20241026-14:35:11 argv ./main.py --test=reasoning --gpus=1 --nb_blocks=32 --batch_size=10 --eval_batch_size=10 --learning_rate=2e-4 20241026-14:35:11 args.log_filename train.log 20241026-14:35:11 args.result_dir results_culture 20241026-14:35:11 args.seed 0 20241026-14:35:11 args.resume False 20241026-14:35:11 args.optimizer adam 20241026-14:35:11 args.nb_warmup_samples 5000 20241026-14:35:11 args.nb_epochs 10000 20241026-14:35:11 args.batch_size 10 20241026-14:35:11 args.train_batch_size None 20241026-14:35:11 args.eval_batch_size 10 20241026-14:35:11 args.nb_train_samples 50000 20241026-14:35:11 args.nb_test_samples 2500 20241026-14:35:11 args.nb_c_quizzes 5000 20241026-14:35:11 args.c_quiz_multiplier 1 20241026-14:35:11 args.learning_rate 0.0002 20241026-14:35:11 args.gradient_clipping None 20241026-14:35:11 args.nb_have_to_be_correct 3 20241026-14:35:11 args.nb_have_to_be_wrong 1 20241026-14:35:11 args.nb_mistakes_to_be_wrong 5 20241026-14:35:11 args.model_type standard 20241026-14:35:11 args.model 37M 20241026-14:35:11 args.dim_model 512 20241026-14:35:11 args.dim_keys 64 20241026-14:35:11 args.dim_hidden 2048 20241026-14:35:11 args.nb_heads 8 20241026-14:35:11 args.nb_blocks 32 20241026-14:35:11 args.dropout 0.5 20241026-14:35:11 args.nb_threads 1 20241026-14:35:11 args.gpus 1 20241026-14:35:11 args.nb_models 5 20241026-14:35:11 args.diffusion_nb_iterations 25 20241026-14:35:11 args.diffusion_proba_corruption 0.05 20241026-14:35:11 args.accuracy_to_make_c_quizzes 0.95 20241026-14:35:11 args.proba_prompt_noise 0.05 20241026-14:35:11 args.proba_hint 0.25 20241026-14:35:11 args.quizzes None 20241026-14:35:11 args.test reasoning 20241026-14:35:11 args.grids_world_tasks replace_color,translate,grow,frame 20241026-14:35:23 main_device cuda:1 gpus ['cuda:1'] 20241026-14:35:23 vocabulary_size 11 20241026-14:35:36 quiz_set nb_w_quizzes 50000 nb_c_quizzes 0 20241026-14:42:30 train_loss 0 model 0 1.19219833984375 20241026-14:42:30 quiz_set nb_w_quizzes 2500 nb_c_quizzes 0 20241026-14:42:38 test_loss 0 model 0 0.49539453125 20241026-14:42:38 quiz_set nb_w_quizzes 2500 nb_c_quizzes 0 20241026-14:42:46 test_accuracy 0 model 0 nb_correct 0 / 2500 (0.00%) 20241026-14:42:46 quiz_set nb_w_quizzes 150 nb_c_quizzes 0 20241026-14:43:01 wrote reasoning.pth 20241026-14:43:01 quiz_set nb_w_quizzes 256 nb_c_quizzes 0 20241026-14:43:04 quiz_set nb_w_quizzes 50000 nb_c_quizzes 0 20241026-14:51:12 train_loss 1 model 0 0.41937685546875 20241026-14:51:12 quiz_set nb_w_quizzes 2500 nb_c_quizzes 0 20241026-14:51:20 test_loss 1 model 0 0.33048828125 20241026-14:51:20 quiz_set nb_w_quizzes 2500 nb_c_quizzes 0 20241026-14:51:28 test_accuracy 1 model 0 nb_correct 1 / 2500 (0.04%) 20241026-14:51:28 quiz_set nb_w_quizzes 150 nb_c_quizzes 0 20241026-14:51:44 wrote reasoning.pth 20241026-14:51:44 quiz_set nb_w_quizzes 256 nb_c_quizzes 0 20241026-14:51:47 quiz_set nb_w_quizzes 50000 nb_c_quizzes 0 20241026-15:00:04 train_loss 2 model 0 0.30218671875 20241026-15:00:04 quiz_set nb_w_quizzes 2500 nb_c_quizzes 0 20241026-15:00:12 test_loss 2 model 0 0.212275390625 20241026-15:00:12 quiz_set nb_w_quizzes 2500 nb_c_quizzes 0 20241026-15:00:20 test_accuracy 2 model 0 nb_correct 201 / 2500 (8.04%) 20241026-15:00:20 quiz_set nb_w_quizzes 150 nb_c_quizzes 0 20241026-15:00:36 wrote reasoning.pth 20241026-15:00:36 quiz_set nb_w_quizzes 256 nb_c_quizzes 0 20241026-15:00:39 quiz_set nb_w_quizzes 50000 nb_c_quizzes 0 20241026-15:08:57 train_loss 3 model 0 0.2189287841796875 20241026-15:08:57 quiz_set nb_w_quizzes 2500 nb_c_quizzes 0 20241026-15:09:04 test_loss 3 model 0 0.183650390625 20241026-15:09:04 quiz_set nb_w_quizzes 2500 nb_c_quizzes 0 20241026-15:09:12 test_accuracy 3 model 0 nb_correct 530 / 2500 (21.20%) 20241026-15:09:12 quiz_set nb_w_quizzes 150 nb_c_quizzes 0 20241026-15:09:28 wrote reasoning.pth 20241026-15:09:28 quiz_set nb_w_quizzes 256 nb_c_quizzes 0 20241026-15:09:31 quiz_set nb_w_quizzes 50000 nb_c_quizzes 0 20241026-15:17:20 train_loss 4 model 0 0.18935888671875 20241026-15:17:20 quiz_set nb_w_quizzes 2500 nb_c_quizzes 0 20241026-15:17:28 test_loss 4 model 0 0.16472216796875 20241026-15:17:28 quiz_set nb_w_quizzes 2500 nb_c_quizzes 0 20241026-15:17:36 test_accuracy 4 model 0 nb_correct 715 / 2500 (28.60%) 20241026-15:17:36 quiz_set nb_w_quizzes 150 nb_c_quizzes 0 20241026-15:17:52 wrote reasoning.pth 20241026-15:17:52 quiz_set nb_w_quizzes 256 nb_c_quizzes 0 20241026-15:17:55 quiz_set nb_w_quizzes 50000 nb_c_quizzes 0 20241026-15:25:55 train_loss 5 model 0 0.170767333984375 20241026-15:25:55 quiz_set nb_w_quizzes 2500 nb_c_quizzes 0 20241026-15:26:03 test_loss 5 model 0 0.1507724609375 20241026-15:26:03 quiz_set nb_w_quizzes 2500 nb_c_quizzes 0 20241026-15:26:10 test_accuracy 5 model 0 nb_correct 912 / 2500 (36.48%) 20241026-15:26:10 quiz_set nb_w_quizzes 150 nb_c_quizzes 0 20241026-15:26:27 wrote reasoning.pth 20241026-15:26:27 quiz_set nb_w_quizzes 256 nb_c_quizzes 0 20241026-15:26:30 quiz_set nb_w_quizzes 50000 nb_c_quizzes 0 20241026-15:34:09 train_loss 6 model 0 0.15760806884765624 20241026-15:34:09 quiz_set nb_w_quizzes 2500 nb_c_quizzes 0 20241026-15:34:17 test_loss 6 model 0 0.138344482421875 20241026-15:34:17 quiz_set nb_w_quizzes 2500 nb_c_quizzes 0 20241026-15:34:25 test_accuracy 6 model 0 nb_correct 1102 / 2500 (44.08%) 20241026-15:34:25 quiz_set nb_w_quizzes 150 nb_c_quizzes 0 20241026-15:34:41 wrote reasoning.pth 20241026-15:34:41 quiz_set nb_w_quizzes 256 nb_c_quizzes 0 20241026-15:34:44 quiz_set nb_w_quizzes 50000 nb_c_quizzes 0 20241026-15:42:57 train_loss 7 model 0 0.14907734375 20241026-15:42:57 quiz_set nb_w_quizzes 2500 nb_c_quizzes 0 20241026-15:43:05 test_loss 7 model 0 0.13172314453125 20241026-15:43:05 quiz_set nb_w_quizzes 2500 nb_c_quizzes 0 20241026-15:43:13 test_accuracy 7 model 0 nb_correct 1260 / 2500 (50.40%) 20241026-15:43:13 quiz_set nb_w_quizzes 150 nb_c_quizzes 0 20241026-15:43:28 wrote reasoning.pth 20241026-15:43:28 quiz_set nb_w_quizzes 256 nb_c_quizzes 0 20241026-15:43:32 quiz_set nb_w_quizzes 50000 nb_c_quizzes 0 20241026-15:51:35 train_loss 8 model 0 0.14198023071289062 20241026-15:51:35 quiz_set nb_w_quizzes 2500 nb_c_quizzes 0 20241026-15:51:43 test_loss 8 model 0 0.12695263671875 20241026-15:51:43 quiz_set nb_w_quizzes 2500 nb_c_quizzes 0 20241026-15:51:51 test_accuracy 8 model 0 nb_correct 1075 / 2500 (43.00%) 20241026-15:51:51 quiz_set nb_w_quizzes 150 nb_c_quizzes 0 20241026-15:52:08 wrote reasoning.pth 20241026-15:52:08 quiz_set nb_w_quizzes 256 nb_c_quizzes 0 20241026-15:52:11 quiz_set nb_w_quizzes 50000 nb_c_quizzes 0 20241026-16:00:02 train_loss 9 model 0 0.1338773193359375 20241026-16:00:02 quiz_set nb_w_quizzes 2500 nb_c_quizzes 0 20241026-16:00:10 test_loss 9 model 0 0.10887109375 20241026-16:00:10 quiz_set nb_w_quizzes 2500 nb_c_quizzes 0 20241026-16:00:18 test_accuracy 9 model 0 nb_correct 1239 / 2500 (49.56%) 20241026-16:00:18 quiz_set nb_w_quizzes 150 nb_c_quizzes 0 20241026-16:00:34 wrote reasoning.pth 20241026-16:00:34 quiz_set nb_w_quizzes 256 nb_c_quizzes 0 20241026-16:00:37 quiz_set nb_w_quizzes 50000 nb_c_quizzes 0 20241026-16:08:16 train_loss 10 model 0 0.12672891845703124 20241026-16:08:16 quiz_set nb_w_quizzes 2500 nb_c_quizzes 0 20241026-16:08:24 test_loss 10 model 0 0.1142764892578125 20241026-16:08:24 quiz_set nb_w_quizzes 2500 nb_c_quizzes 0 20241026-16:08:32 test_accuracy 10 model 0 nb_correct 1414 / 2500 (56.56%) 20241026-16:08:32 quiz_set nb_w_quizzes 150 nb_c_quizzes 0 20241026-16:08:48 wrote reasoning.pth 20241026-16:08:48 quiz_set nb_w_quizzes 256 nb_c_quizzes 0 20241026-16:08:51 quiz_set nb_w_quizzes 50000 nb_c_quizzes 0 20241026-16:17:01 train_loss 11 model 0 0.12326857357025146 20241026-16:17:01 quiz_set nb_w_quizzes 2500 nb_c_quizzes 0 20241026-16:17:09 test_loss 11 model 0 0.1087265625 20241026-16:17:09 quiz_set nb_w_quizzes 2500 nb_c_quizzes 0 20241026-16:17:17 test_accuracy 11 model 0 nb_correct 1409 / 2500 (56.36%) 20241026-16:17:17 quiz_set nb_w_quizzes 150 nb_c_quizzes 0 20241026-16:17:33 wrote reasoning.pth 20241026-16:17:33 quiz_set nb_w_quizzes 256 nb_c_quizzes 0 20241026-16:17:36 quiz_set nb_w_quizzes 50000 nb_c_quizzes 0 20241026-16:25:30 train_loss 12 model 0 0.117357568359375 20241026-16:25:30 quiz_set nb_w_quizzes 2500 nb_c_quizzes 0 20241026-16:25:38 test_loss 12 model 0 0.10439990234375 20241026-16:25:38 quiz_set nb_w_quizzes 2500 nb_c_quizzes 0 20241026-16:25:46 test_accuracy 12 model 0 nb_correct 1450 / 2500 (58.00%) 20241026-16:25:46 quiz_set nb_w_quizzes 150 nb_c_quizzes 0 20241026-16:26:02 wrote reasoning.pth 20241026-16:26:02 quiz_set nb_w_quizzes 256 nb_c_quizzes 0 20241026-16:26:05 quiz_set nb_w_quizzes 50000 nb_c_quizzes 0 20241026-16:33:49 train_loss 13 model 0 0.11490308074951172 20241026-16:33:49 quiz_set nb_w_quizzes 2500 nb_c_quizzes 0 20241026-16:33:57 test_loss 13 model 0 0.101795166015625 20241026-16:33:57 quiz_set nb_w_quizzes 2500 nb_c_quizzes 0 20241026-16:34:06 test_accuracy 13 model 0 nb_correct 1373 / 2500 (54.92%) 20241026-16:34:06 quiz_set nb_w_quizzes 150 nb_c_quizzes 0 20241026-16:34:22 wrote reasoning.pth 20241026-16:34:22 quiz_set nb_w_quizzes 256 nb_c_quizzes 0 20241026-16:34:25 quiz_set nb_w_quizzes 50000 nb_c_quizzes 0 20241026-16:42:15 train_loss 14 model 0 0.10846782531738282 20241026-16:42:15 quiz_set nb_w_quizzes 2500 nb_c_quizzes 0 20241026-16:42:23 test_loss 14 model 0 0.0956561279296875 20241026-16:42:23 quiz_set nb_w_quizzes 2500 nb_c_quizzes 0 20241026-16:42:31 test_accuracy 14 model 0 nb_correct 1357 / 2500 (54.28%) 20241026-16:42:31 quiz_set nb_w_quizzes 150 nb_c_quizzes 0 20241026-16:42:47 wrote reasoning.pth 20241026-16:42:47 quiz_set nb_w_quizzes 