137320511506
20240814-22:43:26 test_perplexity 520 model 0 1.174971388070214
20240814-22:44:10 test_accuracy 520 model 2 val 760 / 811
20240814-22:44:11 test_accuracy 520 model 0 val 759 / 811
20240814-22:44:13 wrote gpt_002.pth
20240814-22:44:14 wrote gpt_000.pth
20240814-22:44:27 wrote non_validated_0520_02.png
20240814-22:44:40 wrote non_validated_0520_00.png
20240814-22:44:40 wrote state.pth
20240814-22:44:40 --- epoch 521 ----------------------------------------
20240814-22:44:40 current_test_accuracies 0.9359 0.9545 0.9371 0.9574 0.9664
20240814-22:44:40 training model 0
20240814-22:44:40 training model 2
20240814-22:48:24 train_perplexity 521 model 0 1.1676162673181139
20240814-22:48:26 test_perplexity 521 model 0 1.1741462089507495
20240814-22:48:27 train_perplexity 521 model 2 1.1696343594098375
20240814-22:48:29 test_perplexity 521 model 2 1.172249021343237
20240814-22:49:10 test_accuracy 521 model 0 val 766 / 815
20240814-22:49:13 test_accuracy 521 model 2 val 760 / 807
20240814-22:49:15 wrote gpt_000.pth
20240814-22:49:16 wrote gpt_002.pth
20240814-22:49:29 wrote non_validated_0521_00.png
20240814-22:49:42 wrote non_validated_0521_02.png
20240814-22:49:42 wrote state.pth
20240814-22:49:42 --- epoch 522 ----------------------------------------
20240814-22:49:42 current_test_accuracies 0.9399 0.9545 0.9418 0.9574 0.9664
20240814-22:49:42 training model 0
20240814-22:49:42 training model 2
20240814-22:53:26 train_perplexity 522 model 0 1.1677487394081913
20240814-22:53:28 test_perplexity 522 model 0 1.1742761175547531
20240814-22:53:28 train_perplexity 522 model 2 1.1692349132831825
20240814-22:53:31 test_perplexity 522 model 2 1.174892262224258
20240814-22:54:13 test_accuracy 522 model 0 val 767 / 809
20240814-22:54:15 test_accuracy 522 model 2 val 762 / 807
20240814-22:54:17 wrote gpt_000.pth
20240814-22:54:18 wrote gpt_002.pth
20240814-22:54:31 wrote non_validated_0522_00.png
20240814-22:54:44 wrote non_validated_0522_02.png
20240814-22:54:44 wrote state.pth
20240814-22:54:44 --- epoch 523 ----------------------------------------
20240814-22:54:44 current_test_accuracies 0.9481 0.9545 0.9442 0.9574 0.9664
20240814-22:54:44 training model 2
20240814-22:54:44 training model 0
20240814-22:58:29 train_perplexity 523 model 2 1.1686517178361149
20240814-22:58:31 train_perplexity 523 model 0 1.1680192929290067
20240814-22:58:32 test_perplexity 523 model 2 1.1767666565603006
20240814-22:58:34 test_perplexity 523 model 0 1.1741146612062685
20240814-22:59:17 test_accuracy 523 model 2 val 763 / 818
20240814-22:59:18 test_accuracy 523 model 0 val 749 / 807
20240814-22:59:20 wrote gpt_002.pth
20240814-22:59:21 wrote gpt_000.pth
20240814-22:59:34 wrote non_validated_0523_02.png
20240814-22:59:47 wrote non_validated_0523_00.png
20240814-22:59:47 wrote state.pth
20240814-22:59:47 --- epoch 524 ----------------------------------------
20240814-22:59:47 current_test_accuracies 0.9281 0.9545 0.9328 0.9574 0.9664
20240814-22:59:47 training model 0
20240814-22:59:47 training model 2
20240814-23:03:31 train_perplexity 524 model 0 1.1673168389101434
20240814-23:03:33 test_perplexity 524 model 0 1.1731592414752277
20240814-23:03:35 train_perplexity 524 model 2 1.1687436736845502
20240814-23:03:37 test_perplexity 524 model 2 1.1722429276920583
20240814-23:04:19 test_accuracy 524 model 0 val 738 / 805
20240814-23:04:20 test_accuracy 524 model 2 val 767 / 808
20240814-23:04:22 wrote gpt_000.pth
20240814-23:04:23 wrote gpt_002.pth
20240814-23:04:36 wrote non_validated_0524_00.png
20240814-23:04:49 wrote non_validated_0524_02.png
20240814-23:04:49 wrote state.pth
20240814-23:04:49 --- epoch 525 ----------------------------------------
20240814-23:04:49 current_test_accuracies 0.9168 0.9545 0.9493 0.9574 0.9664
20240814-23:04:49 training model 0
20240814-23:04:49 training model 2
20240814-23:08:34 train_perplexity 525 model 0 1.1671012343508873
20240814-23:08:35 test_perplexity 525 model 0 1.1760261287267657