256 nb_c_quizzes 0 20241026-16:42:51 quiz_set nb_w_quizzes 50000 nb_c_quizzes 0 20241026-16:51:03 train_loss 15 model 0 0.10480760498046875 20241026-16:51:03 quiz_set nb_w_quizzes 2500 nb_c_quizzes 0 20241026-16:51:11 test_loss 15 model 0 0.0826103515625 20241026-16:51:11 quiz_set nb_w_quizzes 2500 nb_c_quizzes 0 20241026-16:51:19 test_accuracy 15 model 0 nb_correct 1522 / 2500 (60.88%) 20241026-16:51:19 quiz_set nb_w_quizzes 150 nb_c_quizzes 0 20241026-16:51:35 wrote reasoning.pth 20241026-16:51:35 quiz_set nb_w_quizzes 256 nb_c_quizzes 0 20241026-16:51:38 quiz_set nb_w_quizzes 50000 nb_c_quizzes 0 20241026-16:59:54 train_loss 16 model 0 0.09993357543945312 20241026-16:59:54 quiz_set nb_w_quizzes 2500 nb_c_quizzes 0 20241026-17:00:02 test_loss 16 model 0 0.08880517578125 20241026-17:00:02 quiz_set nb_w_quizzes 2500 nb_c_quizzes 0 20241026-17:00:10 test_accuracy 16 model 0 nb_correct 1454 / 2500 (58.16%) 20241026-17:00:10 quiz_set nb_w_quizzes 150 nb_c_quizzes 0 20241026-17:00:26 wrote reasoning.pth 20241026-17:00:26 quiz_set nb_w_quizzes 256 nb_c_quizzes 0 20241026-17:00:29 quiz_set nb_w_quizzes 50000 nb_c_quizzes 0 20241026-17:08:23 train_loss 17 model 0 0.09795024566650391 20241026-17:08:23 quiz_set nb_w_quizzes 2500 nb_c_quizzes 0 20241026-17:08:31 test_loss 17 model 0 0.09037939453125 20241026-17:08:31 quiz_set nb_w_quizzes 2500 nb_c_quizzes 0 20241026-17:08:39 test_accuracy 17 model 0 nb_correct 1423 / 2500 (56.92%) 20241026-17:08:39 quiz_set nb_w_quizzes 150 nb_c_quizzes 0 20241026-17:08:55 wrote reasoning.pth 20241026-17:08:55 quiz_set nb_w_quizzes 256 nb_c_quizzes 0 20241026-17:08:59 quiz_set nb_w_quizzes 50000 nb_c_quizzes 0 20241026-17:16:40 train_loss 18 model 0 0.09491718597412109 20241026-17:16:40 quiz_set nb_w_quizzes 2500 nb_c_quizzes 0 20241026-17:16:48 test_loss 18 model 0 0.081450927734375 20241026-17:16:48 quiz_set nb_w_quizzes 2500 nb_c_quizzes 0 20241026-17:16:56 test_accuracy 18 model 0 nb_correct 1500 / 2500 (60.00%) 20241026-17:16:56 quiz_set nb_w_quizzes 150 nb_c_quizzes 0 20241026-17:17:12 wrote reasoning.pth 20241026-17:17:12 quiz_set nb_w_quizzes 256 nb_c_quizzes 0 20241026-17:17:15 quiz_set nb_w_quizzes 50000 nb_c_quizzes 0 20241026-17:25:03 train_loss 19 model 0 0.09312870464324952 20241026-17:25:03 quiz_set nb_w_quizzes 2500 nb_c_quizzes 0 20241026-17:25:11 test_loss 19 model 0 0.0752928466796875 20241026-17:25:11 quiz_set nb_w_quizzes 2500 nb_c_quizzes 0 20241026-17:25:19 test_accuracy 19 model 0 nb_correct 1476 / 2500 (59.04%) 20241026-17:25:19 quiz_set nb_w_quizzes 150 nb_c_quizzes 0 20241026-17:25:35 wrote reasoning.pth 20241026-17:25:35 quiz_set nb_w_quizzes 256 nb_c_quizzes 0 20241026-17:25:38 quiz_set nb_w_quizzes 50000 nb_c_quizzes 0 20241026-17:33:22 train_loss 20 model 0 0.08770561065673828 20241026-17:33:22 quiz_set nb_w_quizzes 2500 nb_c_quizzes 0 20241026-17:33:30 test_loss 20 model 0 0.06728302001953125 20241026-17:33:30 quiz_set nb_w_quizzes 2500 nb_c_quizzes 0 20241026-17:33:38 test_accuracy 20 model 0 nb_correct 1572 / 2500 (62.88%) 20241026-17:33:38 quiz_set nb_w_quizzes 150 nb_c_quizzes 0 20241026-17:33:54 wrote reasoning.pth 20241026-17:33:54 quiz_set nb_w_quizzes 256 nb_c_quizzes 0 20241026-17:33:57 quiz_set nb_w_quizzes 50000 nb_c_quizzes 0 20241026-17:42:03 train_loss 21 model 0 0.08450033187866211 20241026-17:42:03 quiz_set nb_w_quizzes 2500 nb_c_quizzes 0 20241026-17:42:11 test_loss 21 model 0 0.0749085693359375 20241026-17:42:11 quiz_set nb_w_quizzes 2500 nb_c_quizzes 0 20241026-17:42:19 test_accuracy 21 model 0 nb_correct 1567 / 2500 (62.68%) 20241026-17:42:19 quiz_set nb_w_quizzes 150 nb_c_quizzes 0 20241026-17:42:35 wrote reasoning.pth 20241026-17:42:35 quiz_set nb_w_quizzes 256 nb_c_quizzes 0 20241026-17:42:38 quiz_set nb_w_quizzes 50000 nb_c_quizzes 0 20241026-17:50:58 train_loss 22 model 0 0.08206088790893555 20241026-17:50:58 quiz_set nb_w_quizzes 2500 nb_c_quizzes 0 20241026-17:51:05 test_loss 22 model 0 0.068098388671875 20241026-17:51:05 quiz_set nb_w_quizzes 2500 nb_c_quizzes 0 20241026-17:51:13 test_accuracy 22 model 0 nb_correct 1633 / 2500 (65.32%) 20241026-17:51:13 quiz_set nb_w_quizzes 150 nb_c_quizzes 0 20241026-17:51:29 wrote reasoning.pth 20241026-17:51:29 quiz_set nb_w_quizzes 256 nb_c_quizzes 0 20241026-17:51:32 quiz_set nb_w_quizzes 50000 nb_c_quizzes 0 20241026-17:59:50 train_loss 23 model 0 0.0785144775390625 20241026-17:59:50 quiz_set nb_w_quizzes 2500 nb_c_quizzes 0 20241026-17:59:59 test_loss 23 model 0 0.06533599853515625 20241026-17:59:59 quiz_set nb_w_quizzes 2500 nb_c_quizzes 0 20241026-18:00:07 test_accuracy 23 model 0 nb_correct 1570 / 2500 (62.80%) 20241026-18:00:07 quiz_set nb_w_quizzes 150 nb_c_quizzes 0 20241026-18:00:23 wrote reasoning.pth 20241026-18:00:23 quiz_set nb_w_quizzes 256 nb_c_quizzes 0 20241026-18:00:26 quiz_set nb_w_quizzes 50000 nb_c_quizzes 0 20241026-18:08:45 train_loss 24 model 0 0.07568446044921875 20241026-18:08:45 quiz_set nb_w_quizzes 2500 nb_c_quizzes 0 20241026-18:08:52 test_loss 24 model 0 0.0650113525390625 20241026-18:08:52 quiz_set nb_w_quizzes 2500 nb_c_quizzes 0 20241026-18:09:00 test_accuracy 24 model 0 nb_correct 1581 / 2500 (63.24%) 20241026-18:09:00 quiz_set nb_w_quizzes 150 nb_c_quizzes 0 20241026-18:09:16 wrote reasoning.pth 20241026-18:09:16 quiz_set nb_w_quizzes 256 nb_c_quizzes 0 20241026-18:09:19 quiz_set nb_w_quizzes 50000 nb_c_quizzes 0 20241026-18:17:14 train_loss 25 model 0 0.07434000701904298 20241026-18:17:14 quiz_set nb_w_quizzes 2500 nb_c_quizzes 0 20241026-18:17:22 test_loss 25 model 0 0.05693914794921875 20241026-18:17:22 quiz_set nb_w_quizzes 2500 nb_c_quizzes 0 20241026-18:17:30 test_accuracy 25 model 0 nb_correct 1673 / 2500 (66.92%) 20241026-18:17:30 quiz_set nb_w_quizzes 150 nb_c_quizzes 0 20241026-18:17:46 wrote reasoning.pth 20241026-18:17:46 quiz_set nb_w_quizzes 256 nb_c_quizzes 0 20241026-18:17:49 quiz_set nb_w_quizzes 50000 nb_c_quizzes 0 20241026-18:25:41 train_loss 26 model 0 0.07068528594970704 20241026-18:25:41 quiz_set nb_w_quizzes 2500 nb_c_quizzes 0 20241026-18:25:49 test_loss 26 model 0 0.05582275390625 20241026-18:25:49 quiz_set nb_w_quizzes 2500 nb_c_quizzes 0 20241026-18:25:57 test_accuracy 26 model 0 nb_correct 1695 / 2500 (67.80%) 20241026-18:25:57 quiz_set nb_w_quizzes 150 nb_c_quizzes 0 20241026-18:26:13 wrote reasoning.pth 20241026-18:26:13 quiz_set nb_w_quizzes 256 nb_c_quizzes 0 20241026-18:26:16 quiz_set nb_w_quizzes 50000 nb_c_quizzes 0 20241026-18:34:30 train_loss 27 model 0 0.06611269721984864 20241026-18:34:30 quiz_set nb_w_quizzes 2500 nb_c_quizzes 0 20241026-18:34:38 test_loss 27 model 0 0.05543994140625 20241026-18:34:38 quiz_set nb_w_quizzes 2500 nb_c_quizzes 0 20241026-18:34:46 test_accuracy 27 model 0 nb_correct 1716 / 2500 (68.64%) 20241026-18:34:46 quiz_set nb_w_quizzes 150 nb_c_quizzes 0 20241026-18:35:02 wrote reasoning.pth 20241026-18:35:02 quiz_set nb_w_quizzes 256 nb_c_quizzes 0 20241026-18:35:05 quiz_set nb_w_quizzes 50000 nb_c_quizzes 0 20241026-18:43:12 train_loss 28 model 0 0.06324700469970704 20241026-18:43:12 quiz_set nb_w_quizzes 2500 nb_c_quizzes 0 20241026-18:43:20 test_loss 28 model 0 0.05655438232421875 20241026-18:43:20 quiz_set nb_w_quizzes 2500 nb_c_quizzes 0 20241026-18:43:28 test_accuracy 28 model 0 nb_correct 1653 / 2500 (66.12%) 20241026-18:43:28 quiz_set nb_w_quizzes 150 nb_c_quizzes 0 20241026-18:43:43 wrote reasoning.pth 20241026-18:43:43 quiz_set nb_w_quizzes 256 nb_c_quizzes 0 20241026-18:43:46 quiz_set nb_w_quizzes 50000 nb_c_quizzes 0 20241026-18:51:34 train_loss 29 model 0 0.061549469757080075 20241026-18:51:34 quiz_set nb_w_quizzes 2500 nb_c_quizzes 0 20241026-18:51:42 test_loss 29 model 0 0.046053329467773435 20241026-18:51:42 quiz_set nb_w_quizzes 2500 nb_c_quizzes 0 20241026-18:51:50 test_accuracy 29 model 0 nb_correct 1738 / 2500 (69.52%) 20241026-18:51:50 quiz_set nb_w_quizzes 150 nb_c_quizzes 0 20241026-18:52:05 wrote reasoning.pth 20241026-18:52:05 quiz_set nb_w_quizzes 256 nb_c_quizzes 0 20241026-18:52:08 quiz_set nb_w_quizzes 50000 nb_c_quizzes 0 20241026-18:59:49 train_loss 30 model 0 0.05965289850234985 20241026-18:59:49 quiz_set nb_w_quizzes 2500 nb_c_quizzes 0 20241026-18:59:57 test_loss 30 model 0 0.045533439636230466 20241026-18:59:57 quiz_set nb_w_quizzes 2500 nb_c_quizzes 0 20241026-19:00:05 test_accuracy 30 model 0 nb_correct 1797 / 2500 (71.88%) 20241026-19:00:05 quiz_set nb_w_quizzes 150 nb_c_quizzes 0 20241026-19:00:21 wrote reasoning.pth 20241026-19:00:21 quiz_set nb_w_quizzes 256 nb_c_quizzes 0 20241026-19:00:24 quiz_set nb_w_quizzes 50000 nb_c_quizzes 0 20241026-19:08:10 train_loss 31 model 0 0.05765024242401123 20241026-19:08:10 quiz_set nb_w_quizzes 2500 nb_c_quizzes 0 20241026-19:08:18 test_loss 31 model 0 0.04469183349609375 20241026-19:08:18 quiz_set nb_w_quizzes 2500 nb_c_quizzes 0 20241026-19:08:26 test_accuracy 31 model 0 nb_correct 1764 / 2500 (70.56%) 20241026-19:08:26 quiz_set nb_w_quizzes 150 nb_c_quizzes 0 20241026-19:08:42 wrote reasoning.pth 20241026-19:08:42 quiz_set nb_w_quizzes 256 nb_c_quizzes 0 20241026-19:08:45 quiz_set nb_w_quizzes 50000 nb_c_quizzes 0 20241026-19:16:26 train_loss 32 model 0 0.056290576553344726 20241026-19:16:26 quiz_set nb_w_quizzes 2500 nb_c_quizzes 0 20241026-19:16:34 test_loss 32 model 0 0.03899111938476563 20241026-19:16:34 quiz_set nb_w_quizzes 2500 nb_c_quizzes 0 20241026-19:16:42 test_accuracy 32 model 0 nb_correct 1841 / 2500 (73.64%) 20241026-19:16:42 quiz_set nb_w_quizzes 150 nb_c_quizzes 0 20241026-19:16:58 wrote reasoning.pth 20241026-19:16:58 quiz_set nb_w_quizzes 256 nb_c_quizzes 0 20241026-19:17:01 quiz_set nb_w_quizzes 50000 nb_c_quizzes 0 20241026-19:24:41 train_loss 33 model 0 0.05465683135986328 20241026-19:24:41 quiz_set nb_w_quizzes 2500 nb_c_quizzes 0 20241026-19:24:49 test_loss 33 model 0 0.044581253051757815 20241026-19:24:49 quiz_set nb_w_quizzes 2500 nb_c_quizzes 0 20241026-19:24:57 test_accuracy 33 model 0 nb_correct 1860 / 2500 (74.40%) 20241026-19:24:57 quiz_set nb_w_quizzes 150 nb_c_quizzes 0 20241026-19:25:13 wrote reasoning.pth 20241026-19:25:13 quiz_set nb_w_quizzes 256 nb_c_quizzes 0 20241026-19:25:16 quiz_set nb_w_quizzes 50000 nb_c_quizzes 0 20241026-19:32:57 train_loss 34 model 0 0.05341156883239746 20241026-19:32:57 quiz_set nb_w_quizzes 2500 nb_c_quizzes 0 20241026-19:33:05 test_loss 34 model 0 0.03976387786865234 20241026-19:33:05 quiz_set nb_w_quizzes 2500 nb_c_quizzes 0 20241026-19:33:13 test_accuracy 34 model 0 nb_correct 1901 / 2500 (76.04%) 20241026-19:33:13 quiz_set nb_w_quizzes 150 nb_c_quizzes 0 20241026-19:33:28 wrote reasoning.pth 20241026-19:33:28 quiz_set nb_w_quizzes 256 nb_c_quizzes 0 20241026-19:33:31 quiz_set nb_w_quizzes 50000 nb_c_quizzes 0 20241026-19:41:11 train_loss 35 model 0 0.052154809951782226 20241026-19:41:11 quiz_set nb_w_quizzes 2500 nb_c_quizzes 0 20241026-19:41:19 test_loss 35 model 0 0.0408354606628418 20241026-19:41:19 quiz_set nb_w_quizzes 2500 nb_c_quizzes 0 20241026-19:41:27 test_accuracy 35 model 0 nb_correct 1947 / 2500 (77.88%) 20241026-19:41:27 quiz_set nb_w_quizzes 150 nb_c_quizzes 0 20241026-19:41:42 wrote reasoning.pth 20241026-19:41:42 quiz_set nb_w_quizzes 256 nb_c_quizzes 0 20241026-19:41:45 quiz_set nb_w_quizzes 50000 nb_c_quizzes 0 20241026-19:49:27 train_loss 36 model 0 0.050291860389709474 20241026-19:49:27 quiz_set nb_w_quizzes 2500 nb_c_quizzes 0 20241026-19:49:35 test_loss 36 model 0 0.03941079330444336 20241026-19:49:35 quiz_set nb_w_quizzes 2500 nb_c_quizzes 0 20241026-19:49:44 test_accuracy 36 model 0 nb_correct 1950 / 2500 (78.00%) 20241026-19:49:44 quiz_set nb_w_quizzes 150 nb_c_quizzes 0 20241026-19:49:59 wrote reasoning.pth 20241026-19:49:59 quiz_set nb_w_quizzes 256 nb_c_quizzes 0 20241026-19:50:02 quiz_set nb_w_quizzes 50000 nb_c_quizzes 0 20241026-19:57:42 train_loss 37 model 0 0.05002166290283203 20241026-19:57:42 quiz_set nb_w_quizzes 2500 nb_c_quizzes 0 20241026-19:57:50 test_loss 37 model 0 0.03804085946083069 20241026-19:57:50 quiz_set nb_w_quizzes 2500 nb_c_quizzes 0 20241026-19:57:58 test_accuracy 37 model 0 nb_correct 2074 / 2500 (82.96%) 20241026-19:57:58 quiz_set nb_w_quizzes 150 nb_c_quizzes 0 20241026-19:58:13 wrote reasoning.pth 20241026-19:58:13 quiz_set nb_w_quizzes 256 nb_c_quizzes 0 20241026-19:58:16 quiz_set nb_w_quizzes 50000 nb_c_quizzes 0 20241026-20:05:56 train_loss 38 model 0 0.04803831977844238 20241026-20:05:56 quiz_set nb_w_quizzes 2500 nb_c_quizzes 0 20241026-20:06:04 test_loss 38 model 0 0.03697367858886719 20241026-20:06:04 quiz_set nb_w_quizzes 2500 nb_c_quizzes 0 20241026-20:06:12 test_accuracy 38 model 0 nb_correct 2058 / 2500 (82.32%) 20241026-20:06:12 quiz_set nb_w_quizzes 150 nb_c_quizzes 0 20241026-20:06:28 wrote reasoning.pth 20241026-20:06:28 quiz_set nb_w_quizzes 256 nb_c_quizzes 0 20241026-20:06:31 quiz_set nb_w_quizzes 50000 nb_c_quizzes 0 20241026-20:14:11 train_loss 39 model 0 0.047117910957336424 20241026-20:14:11 quiz_set nb_w_quizzes 2500 nb_c_quizzes 0 20241026-20:14:19 test_loss 39 model 0 0.035503189086914064 20241026-20:14:19 quiz_set nb_w_quizzes 2500 nb_c_quizzes 0 20241026-20:14:27 test_accuracy 39 model 0 nb_correct 2128 / 2500 (85.12%) 20241026-20:14:27 quiz_set nb_w_quizzes 150 nb_c_quizzes 0 20241026-20:14:43 wrote reasoning.pth 20241026-20:14:43 quiz_set nb_w_quizzes 256 nb_c_quizzes 0 20241026-20:14:46 quiz_set nb_w_quizzes 50000 nb_c_quizzes 0 20241026-20:22:26 train_loss 40 model 0 0.04620383615493774 20241026-20:22:26 quiz_set nb_w_quizzes 2500 nb_c_quizzes 0 20241026-20:22:34 test_loss 40 model 0 0.032954241752624513 20241026-20:22:34 quiz_set nb_w_quizzes 2500 nb_c_quizzes 0 20241026-20:22:42 test_accuracy 40 model 0 nb_correct 2140 / 2500 (85.60%) 20241026-20:22:42 quiz_set nb_w_quizzes 150 nb_c_quizzes 0 20241026-20:22:57 wrote reasoning.pth 20241026-20:22:57 quiz_set nb_w_quizzes 256 nb_c_quizzes 0 20241026-20:23:00 quiz_set nb_w_quizzes 50000 nb_c_quizzes 0 20241026-20:31:01 train_loss 41 model 0 0.044238821339607236 20241026-20:31:01 quiz_set nb_w_quizzes 2500 nb_c_quizzes 0 20241026-20:31:09 test_loss 41 model 0 0.035033746719360354 20241026-20:31:09 quiz_set nb_w_quizzes 2500 nb_c_quizzes 0 20241026-20:31:17 test_accuracy 41 model 0 nb_correct 2213 / 2500 (88.52%) 20241026-20:31:17 quiz_set nb_w_quizzes 150 nb_c_quizzes 0 20241026-20:31:32 wrote reasoning.pth 20241026-20:31:32 quiz_set nb_w_quizzes 256 nb_c_quizzes 0 20241026-20:31:35 quiz_set nb_w_quizzes 50000 nb_c_quizzes 0 20241026-20:39:15 train_loss 42 model 0 0.044276744842529296 20241026-20:39:15 quiz_set nb_w_quizzes 2500 nb_c_quizzes 0 20241026-20:39:23 test_loss 42 model 0 0.03323415279388428 20241026-20:39:23 quiz_set nb_w_quizzes 2500 nb_c_quizzes 0 20241026-20:39:31 test_accuracy 42 model 0 nb_correct 2100 / 2500 (84.00%) 20241026-20:39:31 quiz_set nb_w_quizzes 150 nb_c_quizzes 0 20241026-20:39:46 wrote reasoning.pth 20241026-20:39:46 quiz_set nb_w_quizzes 256 nb_c_quizzes 0 20241026-20:39:49 quiz_set nb_w_quizzes 50000 nb_c_quizzes 0 20241026-20:47:31 train_loss 43 model 0 0.04442180194854736 20241026-20:47:31 quiz_set nb_w_quizzes 2500 nb_c_quizzes 0 20241026-20:47:39 test_loss 43 model 0 0.031068787336349487 20241026-20:47:39 quiz_set nb_w_quizzes 2500 nb_c_quizzes 0 20241026-20:47:47 test_accuracy 43 model 0 nb_correct 2131 / 2500 (85.24%) 20241026-20:47:47 quiz_set nb_w_quizzes 150 nb_c_quizzes 0 20241026-20:48:02 wrote reasoning.pth 20241026-20:48:02 quiz_set nb_w_quizzes 256 nb_c_quizzes 0 20241026-20:48:05 quiz_set nb_w_quizzes 50000 nb_c_quizzes 0 20241026-20:55:46 train_loss 44 model 0 0.04334869079589844 20241026-20:55:46 quiz_set nb_w_quizzes 2500 nb_c_quizzes 0 20241026-20:55:54 test_loss 44 model 0 0.02965343475341797 20241026-20:55:54 quiz_set nb_w_quizzes 2500 nb_c_quizzes 0 20241026-20:56:03 test_accuracy 44 model 0 nb_correct 2194 / 2500 (87.76%) 20241026-20:56:03 quiz_set nb_w_quizzes 150 nb_c_quizzes 0 20241026-20:56:17 wrote reasoning.pth 20241026-20:56:17 quiz_set nb_w_quizzes 256 nb_c_quizzes 0 20241026-20:56:20 quiz_set nb_w_quizzes 50000 nb_c_quizzes 0 20241026-21:04:05 train_loss 45 model 0 0.042192392921447754 20241026-21:04:05 quiz_set nb_w_quizzes 2500 nb_c_quizzes 0 20241026-21:04:13 test_loss 45 model 0 0.03396255207061768 20241026-21:04:13 quiz_set nb_w_quizzes 2500 nb_c_quizzes 0 20241026-21:04:21 test_accuracy 45 model 0 nb_correct 2175 / 2500 (87.00%) 20241026-21:04:21 quiz_set nb_w_quizzes 150 nb_c_quizzes 0 20241026-21:04:36 wrote reasoning.pth 20241026-21:04:36 quiz_set nb_w_quizzes 256 nb_c_quizzes 0 20241026-21:04:39 quiz_set nb_w_quizzes 50000 nb_c_quizzes 0 20241026-21:12:19 train_loss 46 model 0 0.04119373826980591 20241026-21:12:19 quiz_set nb_w_quizzes 2500 nb_c_quizzes 0 20241026-21:12:27 test_loss 46 model 0 0.028289683341979982 20241026-21:12:27 quiz_set nb_w_quizzes 2500 nb_c_quizzes 0 20241026-21:12:35 test_accuracy 46 model 0 nb_correct 2257 / 2500 (90.28%) 20241026-21:12:35 quiz_set nb_w_quizzes 150 nb_c_quizzes 0 20241026-21:12:50 wrote reasoning.pth 20241026-21:12:50 quiz_set nb_w_quizzes 256 nb_c_quizzes 0 20241026-21:12:53 quiz_set nb_w_quizzes 50000 nb_c_quizzes 0 20241026-21:20:32 train_loss 47 model 0 0.04108120422363281 20241026-21:20:32 quiz_set nb_w_quizzes 2500 nb_c_quizzes 0 20241026-21:20:40 test_loss 47 model 0 0.030597606658935548 20241026-21:20:40 quiz_set nb_w_quizzes 2500 nb_c_quizzes 0 20241026-21:20:48 test_accuracy 47 model 0 nb_correct 2291 / 2500 (91.64%) 20241026-21:20:48 quiz_set nb_w_quizzes 150 nb_c_quizzes 0 20241026-21:21:03 wrote reasoning.pth 20241026-21:21:03 quiz_set nb_w_quizzes 256 nb_c_quizzes 0 20241026-21:21:06 quiz_set nb_w_quizzes 50000 nb_c_quizzes 0 20241026-21:28:49 train_loss 48 model 0 0.0398845160484314 20241026-21:28:49 quiz_set nb_w_quizzes 2500 nb_c_quizzes 0 20241026-21:28:58 test_loss 48 model 0 0.029564482271671296 20241026-21:28:58 quiz_set nb_w_quizzes 2500 nb_c_quizzes 0 20241026-21:29:06 test_accuracy 48 model 0 nb_correct 2241 / 2500 (89.64%) 20241026-21:29:06 quiz_set nb_w_quizzes 150 nb_c_quizzes 0 20241026-21:29:20 wrote reasoning.pth 20241026-21:29:20 quiz_set nb_w_quizzes 256 nb_c_quizzes 0 20241026-21:29:23 quiz_set nb_w_quizzes 50000 nb_c_quizzes 0 20241026-21:37:03 train_loss 49 model 0 0.03956693935394287 20241026-21:37:03 quiz_set nb_w_quizzes 2500 nb_c_quizzes 0 20241026-21:37:11 test_loss 49 model 0 0.029344493865966798 20241026-21:37:11 quiz_set nb_w_quizzes 2500 nb_c_quizzes 0 20241026-21:37:19 test_accuracy 49 model 0 nb_correct 2315 / 2500 (92.60%) 20241026-21:37:19 quiz_set nb_w_quizzes 150 nb_c_quizzes 0 20241026-21:37:33 wrote reasoning.pth 20241026-21:37:33 quiz_set nb_w_quizzes 256 nb_c_quizzes 0 20241026-21:37:36 quiz_set nb_w_quizzes 50000 nb_c_quizzes 0 20241026-21:45:20 train_loss 50 model 0 0.03851245131492615 20241026-21:45:20 quiz_set nb_w_quizzes 2500 nb_c_quizzes 0 20241026-21:45:28 test_loss 50 model 0 0.02698425579071045 20241026-21:45:28 quiz_set nb_w_quizzes 2500 nb_c_quizzes 0 20241026-21:45:36 test_accuracy 50 model 0 nb_correct 2326 / 2500 (93.04%) 20241026-21:45:36 quiz_set nb_w_quizzes 150 nb_c_quizzes 0 20241026-21:45:51 wrote reasoning.pth 20241026-21:45:51 quiz_set nb_w_quizzes 256 nb_c_quizzes 0 20241026-21:45:54 quiz_set nb_w_quizzes 50000 nb_c_quizzes 0 20241026-21:53:34 train_loss 51 model 0 0.038811461424827574 20241026-21:53:34 quiz_set nb_w_quizzes 