20240814-23:08:36 train_perplexity 525 model 2 1.168688197715339
20240814-23:08:38 test_perplexity 525 model 2 1.1728585726704366
20240814-23:09:19 test_accuracy 525 model 0 val 773 / 806
20240814-23:09:23 test_accuracy 525 model 2 val 737 / 777
20240814-23:09:25 wrote gpt_000.pth
20240814-23:09:26 wrote gpt_002.pth
20240814-23:09:39 wrote non_validated_0525_00.png
20240814-23:09:52 wrote non_validated_0525_02.png
20240814-23:09:52 wrote state.pth
20240814-23:09:52 --- epoch 526 ----------------------------------------
20240814-23:09:52 current_test_accuracies 0.9591 0.9545 0.9485 0.9574 0.9664
20240814-23:09:52 training model 2
20240814-23:09:52 training model 1
20240814-23:13:36 train_perplexity 526 model 2 1.1684119073984423
20240814-23:13:38 test_perplexity 526 model 2 1.1728530163227913
20240814-23:13:39 train_perplexity 526 model 1 1.1714802175230274
20240814-23:13:41 test_perplexity 526 model 1 1.1719641244137342
20240814-23:14:25 test_accuracy 526 model 1 val 767 / 818
20240814-23:14:27 test_accuracy 526 model 2 val 754 / 794
20240814-23:14:29 wrote gpt_002.pth
20240814-23:14:29 wrote gpt_001.pth
20240814-23:14:42 wrote non_validated_0526_02.png
20240814-23:14:55 wrote non_validated_0526_01.png
20240814-23:14:55 wrote state.pth
20240814-23:14:55 --- epoch 527 ----------------------------------------
20240814-23:14:55 current_test_accuracies 0.9591 0.9377 0.9496 0.9574 0.9664
20240814-23:14:55 training model 1
20240814-23:14:55 training model 2
20240814-23:18:40 train_perplexity 527 model 1 1.1717302464091885
20240814-23:18:41 test_perplexity 527 model 1 1.1731935217589164
20240814-23:18:42 train_perplexity 527 model 2 1.1684249464325576
20240814-23:18:44 test_perplexity 527 model 2 1.1753664181227514
20240814-23:19:27 test_accuracy 527 model 1 val 779 / 821
20240814-23:19:28 test_accuracy 527 model 2 val 755 / 806
20240814-23:19:30 wrote gpt_001.pth
20240814-23:19:31 wrote gpt_002.pth
20240814-23:19:44 wrote non_validated_0527_01.png
20240814-23:19:57 wrote non_validated_0527_02.png
20240814-23:19:57 wrote state.pth
20240814-23:19:57 --- epoch 528 ----------------------------------------
20240814-23:19:57 current_test_accuracies 0.9591 0.9488 0.9367 0.9574 0.9664
20240814-23:19:57 training model 2
20240814-23:19:57 training model 1
20240814-23:23:41 train_perplexity 528 model 2 1.1685908929005362
20240814-23:23:43 test_perplexity 528 model 2 1.1730428785783698
20240814-23:23:44 train_perplexity 528 model 1 1.1718720101882962
20240814-23:23:46 test_perplexity 528 model 1 1.175106620522305
20240814-23:24:32 test_accuracy 528 model 1 val 784 / 835
20240814-23:24:33 test_accuracy 528 model 2 val 739 / 796
20240814-23:24:35 wrote gpt_002.pth
20240814-23:24:35 wrote gpt_001.pth
20240814-23:24:48 wrote non_validated_0528_02.png
20240814-23:25:01 wrote non_validated_0528_01.png
20240814-23:25:01 wrote state.pth
20240814-23:25:01 --- epoch 529 ----------------------------------------
20240814-23:25:01 current_test_accuracies 0.9591 0.9389 0.9284 0.9574 0.9664
20240814-23:25:01 training model 2
20240814-23:25:01 training model 1
20240814-23:28:45 train_perplexity 529 model 2 1.1686221843242997
20240814-23:28:47 test_perplexity 529 model 2 1.1746556561887815
20240814-23:28:48 train_perplexity 529 model 1 1.1713515766682159
20240814-23:28:50 test_perplexity 529 model 1 1.1729009393213785
20240814-23:29:33 test_accuracy 529 model 1 val 751 / 805
20240814-23:29:35 test_accuracy 529 model 2 val 738 / 799
20240814-23:29:37 wrote gpt_002.pth
20240814-23:29:38 wrote gpt_001.pth
20240814-23:29:51 wrote non_validated_0529_02.png
20240814-23:30:04 wrote non_validated_0529_01.png
20240814-23:30:04 wrote state.pth
20240814-23:30:04 --- epoch 530 ----------------------------------------
20240814-23:30:04 current_test_accuracies 0.9591 0.9329 0.9237 0.9574 0.9664
20240814-23:30:04 training model 2
20240814-23:30:04 training model 1
20240814-23:33:48 train_perplexity 530 model 2 1.1683996951661035