2500 nb_c_quizzes 0 20241026-21:53:42 test_loss 51 model 0 0.03201728987693787 20241026-21:53:42 quiz_set nb_w_quizzes 2500 nb_c_quizzes 0 20241026-21:53:50 test_accuracy 51 model 0 nb_correct 2360 / 2500 (94.40%) 20241026-21:53:50 quiz_set nb_w_quizzes 150 nb_c_quizzes 0 20241026-21:54:04 wrote reasoning.pth 20241026-21:54:04 quiz_set nb_w_quizzes 256 nb_c_quizzes 0 20241026-21:54:08 quiz_set nb_w_quizzes 50000 nb_c_quizzes 0 20241026-22:01:49 train_loss 52 model 0 0.03883769550323486 20241026-22:01:49 quiz_set nb_w_quizzes 2500 nb_c_quizzes 0 20241026-22:01:58 test_loss 52 model 0 0.03033629384636879 20241026-22:01:58 quiz_set nb_w_quizzes 2500 nb_c_quizzes 0 20241026-22:02:06 test_accuracy 52 model 0 nb_correct 2296 / 2500 (91.84%) 20241026-22:02:06 quiz_set nb_w_quizzes 150 nb_c_quizzes 0 20241026-22:02:21 wrote reasoning.pth 20241026-22:02:21 quiz_set nb_w_quizzes 256 nb_c_quizzes 0 20241026-22:02:24 quiz_set nb_w_quizzes 50000 nb_c_quizzes 0 20241026-22:10:03 train_loss 53 model 0 0.038258498668670655 20241026-22:10:03 quiz_set nb_w_quizzes 2500 nb_c_quizzes 0 20241026-22:10:11 test_loss 53 model 0 0.027665908813476563 20241026-22:10:11 quiz_set nb_w_quizzes 2500 nb_c_quizzes 0 20241026-22:10:19 test_accuracy 53 model 0 nb_correct 2368 / 2500 (94.72%) 20241026-22:10:19 quiz_set nb_w_quizzes 150 nb_c_quizzes 0 20241026-22:10:33 wrote reasoning.pth 20241026-22:10:33 quiz_set nb_w_quizzes 256 nb_c_quizzes 0 20241026-22:10:36 quiz_set nb_w_quizzes 50000 nb_c_quizzes 0 20241026-22:18:15 train_loss 54 model 0 0.03742943043708801 20241026-22:18:15 quiz_set nb_w_quizzes 2500 nb_c_quizzes 0 20241026-22:18:23 test_loss 54 model 0 0.03063853645324707 20241026-22:18:23 quiz_set nb_w_quizzes 2500 nb_c_quizzes 0 20241026-22:18:31 test_accuracy 54 model 0 nb_correct 2336 / 2500 (93.44%) 20241026-22:18:31 quiz_set nb_w_quizzes 150 nb_c_quizzes 0 20241026-22:18:46 wrote reasoning.pth 20241026-22:18:46 quiz_set nb_w_quizzes 256 nb_c_quizzes 0 20241026-22:18:49 quiz_set nb_w_quizzes 50000 nb_c_quizzes 0 20241026-22:26:29 train_loss 55 model 0 0.03733158402442932 20241026-22:26:29 quiz_set nb_w_quizzes 2500 nb_c_quizzes 0 20241026-22:26:38 test_loss 55 model 0 0.02811914873123169 20241026-22:26:38 quiz_set nb_w_quizzes 2500 nb_c_quizzes 0 20241026-22:26:46 test_accuracy 55 model 0 nb_correct 2387 / 2500 (95.48%) 20241026-22:26:46 quiz_set nb_w_quizzes 150 nb_c_quizzes 0 20241026-22:27:00 wrote reasoning.pth 20241026-22:27:00 quiz_set nb_w_quizzes 256 nb_c_quizzes 0 20241026-22:27:03 quiz_set nb_w_quizzes 50000 nb_c_quizzes 0 20241026-22:34:43 train_loss 56 model 0 0.03714834424257278 20241026-22:34:43 quiz_set nb_w_quizzes 2500 nb_c_quizzes 0 20241026-22:34:50 test_loss 56 model 0 0.028594720840454103 20241026-22:34:50 quiz_set nb_w_quizzes 2500 nb_c_quizzes 0 20241026-22:34:59 test_accuracy 56 model 0 nb_correct 2349 / 2500 (93.96%) 20241026-22:34:59 quiz_set nb_w_quizzes 150 nb_c_quizzes 0 20241026-22:35:13 wrote reasoning.pth 20241026-22:35:13 quiz_set nb_w_quizzes 256 nb_c_quizzes 0 20241026-22:35:17 quiz_set nb_w_quizzes 50000 nb_c_quizzes 0 20241026-22:43:10 train_loss 57 model 0 0.036796553981304166 20241026-22:43:10 quiz_set nb_w_quizzes 2500 nb_c_quizzes 0 20241026-22:43:18 test_loss 57 model 0 0.026342714309692383 20241026-22:43:18 quiz_set nb_w_quizzes 2500 nb_c_quizzes 0 20241026-22:43:27 test_accuracy 57 model 0 nb_correct 2355 / 2500 (94.20%) 20241026-22:43:27 quiz_set nb_w_quizzes 150 nb_c_quizzes 0 20241026-22:43:42 wrote reasoning.pth 20241026-22:43:42 quiz_set nb_w_quizzes 256 nb_c_quizzes 0 20241026-22:43:45 quiz_set nb_w_quizzes 50000 nb_c_quizzes 0 20241026-22:51:25 train_loss 58 model 0 0.03638674791753292 20241026-22:51:25 quiz_set nb_w_quizzes 2500 nb_c_quizzes 0 20241026-22:51:33 test_loss 58 model 0 0.026258593082427978 20241026-22:51:33 quiz_set nb_w_quizzes 2500 nb_c_quizzes 0 20241026-22:51:42 test_accuracy 58 model 0 nb_correct 2325 / 2500 (93.00%) 20241026-22:51:42 quiz_set nb_w_quizzes 150 nb_c_quizzes 0 20241026-22:51:56 wrote reasoning.pth 20241026-22:51:56 quiz_set nb_w_quizzes 256 nb_c_quizzes 0 20241026-22:51:59 quiz_set nb_w_quizzes 50000 nb_c_quizzes 0 20241026-22:59:38 train_loss 59 model 0 0.03612574443817139 20241026-22:59:38 quiz_set nb_w_quizzes 2500 nb_c_quizzes 0 20241026-22:59:46 test_loss 59 model 0 0.026866363525390624 20241026-22:59:46 quiz_set nb_w_quizzes 2500 nb_c_quizzes 0 20241026-22:59:54 test_accuracy 59 model 0 nb_correct 2412 / 2500 (96.48%) 20241026-22:59:54 quiz_set nb_w_quizzes 150 nb_c_quizzes 0 20241026-23:00:09 wrote reasoning.pth 20241026-23:00:09 quiz_set nb_w_quizzes 256 nb_c_quizzes 0 20241026-23:00:12 quiz_set nb_w_quizzes 50000 nb_c_quizzes 0 20241026-23:07:57 train_loss 60 model 0 0.036134620714187625 20241026-23:07:57 quiz_set nb_w_quizzes 2500 nb_c_quizzes 0 20241026-23:08:05 test_loss 60 model 0 0.027198707580566406 20241026-23:08:05 quiz_set nb_w_quizzes 2500 nb_c_quizzes 0 20241026-23:08:13 test_accuracy 60 model 0 nb_correct 2391 / 2500 (95.64%) 20241026-23:08:13 quiz_set nb_w_quizzes 150 nb_c_quizzes 0 20241026-23:08:28 wrote reasoning.pth 20241026-23:08:28 quiz_set nb_w_quizzes 256 nb_c_quizzes 0 20241026-23:08:31 quiz_set nb_w_quizzes 50000 nb_c_quizzes 0 20241026-23:16:10 train_loss 61 model 0 0.03612827044725418 20241026-23:16:10 quiz_set nb_w_quizzes 2500 nb_c_quizzes 0 20241026-23:16:18 test_loss 61 model 0 0.02452927140891552 20241026-23:16:18 quiz_set nb_w_quizzes 2500 nb_c_quizzes 0 20241026-23:16:26 test_accuracy 61 model 0 nb_correct 2411 / 2500 (96.44%) 20241026-23:16:26 quiz_set nb_w_quizzes 150 nb_c_quizzes 0 20241026-23:16:40 wrote reasoning.pth 20241026-23:16:40 quiz_set nb_w_quizzes 256 nb_c_quizzes 0 20241026-23:16:43 quiz_set nb_w_quizzes 50000 nb_c_quizzes 0 20241026-23:24:28 train_loss 62 model 0 0.03571414937973023 20241026-23:24:28 quiz_set nb_w_quizzes 2500 nb_c_quizzes 0 20241026-23:24:35 test_loss 62 model 0 0.027225071430206298 20241026-23:24:35 quiz_set nb_w_quizzes 2500 nb_c_quizzes 0 20241026-23:24:43 test_accuracy 62 model 0 nb_correct 2397 / 2500 (95.88%) 20241026-23:24:43 quiz_set nb_w_quizzes 150 nb_c_quizzes 0 20241026-23:24:58 wrote reasoning.pth 20241026-23:24:58 quiz_set nb_w_quizzes 256 nb_c_quizzes 0 20241026-23:25:01 quiz_set nb_w_quizzes 50000 nb_c_quizzes 0 20241026-23:32:47 train_loss 63 model 0 0.03468295871019363 20241026-23:32:47 quiz_set nb_w_quizzes 2500 nb_c_quizzes 0 20241026-23:32:55 test_loss 63 model 0 0.025491981506347655 20241026-23:32:55 quiz_set nb_w_quizzes 2500 nb_c_quizzes 0 20241026-23:33:03 test_accuracy 63 model 0 nb_correct 2365 / 2500 (94.60%) 20241026-23:33:03 quiz_set nb_w_quizzes 150 nb_c_quizzes 0 20241026-23:33:17 wrote reasoning.pth 20241026-23:33:17 quiz_set nb_w_quizzes 256 nb_c_quizzes 0 20241026-23:33:20 quiz_set nb_w_quizzes 50000 nb_c_quizzes 0 20241026-23:41:09 train_loss 64 model 0 0.035169251227378844 20241026-23:41:09 quiz_set nb_w_quizzes 2500 nb_c_quizzes 0 20241026-23:41:17 test_loss 64 model 0 0.02427301502227783 20241026-23:41:17 quiz_set nb_w_quizzes 2500 nb_c_quizzes 0 20241026-23:41:25 test_accuracy 64 model 0 nb_correct 2398 / 2500 (95.92%) 20241026-23:41:25 quiz_set nb_w_quizzes 150 nb_c_quizzes 0 20241026-23:41:40 wrote reasoning.pth 20241026-23:41:40 quiz_set nb_w_quizzes 256 nb_c_quizzes 0 20241026-23:41:43 quiz_set nb_w_quizzes 50000 nb_c_quizzes 0 20241026-23:49:27 train_loss 65 model 0 0.03515244975090027 20241026-23:49:27 quiz_set nb_w_quizzes 2500 nb_c_quizzes 0 20241026-23:49:35 test_loss 65 model 0 0.02254533290863037 20241026-23:49:35 quiz_set nb_w_quizzes 2500 nb_c_quizzes 0 20241026-23:49:43 test_accuracy 65 model 0 nb_correct 2440 / 2500 (97.60%) 20241026-23:49:43 quiz_set nb_w_quizzes 150 nb_c_quizzes 0 20241026-23:49:58 wrote reasoning.pth 20241026-23:49:58 quiz_set nb_w_quizzes 256 nb_c_quizzes 0 20241026-23:50:01 quiz_set nb_w_quizzes 50000 nb_c_quizzes 0 20241026-23:57:42 train_loss 66 model 0 0.03465883438587189 20241026-23:57:42 quiz_set nb_w_quizzes 2500 nb_c_quizzes 0 20241026-23:57:50 test_loss 66 model 0 0.023318833589553833 20241026-23:57:50 quiz_set nb_w_quizzes 2500 nb_c_quizzes 0 20241026-23:57:58 test_accuracy 66 model 0 nb_correct 2417 / 2500 (96.68%) 20241026-23:57:58 quiz_set nb_w_quizzes 150 nb_c_quizzes 0 20241026-23:58:13 wrote reasoning.pth 20241026-23:58:13 quiz_set nb_w_quizzes 256 nb_c_quizzes 0 20241026-23:58:16 quiz_set nb_w_quizzes 50000 nb_c_quizzes 0 20241027-00:05:58 train_loss 67 model 0 0.03408966798782349 20241027-00:05:58 quiz_set nb_w_quizzes 2500 nb_c_quizzes 0 20241027-00:06:06 test_loss 67 model 0 0.02580696988105774 20241027-00:06:06 quiz_set nb_w_quizzes 2500 nb_c_quizzes 0 20241027-00:06:14 test_accuracy 67 model 0 nb_correct 2353 / 2500 (94.12%) 20241027-00:06:14 quiz_set nb_w_quizzes 150 nb_c_quizzes 0 20241027-00:06:28 wrote reasoning.pth 20241027-00:06:28 quiz_set nb_w_quizzes 256 nb_c_quizzes 0 20241027-00:06:32 quiz_set nb_w_quizzes 50000 nb_c_quizzes 0 20241027-00:14:12 train_loss 68 model 0 0.034080808305740354 20241027-00:14:12 quiz_set nb_w_quizzes 2500 nb_c_quizzes 0 20241027-00:14:19 test_loss 68 model 0 0.02588017749786377 20241027-00:14:19 quiz_set nb_w_quizzes 2500 nb_c_quizzes 0 20241027-00:14:27 test_accuracy 68 model 0 nb_correct 2413 / 2500 (96.52%) 20241027-00:14:27 quiz_set nb_w_quizzes 150 nb_c_quizzes 0 20241027-00:14:42 wrote reasoning.pth 20241027-00:14:42 quiz_set nb_w_quizzes 256 nb_c_quizzes 0 20241027-00:14:45 quiz_set nb_w_quizzes 50000 nb_c_quizzes 0 20241027-00:22:26 train_loss 69 model 0 0.03378744268417359 20241027-00:22:26 quiz_set nb_w_quizzes 2500 nb_c_quizzes 0 20241027-00:22:34 test_loss 69 model 0 0.022243215084075927 20241027-00:22:34 quiz_set nb_w_quizzes 2500 nb_c_quizzes 0 20241027-00:22:42 test_accuracy 69 model 0 nb_correct 2442 / 2500 (97.68%) 20241027-00:22:42 quiz_set nb_w_quizzes 150 nb_c_quizzes 0 20241027-00:22:56 wrote reasoning.pth 20241027-00:22:56 quiz_set nb_w_quizzes 256 nb_c_quizzes 0 20241027-00:23:00 quiz_set nb_w_quizzes 50000 nb_c_quizzes 0 20241027-00:30:39 train_loss 70 model 0 0.03378157732486725 20241027-00:30:39 quiz_set nb_w_quizzes 2500 nb_c_quizzes 0 20241027-00:30:47 test_loss 70 model 0 0.025009858131408692 20241027-00:30:47 quiz_set nb_w_quizzes 2500 nb_c_quizzes 0 20241027-00:30:55 test_accuracy 70 model 0 nb_correct 2416 / 2500 (96.64%) 20241027-00:30:55 quiz_set nb_w_quizzes 150 nb_c_quizzes 0 20241027-00:31:09 wrote reasoning.pth 20241027-00:31:09 quiz_set nb_w_quizzes 256 nb_c_quizzes 0 20241027-00:31:12 quiz_set nb_w_quizzes 50000 nb_c_quizzes 0 20241027-00:39:04 train_loss 71 model 0 0.0333169371843338 20241027-00:39:04 quiz_set nb_w_quizzes 2500 nb_c_quizzes 0 20241027-00:39:12 test_loss 71 model 0 0.023479335784912108 20241027-00:39:12 quiz_set nb_w_quizzes 2500 nb_c_quizzes 0 20241027-00:39:20 test_accuracy 71 model 0 nb_correct 2421 / 2500 (96.84%) 20241027-00:39:20 quiz_set nb_w_quizzes 150 nb_c_quizzes 0 20241027-00:39:35 wrote reasoning.pth 20241027-00:39:35 quiz_set nb_w_quizzes 256 nb_c_quizzes 0 20241027-00:39:38 quiz_set nb_w_quizzes 50000 nb_c_quizzes 0 20241027-00:47:16 train_loss 72 model 0 0.033115634775161745 20241027-00:47:16 quiz_set nb_w_quizzes 2500 nb_c_quizzes 0 20241027-00:47:24 test_loss 72 model 0 0.023808969497680663 20241027-00:47:24 quiz_set nb_w_quizzes 2500 nb_c_quizzes 0 20241027-00:47:32 test_accuracy 72 model 0 nb_correct 2422 / 2500 (96.88%) 20241027-00:47:32 quiz_set nb_w_quizzes 150 nb_c_quizzes 0 20241027-00:47:46 wrote reasoning.pth 20241027-00:47:46 quiz_set nb_w_quizzes 256 nb_c_quizzes 0 20241027-00:47:49 quiz_set nb_w_quizzes 50000 nb_c_quizzes 0 20241027-00:55:28 train_loss 73 model 0 0.033198013627529145 20241027-00:55:28 quiz_set nb_w_quizzes 2500 nb_c_quizzes 0 20241027-00:55:36 test_loss 73 model 0 0.02430002546310425 20241027-00:55:36 quiz_set nb_w_quizzes 2500 nb_c_quizzes 0 20241027-00:55:45 test_accuracy 73 model 0 nb_correct 2426 / 2500 (97.04%) 20241027-00:55:45 quiz_set nb_w_quizzes 150 nb_c_quizzes 0 20241027-00:55:59 wrote reasoning.pth 20241027-00:55:59 quiz_set nb_w_quizzes 256 nb_c_quizzes 0 20241027-00:56:02 quiz_set nb_w_quizzes 50000 nb_c_quizzes 0 20241027-01:04:09 train_loss 74 model 0 0.03282757244110107 20241027-01:04:09 quiz_set nb_w_quizzes 2500 nb_c_quizzes 0 20241027-01:04:17 test_loss 74 model 0 0.02381919240951538 20241027-01:04:17 quiz_set nb_w_quizzes 2500 nb_c_quizzes 0 20241027-01:04:25 test_accuracy 74 model 0 nb_correct 2435 / 2500 (97.40%) 20241027-01:04:25 quiz_set nb_w_quizzes 150 nb_c_quizzes 0 20241027-01:04:39 wrote reasoning.pth 20241027-01:04:39 quiz_set nb_w_quizzes 256 nb_c_quizzes 0 20241027-01:04:43 quiz_set nb_w_quizzes 50000 nb_c_quizzes 0 20241027-01:13:01 train_loss 75 model 0 0.03247369219064713 20241027-01:13:01 quiz_set nb_w_quizzes 2500 nb_c_quizzes 0 20241027-01:13:09 test_loss 75 model 0 0.02184103059768677 20241027-01:13:09 quiz_set nb_w_quizzes 2500 nb_c_quizzes 0 20241027-01:13:17 test_accuracy 75 model 0 nb_correct 2428 / 2500 (97.12%) 20241027-01:13:17 quiz_set nb_w_quizzes 150 nb_c_quizzes 0 20241027-01:13:31 wrote reasoning.pth 20241027-01:13:31 quiz_set nb_w_quizzes 256 nb_c_quizzes 0 20241027-01:13:34 quiz_set nb_w_quizzes 50000 nb_c_quizzes 0 20241027-01:21:36 train_loss 76 model 0 0.032113976287841794 20241027-01:21:36 quiz_set nb_w_quizzes 2500 nb_c_quizzes 0 20241027-01:21:43 test_loss 76 model 0 0.022497615814208984 20241027-01:21:43 quiz_set nb_w_quizzes 2500 nb_c_quizzes 0 20241027-01:21:51 test_accuracy 76 model 0 nb_correct 2438 / 2500 (97.52%) 20241027-01:21:51 quiz_set nb_w_quizzes 150 nb_c_quizzes 0 20241027-01:22:06 wrote reasoning.pth 20241027-01:22:06 quiz_set nb_w_quizzes 256 nb_c_quizzes 0 20241027-01:22:09 quiz_set nb_w_quizzes 50000 nb_c_quizzes 0 20241027-01:30:03 train_loss 77 model 0 0.03261023964881897 20241027-01:30:03 quiz_set nb_w_quizzes 2500 nb_c_quizzes 0 20241027-01:30:11 test_loss 77 model 0 0.023357143878936767 20241027-01:30:11 quiz_set nb_w_quizzes 2500 nb_c_quizzes 0 20241027-01:30:19 test_accuracy 77 model 0 nb_correct 2436 / 2500 (97.44%) 20241027-01:30:19 quiz_set nb_w_quizzes 150 nb_c_quizzes 0 20241027-01:30:34 wrote reasoning.pth 20241027-01:30:34 quiz_set nb_w_quizzes 256 nb_c_quizzes 0 20241027-01:30:37 quiz_set nb_w_quizzes 50000 nb_c_quizzes 0 20241027-01:38:47 train_loss 78 model 0 0.032480770373344424 20241027-01:38:47 quiz_set nb_w_quizzes 2500 nb_c_quizzes 0 20241027-01:38:55 test_loss 78 model 0 0.023223236799240113 20241027-01:38:55 quiz_set nb_w_quizzes 2500 nb_c_quizzes 0 20241027-01:39:02 test_accuracy 78 model 0 nb_correct 2432 / 2500 (97.28%) 20241027-01:39:02 quiz_set nb_w_quizzes 150 nb_c_quizzes 0 20241027-01:39:17 wrote reasoning.pth 20241027-01:39:17 quiz_set nb_w_quizzes 256 nb_c_quizzes 0 20241027-01:39:20 quiz_set nb_w_quizzes 50000 nb_c_quizzes 0 20241027-01:47:01 train_loss 79 model 0 0.03184605348110199 20241027-01:47:01 quiz_set nb_w_quizzes 2500 nb_c_quizzes 0 20241027-01:47:09 test_loss 79 model 0 0.02483304500579834 20241027-01:47:09 quiz_set nb_w_quizzes 2500 nb_c_quizzes 0 20241027-01:47:17 test_accuracy 79 model 0 nb_correct 2437 / 2500 (97.48%) 20241027-01:47:17 quiz_set nb_w_quizzes 150 nb_c_quizzes 0 20241027-01:47:31 wrote reasoning.pth 20241027-01:47:31 quiz_set nb_w_quizzes 256 nb_c_quizzes 0 20241027-01:47:34 quiz_set nb_w_quizzes 50000 nb_c_quizzes 0 20241027-01:55:42 train_loss 80 model 0 0.03166789667606354 20241027-01:55:42 quiz_set nb_w_quizzes 2500 nb_c_quizzes 0 20241027-01:55:50 test_loss 80 model 0 0.022221982002258302 20241027-01:55:50 quiz_set nb_w_quizzes 2500 nb_c_quizzes 0 20241027-01:55:58 test_accuracy 80 model 0 nb_correct 2454 / 2500 (98.16%) 20241027-01:55:58 quiz_set nb_w_quizzes 150 nb_c_quizzes 0 20241027-01:56:12 wrote reasoning.pth 20241027-01:56:12 quiz_set nb_w_quizzes 256 nb_c_quizzes 0 20241027-01:56:15 quiz_set nb_w_quizzes 50000 nb_c_quizzes 0 20241027-02:03:55 train_loss 81 model 0 0.03150317769050598 20241027-02:03:55 quiz_set nb_w_quizzes 2500 nb_c_quizzes 0 20241027-02:04:03 test_loss 81 model 0 0.024557944297790527 20241027-02:04:03 quiz_set nb_w_quizzes 2500 nb_c_quizzes 0 20241027-02:04:11 test_accuracy 81 model 0 nb_correct 2452 / 2500 (98.08%) 20241027-02:04:11 quiz_set nb_w_quizzes 150 nb_c_quizzes 0 20241027-02:04:25 wrote reasoning.pth 20241027-02:04:25 quiz_set nb_w_quizzes 256 nb_c_quizzes 0 20241027-02:04:28 quiz_set nb_w_quizzes 50000 nb_c_quizzes 0 20241027-02:12:26 train_loss 82 model 0 0.0316843515753746 20241027-02:12:26 quiz_set nb_w_quizzes 2500 nb_c_quizzes 0 20241027-02:12:34 test_loss 82 model 0 0.02235838282108307 20241027-02:12:34 quiz_set nb_w_quizzes 2500 nb_c_quizzes 0 20241027-02:12:41 test_accuracy 82 model 0 nb_correct 2436 / 2500 (97.44%) 20241027-02:12:41 quiz_set nb_w_quizzes 150 nb_c_quizzes 0 20241027-02:12:56 wrote reasoning.pth 20241027-02:12:56 quiz_set nb_w_quizzes 256 nb_c_quizzes 0 20241027-02:12:59 quiz_set nb_w_quizzes 50000 nb_c_quizzes 0 20241027-02:21:09 train_loss 83 model 0 0.03141740815639496 20241027-02:21:09 quiz_set nb_w_quizzes 2500 nb_c_quizzes 0 20241027-02:21:17 test_loss 83 model 0 0.022565375320613385 20241027-02:21:17 quiz_set nb_w_quizzes 2500 nb_c_quizzes 0 20241027-02:21:25 test_accuracy 83 model 0 nb_correct 2452 / 2500 (98.08%) 20241027-02:21:25 quiz_set nb_w_quizzes 150 nb_c_quizzes 0 20241027-02:21:39 wrote reasoning.pth 20241027-02:21:39 quiz_set nb_w_quizzes 256 nb_c_quizzes 0 20241027-02:21:42 quiz_set nb_w_quizzes 50000 nb_c_quizzes 0 20241027-02:29:25 train_loss 84 model 0 0.0317225371837616 20241027-02:29:25 quiz_set nb_w_quizzes 2500 nb_c_quizzes 0 20241027-02:29:33 test_loss 84 model 0 0.025468446016311645 20241027-02:29:33 quiz_set nb_w_quizzes 2500 nb_c_quizzes 0 20241027-02:29:41 test_accuracy 84 model 0 nb_correct 2431 / 2500 (97.24%) 20241027-02:29:41 quiz_set nb_w_quizzes 150 nb_c_quizzes 0 20241027-02:29:55 wrote reasoning.pth 20241027-02:29:55 quiz_set nb_w_quizzes 256 nb_c_quizzes 0 20241027-02:29:58 quiz_set nb_w_quizzes 50000 nb_c_quizzes 0 20241027-02:38:10 train_loss 85 model 0 0.030742025780677796 20241027-02:38:10 quiz_set nb_w_quizzes 2500 nb_c_quizzes 0 20241027-02:38:18 test_loss 85 model 0 0.02328262686729431 20241027-02:38:18 quiz_set nb_w_quizzes 2500 nb_c_quizzes 0 20241027-02:38:26 test_accuracy 85 model 0 nb_correct 2429 / 2500 (97.16%) 20241027-02:38:26 quiz_set nb_w_quizzes 150 nb_c_quizzes 0 20241027-02:38:40 wrote reasoning.pth 20241027-02:38:40 quiz_set nb_w_quizzes 256 nb_c_quizzes 0 20241027-02:38:44 quiz_set nb_w_quizzes 50000 nb_c_quizzes 0 20241027-02:46:52 train_loss 86 model 0 0.03146909049153328 20241027-02:46:52 quiz_set nb_w_quizzes 2500 nb_c_quizzes 0 20241027-02:47:00 test_loss 86 model 0 0.02253323268890381 20241027-02:47:00 quiz_set nb_w_quizzes 2500 nb_c_quizzes 0 20241027-02:47:08 test_accuracy 86 model 0 nb_correct 2450 / 2500 (98.00%) 20241027-02:47:08 quiz_set nb_w_quizzes 150 nb_c_quizzes 0 20241027-02:47:22 wrote reasoning.pth 20241027-02:47:22 quiz_set nb_w_quizzes 256 nb_c_quizzes 0 20241027-02:47:25 quiz_set nb_w_quizzes 50000 nb_c_quizzes 0 20241027-02:55:43 train_loss 87 model 0 0.0324437592625618 20241027-02:55:43 quiz_set nb_w_quizzes 2500 nb_c_quizzes 0 20241027-02:55:51 test_loss 87 model 0 0.03014275473356247 20241027-02:55:51 quiz_set nb_w_quizzes 2500 nb_c_quizzes 0 