20240814-23:33:50 test_perplexity 530 model 2 1.1727146255768575
20240814-23:33:50 train_perplexity 530 model 1 1.171243586845075
20240814-23:33:53 test_perplexity 530 model 1 1.1713151750478057
20240814-23:34:39 test_accuracy 530 model 2 val 735 / 774
20240814-23:34:40 test_accuracy 530 model 1 val 756 / 799
20240814-23:34:42 wrote gpt_002.pth
20240814-23:34:43 wrote gpt_001.pth
20240814-23:34:56 wrote non_validated_0530_02.png
20240814-23:35:09 wrote non_validated_0530_01.png
20240814-23:35:09 wrote state.pth
20240814-23:35:09 --- epoch 531 ----------------------------------------
20240814-23:35:09 current_test_accuracies 0.9591 0.9462 0.9496 0.9574 0.9664
20240814-23:35:09 training model 1
20240814-23:35:09 training model 2
20240814-23:38:54 train_perplexity 531 model 1 1.1712317226054225
20240814-23:38:55 train_perplexity 531 model 2 1.1681304395390775
20240814-23:38:57 test_perplexity 531 model 1 1.1695069268694749
20240814-23:38:58 test_perplexity 531 model 2 1.1708015885095786
20240814-23:39:46 test_accuracy 531 model 1 val 745 / 790
20240814-23:39:47 test_accuracy 531 model 2 val 753 / 793
20240814-23:39:49 wrote gpt_001.pth
20240814-23:39:50 wrote gpt_002.pth
20240814-23:40:03 wrote non_validated_0531_01.png
20240814-23:40:16 wrote non_validated_0531_02.png
20240814-23:40:16 wrote state.pth
20240814-23:40:16 --- epoch 532 ----------------------------------------
20240814-23:40:16 current_test_accuracies 0.9591 0.9430 0.9496 0.9574 0.9664
20240814-23:40:16 training model 1
20240814-23:40:16 training model 2
20240814-23:44:00 train_perplexity 532 model 1 1.1717204672049255
20240814-23:44:02 test_perplexity 532 model 1 1.1685064568754349
20240814-23:44:02 train_perplexity 532 model 2 1.1684442567854498
20240814-23:44:04 test_perplexity 532 model 2 1.1717696974713676
20240814-23:44:47 test_accuracy 532 model 2 val 762 / 804
20240814-23:44:48 test_accuracy 532 model 1 val 770 / 814
20240814-23:44:50 wrote gpt_001.pth
20240814-23:44:51 wrote gpt_002.pth
20240814-23:45:04 wrote non_validated_0532_01.png
20240814-23:45:17 wrote non_validated_0532_02.png
20240814-23:45:17 wrote state.pth
20240814-23:45:17 --- epoch 533 ----------------------------------------
20240814-23:45:17 current_test_accuracies 0.9591 0.9459 0.9478 0.9574 0.9664
20240814-23:45:17 training model 1
20240814-23:45:17 training model 2
20240814-23:49:01 train_perplexity 533 model 1 1.1715402261157488
20240814-23:49:03 test_perplexity 533 model 1 1.1699202335312229
20240814-23:49:03 train_perplexity 533 model 2 1.1683035787233114
20240814-23:49:06 test_perplexity 533 model 2 1.1739132193269035
20240814-23:49:52 test_accuracy 533 model 1 val 730 / 782
20240814-23:49:54 test_accuracy 533 model 2 val 730 / 777
20240814-23:49:56 wrote gpt_001.pth
20240814-23:49:57 wrote gpt_002.pth
20240814-23:50:10 wrote non_validated_0533_01.png
20240814-23:50:23 wrote non_validated_0533_02.png
20240814-23:50:23 wrote state.pth
20240814-23:50:23 --- epoch 534 ----------------------------------------
20240814-23:50:23 current_test_accuracies 0.9591 0.9335 0.9395 0.9574 0.9664
20240814-23:50:23 training model 1
20240814-23:50:23 training model 2
20240814-23:54:08 train_perplexity 534 model 1 1.1711625329660973
20240814-23:54:10 train_perplexity 534 model 2 1.1681158845374982
20240814-23:54:10 test_perplexity 534 model 1 1.1739473244065899
20240814-23:54:12 test_perplexity 534 model 2 1.1732751805841621
20240814-23:54:58 test_accuracy 534 model 1 val 746 / 798
20240814-23:54:59 test_accuracy 534 model 2 val 746 / 789
20240814-23:55:01 wrote gpt_001.pth
20240814-23:55:02 wrote gpt_002.pth
20240814-23:55:15 wrote non_validated_0534_01.png
20240814-23:55:28 wrote non_validated_0534_02.png
20240814-23:55:28 wrote state.pth
20240814-23:55:28 --- epoch 535 ----------------------------------------
20240814-23:55:28 current_test_accuracies 0.9591 0.9348 0.9455 0.9574 0.9664
20240814-23:55:28 training model 1
20240814-23:55:28 training model 2