20241027-02:55:58 test_accuracy 87 model 0 nb_correct 2389 / 2500 (95.56%) 20241027-02:55:58 quiz_set nb_w_quizzes 150 nb_c_quizzes 0 20241027-02:56:13 wrote reasoning.pth 20241027-02:56:13 quiz_set nb_w_quizzes 256 nb_c_quizzes 0 20241027-02:56:16 quiz_set nb_w_quizzes 50000 nb_c_quizzes 0 20241027-02:04:21 train_loss 88 model 0 0.035036446690559386 20241027-02:04:21 quiz_set nb_w_quizzes 2500 nb_c_quizzes 0 20241027-02:04:29 test_loss 88 model 0 0.01976126706600189 20241027-02:04:29 quiz_set nb_w_quizzes 2500 nb_c_quizzes 0 20241027-02:04:37 test_accuracy 88 model 0 nb_correct 2458 / 2500 (98.32%) 20241027-02:04:37 quiz_set nb_w_quizzes 150 nb_c_quizzes 0 20241027-02:04:51 wrote reasoning.pth 20241027-02:04:51 quiz_set nb_w_quizzes 256 nb_c_quizzes 0 20241027-02:04:54 quiz_set nb_w_quizzes 50000 nb_c_quizzes 0 20241027-02:13:14 train_loss 89 model 0 0.5677008141756058 20241027-02:13:14 quiz_set nb_w_quizzes 2500 nb_c_quizzes 0 20241027-02:13:22 test_loss 89 model 0 1.062 20241027-02:13:22 quiz_set nb_w_quizzes 2500 nb_c_quizzes 0 20241027-02:13:30 test_accuracy 89 model 0 nb_correct 0 / 2500 (0.00%) 20241027-02:13:30 quiz_set nb_w_quizzes 150 nb_c_quizzes 0 20241027-02:13:46 wrote reasoning.pth 20241027-02:13:46 quiz_set nb_w_quizzes 256 nb_c_quizzes 0 20241027-02:13:49 quiz_set nb_w_quizzes 50000 nb_c_quizzes 0 20241027-02:21:56 train_loss 90 model 0 2.773657421875 20241027-02:21:56 quiz_set nb_w_quizzes 2500 nb_c_quizzes 0 20241027-02:22:04 test_loss 90 model 0 4.2510625 20241027-02:22:04 quiz_set nb_w_quizzes 2500 nb_c_quizzes 0 20241027-02:22:12 test_accuracy 90 model 0 nb_correct 0 / 2500 (0.00%) 20241027-02:22:12 quiz_set nb_w_quizzes 150 nb_c_quizzes 0 20241027-02:22:28 wrote reasoning.pth 20241027-02:22:28 quiz_set nb_w_quizzes 256 nb_c_quizzes 0 20241027-02:22:31 quiz_set nb_w_quizzes 50000 nb_c_quizzes 0 20241027-02:30:13 train_loss 91 model 0 4.64564375 20241027-02:30:13 quiz_set nb_w_quizzes 2500 nb_c_quizzes 0 20241027-02:30:21 test_loss 91 model 0 1.486640625 20241027-02:30:21 quiz_set nb_w_quizzes 2500 nb_c_quizzes 0 20241027-02:30:28 test_accuracy 91 model 0 nb_correct 0 / 2500 (0.00%) 20241027-02:30:28 quiz_set nb_w_quizzes 150 nb_c_quizzes 0 20241027-02:30:45 wrote reasoning.pth 20241027-02:30:45 quiz_set nb_w_quizzes 256 nb_c_quizzes 0 20241027-02:30:48 quiz_set nb_w_quizzes 50000 nb_c_quizzes 0 20241027-02:38:27 train_loss 92 model 0 12.778171875 20241027-02:38:27 quiz_set nb_w_quizzes 2500 nb_c_quizzes 0 20241027-02:38:35 test_loss 92 model 0 6.0866875 20241027-02:38:35 quiz_set nb_w_quizzes 2500 nb_c_quizzes 0 20241027-02:38:43 test_accuracy 92 model 0 nb_correct 0 / 2500 (0.00%) 20241027-02:38:43 quiz_set nb_w_quizzes 150 nb_c_quizzes 0 20241027-02:38:59 wrote reasoning.pth 20241027-02:38:59 quiz_set nb_w_quizzes 256 nb_c_quizzes 0 20241027-02:39:02 quiz_set nb_w_quizzes 50000 nb_c_quizzes 0 20241027-02:46:51 train_loss 93 model 0 10.2876875 20241027-02:46:51 quiz_set nb_w_quizzes 2500 nb_c_quizzes 0 20241027-02:46:59 test_loss 93 model 0 10.99975 20241027-02:46:59 quiz_set nb_w_quizzes 2500 nb_c_quizzes 0 20241027-02:47:07 test_accuracy 93 model 0 nb_correct 0 / 2500 (0.00%) 20241027-02:47:07 quiz_set nb_w_quizzes 150 nb_c_quizzes 0 20241027-02:47:21 wrote reasoning.pth 20241027-02:47:21 quiz_set nb_w_quizzes 256 nb_c_quizzes 0 20241027-02:47:24 quiz_set nb_w_quizzes 50000 nb_c_quizzes 0 20241027-02:55:27 train_loss 94 model 0 25.059915625 20241027-02:55:27 quiz_set nb_w_quizzes 2500 nb_c_quizzes 0 20241027-02:55:35 test_loss 94 model 0 20.072875 20241027-02:55:35 quiz_set nb_w_quizzes 2500 nb_c_quizzes 0 20241027-02:55:43 test_accuracy 94 model 0 nb_correct 0 / 2500 (0.00%) 20241027-02:55:43 quiz_set nb_w_quizzes 150 nb_c_quizzes 0 20241027-02:55:57 wrote reasoning.pth 20241027-02:55:57 quiz_set nb_w_quizzes 256 nb_c_quizzes 0 20241027-02:56:00 quiz_set nb_w_quizzes 50000 nb_c_quizzes 0 20241027-03:04:14 train_loss 95 model 0 33.48465 20241027-03:04:14 quiz_set nb_w_quizzes 2500 nb_c_quizzes 0 20241027-03:04:22 test_loss 95 model 0 26.61775 20241027-03:04:22 quiz_set nb_w_quizzes 2500 nb_c_quizzes 0 20241027-03:04:29 test_accuracy 95 model 0 nb_correct 0 / 2500 (0.00%) 20241027-03:04:29 quiz_set nb_w_quizzes 150 nb_c_quizzes 0 20241027-03:04:43 wrote reasoning.pth 20241027-03:04:43 quiz_set nb_w_quizzes 256 nb_c_quizzes 0 20241027-03:04:46 quiz_set nb_w_quizzes 50000 nb_c_quizzes 0 20241027-03:13:05 train_loss 96 model 0 59.009925 20241027-03:13:05 quiz_set nb_w_quizzes 2500 nb_c_quizzes 0 20241027-03:13:12 test_loss 96 model 0 53.541 20241027-03:13:12 quiz_set nb_w_quizzes 2500 nb_c_quizzes 0 20241027-03:13:20 test_accuracy 96 model 0 nb_correct 0 / 2500 (0.00%) 20241027-03:13:20 quiz_set nb_w_quizzes 150 nb_c_quizzes 0 20241027-03:13:34 wrote reasoning.pth 20241027-03:13:34 quiz_set nb_w_quizzes 256 nb_c_quizzes 0 20241027-03:13:38 quiz_set nb_w_quizzes 50000 nb_c_quizzes 0 20241027-03:21:37 train_loss 97 model 0 92.2917875 20241027-03:21:37 quiz_set nb_w_quizzes 2500 nb_c_quizzes 0 20241027-03:21:44 test_loss 97 model 0 78.4945 20241027-03:21:44 quiz_set nb_w_quizzes 2500 nb_c_quizzes 0 20241027-03:21:52 test_accuracy 97 model 0 nb_correct 0 / 2500 (0.00%) 20241027-03:21:52 quiz_set nb_w_quizzes 150 nb_c_quizzes 0 20241027-03:22:06 wrote reasoning.pth 20241027-03:22:06 quiz_set nb_w_quizzes 256 nb_c_quizzes 0 20241027-03:22:09 quiz_set nb_w_quizzes 50000 nb_c_quizzes 0 20241027-03:29:49 train_loss 98 model 0 121.72115 20241027-03:29:49 quiz_set nb_w_quizzes 2500 nb_c_quizzes 0 20241027-03:29:57 test_loss 98 model 0 87.406 20241027-03:29:57 quiz_set nb_w_quizzes 2500 nb_c_quizzes 0 20241027-03:30:04 test_accuracy 98 model 0 nb_correct 0 / 2500 (0.00%) 20241027-03:30:04 quiz_set nb_w_quizzes 150 nb_c_quizzes 0 20241027-03:30:18 wrote reasoning.pth 20241027-03:30:18 quiz_set nb_w_quizzes 256 nb_c_quizzes 0 20241027-03:30:22 quiz_set nb_w_quizzes 50000 nb_c_quizzes 0 20241027-03:38:08 train_loss 99 model 0 153.82285 20241027-03:38:09 quiz_set nb_w_quizzes 2500 nb_c_quizzes 0 20241027-03:38:16 test_loss 99 model 0 177.022 20241027-03:38:16 quiz_set nb_w_quizzes 2500 nb_c_quizzes 0 20241027-03:38:24 test_accuracy 99 model 0 nb_correct 0 / 2500 (0.00%) 20241027-03:38:24 quiz_set nb_w_quizzes 150 nb_c_quizzes 0 20241027-03:38:38 wrote reasoning.pth 20241027-03:38:38 quiz_set nb_w_quizzes 256 nb_c_quizzes 0 20241027-03:38:41 quiz_set nb_w_quizzes 50000 nb_c_quizzes 0 20241027-03:46:54 train_loss 100 model 0 195.02365 20241027-03:46:54 quiz_set nb_w_quizzes 2500 nb_c_quizzes 0 20241027-03:47:01 test_loss 100 model 0 145.68 20241027-03:47:01 quiz_set nb_w_quizzes 2500 nb_c_quizzes 0 20241027-03:47:09 test_accuracy 100 model 0 nb_correct 0 / 2500 (0.00%) 20241027-03:47:09 quiz_set nb_w_quizzes 150 nb_c_quizzes 0 20241027-03:47:25 wrote reasoning.pth 20241027-03:47:25 quiz_set nb_w_quizzes 256 nb_c_quizzes 0 20241027-03:47:29 quiz_set nb_w_quizzes 50000 nb_c_quizzes 0 20241027-03:55:12 train_loss 101 model 0 215.0651 20241027-03:55:12 quiz_set nb_w_quizzes 2500 nb_c_quizzes 0 20241027-03:55:20 test_loss 101 model 0 153.23 20241027-03:55:20 quiz_set nb_w_quizzes 2500 nb_c_quizzes 0 20241027-03:55:28 test_accuracy 101 model 0 nb_correct 0 / 2500 (0.00%) 20241027-03:55:28 quiz_set nb_w_quizzes 150 nb_c_quizzes 0 20241027-03:55:44 wrote reasoning.pth 20241027-03:55:44 quiz_set nb_w_quizzes 256 nb_c_quizzes 0 20241027-03:55:47 quiz_set nb_w_quizzes 50000 nb_c_quizzes 0 20241027-04:03:38 train_loss 102 model 0 240.6391 20241027-04:03:38 quiz_set nb_w_quizzes 2500 nb_c_quizzes 0 20241027-04:03:45 test_loss 102 model 0 145.831 20241027-04:03:45 quiz_set nb_w_quizzes 2500 nb_c_quizzes 0 20241027-04:03:53 test_accuracy 102 model 0 nb_correct 0 / 2500 (0.00%) 20241027-04:03:53 quiz_set nb_w_quizzes 150 nb_c_quizzes 0 20241027-04:04:07 wrote reasoning.pth 20241027-04:04:07 quiz_set nb_w_quizzes 256 nb_c_quizzes 0 20241027-04:04:11 quiz_set nb_w_quizzes 50000 nb_c_quizzes 0 20241027-04:12:08 train_loss 103 model 0 248.0277 20241027-04:12:08 quiz_set nb_w_quizzes 2500 nb_c_quizzes 0 20241027-04:12:16 test_loss 103 model 0 149.958 20241027-04:12:16 quiz_set nb_w_quizzes 2500 nb_c_quizzes 0 20241027-04:12:24 test_accuracy 103 model 0 nb_correct 0 / 2500 (0.00%) 20241027-04:12:24 quiz_set nb_w_quizzes 150 nb_c_quizzes 0 20241027-04:12:40 wrote reasoning.pth 20241027-04:12:40 quiz_set nb_w_quizzes 256 nb_c_quizzes 0 20241027-04:12:43 quiz_set nb_w_quizzes 50000 nb_c_quizzes 0 20241027-04:20:51 train_loss 104 model 0 271.2763 20241027-04:20:51 quiz_set nb_w_quizzes 2500 nb_c_quizzes 0 20241027-04:20:59 test_loss 104 model 0 191.216 20241027-04:20:59 quiz_set nb_w_quizzes 2500 nb_c_quizzes 0 20241027-04:21:07 test_accuracy 104 model 0 nb_correct 0 / 2500 (0.00%) 20241027-04:21:07 quiz_set nb_w_quizzes 150 nb_c_quizzes 0 20241027-04:21:21 wrote reasoning.pth 20241027-04:21:21 quiz_set nb_w_quizzes 256 nb_c_quizzes 0 20241027-04:21:24 quiz_set nb_w_quizzes 50000 nb_c_quizzes 0 20241027-04:29:03 train_loss 105 model 0 299.9876 20241027-04:29:03 quiz_set nb_w_quizzes 2500 nb_c_quizzes 0 20241027-04:29:11 test_loss 105 model 0 256.758 20241027-04:29:11 quiz_set nb_w_quizzes 2500 nb_c_quizzes 0 20241027-04:29:19 test_accuracy 105 model 0 nb_correct 0 / 2500 (0.00%) 20241027-04:29:19 quiz_set nb_w_quizzes 150 nb_c_quizzes 0 20241027-04:29:33 wrote reasoning.pth 20241027-04:29:33 quiz_set nb_w_quizzes 256 nb_c_quizzes 0 20241027-04:29:36 quiz_set nb_w_quizzes 50000 nb_c_quizzes 0 20241027-04:37:43 train_loss 106 model 0 314.5561 20241027-04:37:43 quiz_set nb_w_quizzes 2500 nb_c_quizzes 0 20241027-04:37:51 test_loss 106 model 0 236.574 20241027-04:37:51 quiz_set nb_w_quizzes 2500 nb_c_quizzes 0 20241027-04:37:59 test_accuracy 106 model 0 nb_correct 0 / 2500 (0.00%) 20241027-04:37:59 quiz_set nb_w_quizzes 150 nb_c_quizzes 0 20241027-04:38:15 wrote reasoning.pth 20241027-04:38:15 quiz_set nb_w_quizzes 256 nb_c_quizzes 0 20241027-04:38:18 quiz_set nb_w_quizzes 50000 nb_c_quizzes 0 20241027-04:46:38 train_loss 107 model 0 348.7287 20241027-04:46:38 quiz_set nb_w_quizzes 2500 nb_c_quizzes 0 20241027-04:46:45 test_loss 107 model 0 157.824 20241027-04:46:45 quiz_set nb_w_quizzes 2500 nb_c_quizzes 0 20241027-04:46:53 test_accuracy 107 model 0 nb_correct 0 / 2500 (0.00%) 20241027-04:46:53 quiz_set nb_w_quizzes 150 nb_c_quizzes 0 20241027-04:47:07 wrote reasoning.pth 20241027-04:47:07 quiz_set nb_w_quizzes 256 nb_c_quizzes 0 20241027-04:47:10 quiz_set nb_w_quizzes 50000 nb_c_quizzes 0 20241027-04:54:50 train_loss 108 model 0 370.709 20241027-04:54:50 quiz_set nb_w_quizzes 2500 nb_c_quizzes 0 20241027-04:54:58 test_loss 108 model 0 249.976 20241027-04:54:58 quiz_set nb_w_quizzes 2500 nb_c_quizzes 0 20241027-04:55:05 test_accuracy 108 model 0 nb_correct 0 / 2500 (0.00%) 20241027-04:55:05 quiz_set nb_w_quizzes 150 nb_c_quizzes 0 20241027-04:55:22 wrote reasoning.pth 20241027-04:55:22 quiz_set nb_w_quizzes 256 nb_c_quizzes 0 20241027-04:55:25 quiz_set nb_w_quizzes 50000 nb_c_quizzes 0 20241027-05:03:06 train_loss 109 model 0 376.7542 20241027-05:03:06 quiz_set nb_w_quizzes 2500 nb_c_quizzes 0 20241027-05:03:14 test_loss 109 model 0 283.506 20241027-05:03:14 quiz_set nb_w_quizzes 2500 nb_c_quizzes 0 20241027-05:03:22 test_accuracy 109 model 0 nb_correct 0 / 2500 (0.00%) 20241027-05:03:22 quiz_set nb_w_quizzes 150 nb_c_quizzes 0 20241027-05:03:38 wrote reasoning.pth 20241027-05:03:38 quiz_set nb_w_quizzes 256 nb_c_quizzes 0 20241027-05:03:41 quiz_set nb_w_quizzes 50000 nb_c_quizzes 0 20241027-05:11:39 train_loss 110 model 0 399.6117 20241027-05:11:39 quiz_set nb_w_quizzes 2500 nb_c_quizzes 0 20241027-05:11:47 test_loss 110 model 0 210.014 20241027-05:11:47 quiz_set nb_w_quizzes 2500 nb_c_quizzes 0 20241027-05:11:54 test_accuracy 110 model 0 nb_correct 0 / 2500 (0.00%) 20241027-05:11:54 quiz_set nb_w_quizzes 150 nb_c_quizzes 0 20241027-05:12:11 wrote reasoning.pth 20241027-05:12:11 quiz_set nb_w_quizzes 256 nb_c_quizzes 0 20241027-05:12:14 quiz_set nb_w_quizzes 50000 nb_c_quizzes 0 20241027-05:20:30 train_loss 111 model 0 412.7952 20241027-05:20:30 quiz_set nb_w_quizzes 2500 nb_c_quizzes 0 20241027-05:20:38 test_loss 111 model 0 179.528 20241027-05:20:38 quiz_set nb_w_quizzes 2500 nb_c_quizzes 0 20241027-05:20:46 test_accuracy 111 model 0 nb_correct 0 / 2500 (0.00%) 20241027-05:20:46 quiz_set nb_w_quizzes 150 nb_c_quizzes 0 20241027-05:21:02 wrote reasoning.pth 20241027-05:21:02 quiz_set nb_w_quizzes 256 nb_c_quizzes 0 20241027-05:21:05 quiz_set nb_w_quizzes 50000 nb_c_quizzes 0 20241027-05:29:01 train_loss 112 model 0 426.7587 20241027-05:29:01 quiz_set nb_w_quizzes 2500 nb_c_quizzes 0 20241027-05:29:09 test_loss 112 model 0 329.036 20241027-05:29:09 quiz_set nb_w_quizzes 2500 nb_c_quizzes 0 20241027-05:29:17 test_accuracy 112 model 0 nb_correct 0 / 2500 (0.00%) 20241027-05:29:17 quiz_set nb_w_quizzes 150 nb_c_quizzes 0 20241027-05:29:33 wrote reasoning.pth 20241027-05:29:33 quiz_set nb_w_quizzes 256 nb_c_quizzes 0 20241027-05:29:36 quiz_set nb_w_quizzes 50000 nb_c_quizzes 0 20241027-05:37:52 train_loss 113 model 0 438.4936 20241027-05:37:52 quiz_set nb_w_quizzes 2500 nb_c_quizzes 0 20241027-05:38:00 test_loss 113 model 0 180.728 20241027-05:38:00 quiz_set nb_w_quizzes 2500 nb_c_quizzes 0 20241027-05:38:08 test_accuracy 113 model 0 nb_correct 0 / 2500 (0.00%) 20241027-05:38:08 quiz_set nb_w_quizzes 150 nb_c_quizzes 0 20241027-05:38:24 wrote reasoning.pth 20241027-05:38:24 quiz_set nb_w_quizzes 256 nb_c_quizzes 0 20241027-05:38:28 quiz_set nb_w_quizzes 50000 nb_c_quizzes 0 20241027-05:46:42 train_loss 114 model 0 467.1722 20241027-05:46:43 quiz_set nb_w_quizzes 2500 nb_c_quizzes 0 20241027-05:46:50 test_loss 114 model 0 128.335 20241027-05:46:50 quiz_set nb_w_quizzes 2500 nb_c_quizzes 0 20241027-05:46:58 test_accuracy 114 model 0 nb_correct 0 / 2500 (0.00%) 20241027-05:46:58 quiz_set nb_w_quizzes 150 nb_c_quizzes 0 20241027-05:47:12 wrote reasoning.pth 20241027-05:47:12 quiz_set nb_w_quizzes 256 nb_c_quizzes 0 20241027-05:47:15 quiz_set nb_w_quizzes 50000 nb_c_quizzes 0 20241027-05:54:56 train_loss 115 model 0 491.8356 20241027-05:54:56 quiz_set nb_w_quizzes 2500 nb_c_quizzes 0 20241027-05:55:04 test_loss 115 model 0 240.16 20241027-05:55:04 quiz_set nb_w_quizzes 2500 nb_c_quizzes 0 20241027-05:55:11 test_accuracy 115 model 0 nb_correct 0 / 2500 (0.00%) 20241027-05:55:11 quiz_set nb_w_quizzes 150 nb_c_quizzes 0 20241027-05:55:25 wrote reasoning.pth 20241027-05:55:25 quiz_set nb_w_quizzes 256 nb_c_quizzes 0 20241027-05:55:29 quiz_set nb_w_quizzes 50000 nb_c_quizzes 0 20241027-06:03:49 train_loss 116 model 0 525.618 20241027-06:03:49 quiz_set nb_w_quizzes 2500 nb_c_quizzes 0 20241027-06:03:57 test_loss 116 model 0 204.194 20241027-06:03:57 quiz_set nb_w_quizzes 2500 nb_c_quizzes 0 20241027-06:04:05 test_accuracy 116 model 0 nb_correct 0 / 2500 (0.00%) 20241027-06:04:05 quiz_set nb_w_quizzes 150 nb_c_quizzes 0 20241027-06:04:19 wrote reasoning.pth 20241027-06:04:19 quiz_set nb_w_quizzes 256 nb_c_quizzes 0 20241027-06:04:22 quiz_set nb_w_quizzes 50000 nb_c_quizzes 0 20241027-06:12:01 train_loss 117 model 0 551.9758 20241027-06:12:01 quiz_set nb_w_quizzes 2500 nb_c_quizzes 0 20241027-06:12:09 test_loss 117 model 0 583.628 20241027-06:12:09 quiz_set nb_w_quizzes 2500 nb_c_quizzes 0 20241027-06:12:17 test_accuracy 117 model 0 nb_correct 0 / 2500 (0.00%) 20241027-06:12:17 quiz_set nb_w_quizzes 150 nb_c_quizzes 0 20241027-06:12:33 wrote reasoning.pth 20241027-06:12:33 quiz_set nb_w_quizzes 256 nb_c_quizzes 0 20241027-06:12:37 quiz_set nb_w_quizzes 50000 nb_c_quizzes 0 20241027-06:20:15 train_loss 118 model 0 583.996 20241027-06:20:15 quiz_set nb_w_quizzes 2500 nb_c_quizzes 0 20241027-06:20:23 test_loss 118 model 0 1252.032 20241027-06:20:23 quiz_set nb_w_quizzes 2500 nb_c_quizzes 0 20241027-06:20:31 test_accuracy 118 model 0 nb_correct 0 / 2500 (0.00%) 20241027-06:20:31 quiz_set nb_w_quizzes 150 nb_c_quizzes 0 20241027-06:20:45 wrote reasoning.pth 20241027-06:20:45 quiz_set nb_w_quizzes 256 nb_c_quizzes 0 20241027-06:20:48 quiz_set nb_w_quizzes 50000 nb_c_quizzes 0 20241027-06:28:53 train_loss 119 model 0 607.1996 20241027-06:28:53 quiz_set nb_w_quizzes 2500 nb_c_quizzes 0 20241027-06:29:01 test_loss 119 model 0 309.896 20241027-06:29:01 quiz_set nb_w_quizzes 2500 nb_c_quizzes 0 20241027-06:29:09 test_accuracy 119 model 0 nb_correct 0 / 2500 (0.00%) 20241027-06:29:09 quiz_set nb_w_quizzes 150 nb_c_quizzes 0 20241027-06:29:25 wrote reasoning.pth 20241027-06:29:25 quiz_set nb_w_quizzes 256 nb_c_quizzes 0 20241027-06:29:29 quiz_set nb_w_quizzes 50000 nb_c_quizzes 0 20241027-06:37:21 train_loss 120 model 0 620.893 20241027-06:37:21 quiz_set nb_w_quizzes 2500 nb_c_quizzes 0 20241027-06:37:29 test_loss 120 model 0 1060.304 20241027-06:37:29 quiz_set nb_w_quizzes 2500 nb_c_quizzes 0 20241027-06:37:38 test_accuracy 120 model 0 nb_correct 0 / 2500 (0.00%) 20241027-06:37:38 quiz_set nb_w_quizzes 150 nb_c_quizzes 0 20241027-06:37:52 wrote reasoning.pth 20241027-06:37:52 quiz_set nb_w_quizzes 256 nb_c_quizzes 0 20241027-06:37:55 quiz_set nb_w_quizzes 50000 nb_c_quizzes 0 20241027-06:45:59 train_loss 121 model 0 642.7892 20241027-06:45:59 quiz_set nb_w_quizzes 2500 nb_c_quizzes 0 20241027-06:46:07 test_loss 121 model 0 267.6 20241027-06:46:07 quiz_set nb_w_quizzes 2500 nb_c_quizzes 0 20241027-06:46:16 test_accuracy 121 model 0 nb_correct 0 / 2500 (0.00%) 20241027-06:46:16 quiz_set nb_w_quizzes 150 nb_c_quizzes 0 20241027-06:46:32 wrote reasoning.pth 20241027-06:46:32 quiz_set nb_w_quizzes 256 nb_c_quizzes 0 20241027-06:46:35 quiz_set nb_w_quizzes 50000 nb_c_quizzes 0 20241027-06:54:36 train_loss 122 model 0 653.4626 20241027-06:54:36 quiz_set nb_w_quizzes 2500 nb_c_quizzes 0 20241027-06:54:44 test_loss 122 model 0 263.398 20241027-06:54:44 quiz_set nb_w_quizzes 2500 nb_c_quizzes 0 20241027-06:54:51 test_accuracy 122 model 0 nb_correct 0 / 2500 (0.00%) 20241027-06:54:51 quiz_set nb_w_quizzes 150 nb_c_quizzes 0 20241027-06:55:08 wrote reasoning.pth 20241027-06:55:08 quiz_set nb_w_quizzes 256 nb_c_quizzes 0 20241027-06:55:11 quiz_set nb_w_quizzes 50000 nb_c_quizzes 0 20241027-07:03:30 train_loss 123 model 0 672.7182 20241027-07:03:30 quiz_set nb_w_quizzes 2500 nb_c_quizzes 0 20241027-07:03:37 test_loss 123 model 0 266.944 20241027-07:03:37 quiz_set nb_w_quizzes 2500 nb_c_quizzes 0 20241027-07:03:45 test_accuracy 123 model 0 nb_correct 0 / 2500 (0.00%) 20241027-07:03:45 quiz_set nb_w_quizzes 150 nb_c_quizzes 0 20241027-07:04:01 wrote reasoning.pth 20241027-07:04:01 quiz_set nb_w_quizzes 256 nb_c_quizzes 0 20241027-07:04:05 quiz_set nb_w_quizzes 50000 nb_c_quizzes 0 20241027-07:12:20 train_loss 124 model 0 712.9264 20241027-07:12:20 quiz_set nb_w_quizzes 2500 nb_c_quizzes 0 20241027-07:12:28 test_loss 124 model 0 357.2 20241027-07:12:28 quiz_set nb_w_quizzes 2500 nb_c_quizzes 0 20241027-07:12:36 test_accuracy 124 model 0 nb_correct 0 / 2500 (0.00%) 20241027-07:12:36 quiz_set nb_w_quizzes 150 nb_c_quizzes 0 20241027-07:12:50 wrote reasoning.pth 20241027-07:12:50 quiz_set nb_w_quizzes 256 nb_c_quizzes 0 20241027-07:12:53 quiz_set nb_w_quizzes 50000 nb_c_quizzes 0 20241027-07:20:32 train_loss 125 model 0 760.7676 20241027-07:20:32 quiz_set nb_w_quizzes 2500 nb_c_quizzes 0 20241027-07:20:39 test_loss 125 model 0 542.672 20241027-07:20:39 quiz_set nb_w_quizzes 2500 nb_c_quizzes 0 20241027-07:20:47 test_accuracy 125 model 0 nb_correct 0 / 2500 (0.00%) 20241027-07:20:47 quiz_set nb_w_quizzes 150 nb_c_quizzes 0 20241027-07:21:03 wrote reasoning.pth 20241027-07:21:03 quiz_set nb_w_quizzes 256 nb_c_quizzes 0 20241027-07:21:07 quiz_set nb_w_quizzes 50000 nb_c_quizzes 0 20241027-07:28:47 train_loss 126 model 0 767.0148 20241027-07:28:48 quiz_set nb_w_quizzes 2500 nb_c_quizzes 0 20241027-07:28:55 test_loss 126 model 0 186.83 20241027-07:28:55 quiz_set nb_w_quizzes 2500 nb_c_quizzes 0 20241027-07:29:03 test_accuracy 126 model 0 nb_correct 0 / 2500 (0.00%) 20241027-07:29:03 quiz_set nb_w_quizzes 150 nb_c_quizzes 0 20241027-07:29:20 wrote reasoning.pth 20241027-07:29:20 quiz_set nb_w_quizzes 256 nb_c_quizzes 0 20241027-07:29:23 quiz_set nb_w_quizzes 50000 nb_c_quizzes 0 20241027-07:37:37 train_loss 127 model 0 800.5392 20241027-07:37:37 quiz_set nb_w_quizzes 2500 nb_c_quizzes 0 20241027-07:37:45 test_loss 127 model 0 973.232 20241027-07:37:45 quiz_set nb_w_quizzes 2500 nb_c_quizzes 0 20241027-07:37:52 test_accuracy 127 model 0 nb_correct 0 / 2500 (0.00%) 20241027-07:37:52 quiz_set nb_w_quizzes 150 nb_c_quizzes 0 20241027-07:38:06 wrote reasoning.pth 20241027-07:38:06 quiz_set nb_w_quizzes 256 nb_c_quizzes 0 20241027-07:38:10 quiz_set nb_w_quizzes 50000 nb_c_quizzes 0 20241027-07:46:27 train_loss 128 model 0 814.9224 20241027-07:46:27 quiz_set nb_w_quizzes 2500 nb_c_quizzes 0 20241027-07:46:34 test_loss 128 model 0 1268.832 20241027-07:46:34 quiz_set nb_w_quizzes 2500 nb_c_quizzes 0 20241027-07:46:42 test_accuracy 128 model 0 nb_correct 0 / 2500 (0.00%) 20241027-07:46:42 quiz_set nb_w_quizzes 150 nb_c_quizzes 0 20241027-07:46:58 wrote reasoning.pth 20241027-07:46:58 quiz_set nb_w_quizzes 256 nb_c_quizzes 0 20241027-07:47:02 quiz_set nb_w_quizzes 50000 nb_c_quizzes 0 20241027-07:54:50 train_loss 129 model 0 835.216 20241027-07:54:50 quiz_set nb_w_quizzes 2500 nb_c_quizzes 0 20241027-07:54:58 test_loss 129 model 0 1118.368 20241027-07:54:58 quiz_set nb_w_quizzes 2500 nb_c_quizzes 0 20241027-07:55:06 test_accuracy 129 model 0 nb_correct 0 / 2500 (0.00%) 20241027-07:55:06 quiz_set nb_w_quizzes 150 nb_c_quizzes 0 20241027-07:55:22 wrote reasoning.pth 20241027-07:55:22 quiz_set nb_w_quizzes 256 nb_c_quizzes 0 20241027-07:55:26 quiz_set nb_w_quizzes 50000 nb_c_quizzes 0 20241027-08:03:39 train_loss 130 model 0 891.8452 20241027-08:03:39 quiz_set nb_w_quizzes 2500 nb_c_quizzes 0 20241027-08:03:46 test_loss 130 model 0 890.096 20241027-08:03:46 quiz_set nb_w_quizzes 2500 nb_c_quizzes 0 20241027-08:03:54 test_accuracy 130 model 0 nb_correct 0 / 2500 (0.00%) 20241027-08:03:54 quiz_set nb_w_quizzes 150 nb_c_quizzes 0 20241027-08:04:10 wrote reasoning.pth 20241027-08:04:10 quiz_set nb_w_quizzes 256 nb_c_quizzes 0 20241027-08:04:14 quiz_set nb_w_quizzes 50000 nb_c_quizzes 0 20241027-08:12:27 train_loss 131 model 0 912.952 20241027-08:12:27 quiz_set nb_w_quizzes 2500 nb_c_quizzes 0 20241027-08:12:35 test_loss 131 model 0 973.592 20241027-08:12:35 quiz_set nb_w_quizzes 2500 nb_c_quizzes 0 20241027-08:12:43 test_accuracy 131 model 0 nb_correct 0 / 2500 (0.00%) 20241027-08:12:43 quiz_set nb_w_quizzes 150 nb_c_quizzes 0 20241027-08:12:59 wrote reasoning.pth 20241027-08:12:59 quiz_set nb_w_quizzes 256 nb_c_quizzes 0 20241027-08:13:02 quiz_set nb_w_quizzes 50000 nb_c_quizzes 0 20241027-08:20:43 train_loss 132 model 0 942.5076 20241027-08:20:43 quiz_set nb_w_quizzes 2500 nb_c_quizzes 0 20241027-08:20:50 test_loss 132 model 0 1668.816 20241027-08:20:50 quiz_set nb_w_quizzes 2500 nb_c_quizzes 0 20241027-08:20:59 test_accuracy 132 model 0 nb_correct 0 / 2500 (0.00%) 20241027-08:20:59 quiz_set nb_w_quizzes 150 nb_c_quizzes 0 20241027-08:21:13 wrote reasoning.pth 20241027-08:21:13 quiz_set nb_w_quizzes 256 nb_c_quizzes 0 20241027-08:21:16 quiz_set nb_w_quizzes 50000 nb_c_quizzes 0 20241027-08:29:22 train_loss 133 model 0 958.4164 20241027-08:29:22 quiz_set nb_w_quizzes 2500 nb_c_quizzes 0 20241027-08:29:30 test_loss 133 model 0 1176.112 20241027-08:29:30 quiz_set nb_w_quizzes 2500 nb_c_quizzes 0 20241027-08:29:38 test_accuracy 133 model 0 nb_correct 0 / 2500 (0.00%) 20241027-08:29:38 quiz_set nb_w_quizzes 150 nb_c_quizzes 0 20241027-08:29:54 wrote reasoning.pth 20241027-08:29:54 quiz_set nb_w_quizzes 256 nb_c_quizzes 0 20241027-08:29:57 quiz_set nb_w_quizzes 50000 nb_c_quizzes 0 20241027-08:37:57 train_loss 134 model 0 968.6432 20241027-08:37:57 quiz_set nb_w_quizzes 2500 nb_c_quizzes 0 20241027-08:38:04 test_loss 134 model 0 2127.2 20241027-08:38:04 quiz_set nb_w_quizzes 2500 nb_c_quizzes 0 20241027-08:38:12 test_accuracy 134 model 0 nb_correct 0 / 2500 (0.00%) 20241027-08:38:12 quiz_set nb_w_quizzes 150 nb_c_quizzes 0 20241027-08:38:26 wrote reasoning.pth 20241027-08:38:26 quiz_set nb_w_quizzes 256 nb_c_quizzes 0 20241027-08:38:29 quiz_set nb_w_quizzes 50000 nb_c_quizzes 0 20241027-08:46:30 train_loss 135 model 0 1006.8536 20241027-08:46:30 quiz_set nb_w_quizzes 2500 nb_c_quizzes 0 20241027-08:46:38 test_loss 135 model 0 1495.328 20241027-08:46:38 quiz_set nb_w_quizzes 2500 nb_c_quizzes 0 20241027-08:46:46 test_accuracy 135 model 0 nb_correct 0 / 2500 (0.00%) 20241027-08:46:46 quiz_set nb_w_quizzes 150 nb_c_quizzes 0 20241027-08:47:02 wrote reasoning.pth 20241027-08:47:02 quiz_set nb_w_quizzes 256 nb_c_quizzes 0 20241027-08:47:05 quiz_set nb_w_quizzes 50000 nb_c_quizzes 0 20241027-08:54:52 train_loss 136 model 0 1030.8668 20241027-08:54:52 quiz_set nb_w_quizzes 2500 nb_c_quizzes 0 20241027-08:54:59 test_loss 136 model 0 1966.4 20241027-08:54:59 quiz_set nb_w_quizzes 2500 nb_c_quizzes 0 20241027-08:55:07 test_accuracy 136 model 0 nb_correct 0 / 2500 (0.00%) 20241027-08:55:07 quiz_set nb_w_quizzes 150 nb_c_quizzes 0 20241027-08:55:23 wrote reasoning.pth 20241027-08:55:23 quiz_set nb_w_quizzes 256 nb_c_quizzes 0 20241027-08:55:27 quiz_set nb_w_quizzes 50000 nb_c_quizzes 0 20241027-09:03:18 train_loss 137 model 0 1054.6616 20241027-09:03:18 quiz_set nb_w_quizzes 2500 nb_c_quizzes 0 20241027-09:03:26 test_loss 137 model 0 1642.208 20241027-09:03:26 quiz_set nb_w_quizzes 2500 nb_c_quizzes 0 20241027-09:03:34 test_accuracy 137 model 0 nb_correct 0 / 2500 (0.00%) 20241027-09:03:34 quiz_set nb_w_quizzes 150 nb_c_quizzes 0 20241027-09:03:50 wrote reasoning.pth 20241027-09:03:50 quiz_set nb_w_quizzes 256 nb_c_quizzes 0 20241027-09:03:54 quiz_set nb_w_quizzes 50000 nb_c_quizzes 0 20241027-09:11:58 train_loss 138 model 0 1075.4204 20241027-09:11:58 quiz_set nb_w_quizzes 2500 nb_c_quizzes 0 20241027-09:12:06 test_loss 138 model 0 2262.688 20241027-09:12:06 quiz_set nb_w_quizzes 2500 nb_c_quizzes 0 20241027-09:12:13 test_accuracy 138 model 0 nb_correct 0 / 2500 (0.00%) 20241027-09:12:13 quiz_set nb_w_quizzes 150 nb_c_quizzes 0 20241027-09:12:30 wrote reasoning.pth 20241027-09:12:30 quiz_set nb_w_quizzes 256 nb_c_quizzes 0 20241027-09:12:33 quiz_set nb_w_quizzes 50000 nb_c_quizzes 0 20241027-09:20:50 train_loss 139 model 0 1104.3008 20241027-09:20:50 quiz_set nb_w_quizzes 2500 nb_c_quizzes 0 20241027-09:20:58 test_loss 139 model 0 1654.736 20241027-09:20:58 quiz_set nb_w_quizzes 2500 nb_c_quizzes 0 20241027-09:21:06 test_accuracy 139 model 0 nb_correct 0 / 2500 (0.00%) 20241027-09:21:06 quiz_set nb_w_quizzes 150 nb_c_quizzes 0 20241027-09:21:22 wrote reasoning.pth 20241027-09:21:22 quiz_set nb_w_quizzes 256 nb_c_quizzes 0 20241027-09:21:25 quiz_set nb_w_quizzes 50000 nb_c_quizzes 0 20241027-09:29:39 train_loss 140 model 0 1120.7108 20241027-09:29:39 quiz_set nb_w_quizzes 2500 nb_c_quizzes 0 20241027-09:29:47 test_loss 140 model 0 495.208 20241027-09:29:47 quiz_set nb_w_quizzes 2500 nb_c_quizzes 0 20241027-09:29:55 test_accuracy 140 model 0 nb_correct 0 / 2500 (0.00%) 20241027-09:29:55 quiz_set nb_w_quizzes 150 nb_c_quizzes 0 20241027-09:30:12 wrote reasoning.pth 20241027-09:30:12 quiz_set nb_w_quizzes 256 nb_c_quizzes 0 20241027-09:30:15 quiz_set nb_w_quizzes 50000 nb_c_quizzes 0 20241027-09:38:34 train_loss 141 model 0 1150.856 20241027-09:38:34 quiz_set nb_w_quizzes 2500 nb_c_quizzes 0 20241027-09:38:42 test_loss 141 model 0 1863.6 20241027-09:38:42 quiz_set nb_w_quizzes 2500 nb_c_quizzes 0 20241027-09:38:50 test_accuracy 141 model 0 nb_correct 0 / 2500 (0.00%) 20241027-09:38:50 quiz_set nb_w_quizzes 150 nb_c_quizzes 0 20241027-09:39:06 wrote reasoning.pth 20241027-09:39:06 quiz_set nb_w_quizzes 256 nb_c_quizzes 0 20241027-09:39:09 quiz_set nb_w_quizzes 50000 nb_c_quizzes 0 20241027-09:47:14 train_loss 142 model 0 1164.2584 20241027-09:47:14 quiz_set nb_w_quizzes 2500 nb_c_quizzes 0 20241027-09:47:22 test_loss 142 model 0 1258.44 20241027-09:47:22 quiz_set nb_w_quizzes 2500 nb_c_quizzes 0 20241027-09:47:30 test_accuracy 142 model 0 nb_correct 0 / 2500 (0.00%) 20241027-09:47:30 quiz_set nb_w_quizzes 150 nb_c_quizzes 0 20241027-09:47:46 wrote reasoning.pth 20241027-09:47:46 quiz_set nb_w_quizzes 256 nb_c_quizzes 0 20241027-09:47:49 quiz_set nb_w_quizzes 50000 nb_c_quizzes 0 20241027-09:55:53 train_loss 143 model 0 1207.9772 20241027-09:55:53 quiz_set nb_w_quizzes 2500 nb_c_quizzes 0 20241027-09:56:01 test_loss 143 model 0 1999.744 20241027-09:56:01 quiz_set nb_w_quizzes 2500 nb_c_quizzes 0 20241027-09:56:09 test_accuracy 143 model 0 nb_correct 0 / 2500 (0.00%) 20241027-09:56:09 quiz_set nb_w_quizzes 150 nb_c_quizzes 0 20241027-09:56:25 wrote reasoning.pth 20241027-09:56:25 quiz_set nb_w_quizzes 256 nb_c_quizzes 0 20241027-09:56:28 quiz_set nb_w_quizzes 50000 nb_c_quizzes 0 20241027-10:04:42 train_loss 144 model 0 1248.1 20241027-10:04:42 quiz_set nb_w_quizzes 2500 nb_c_quizzes 0 20241027-10:04:50 test_loss 144 model 0 2394.0 20241027-10:04:50 quiz_set nb_w_quizzes 2500 nb_c_quizzes 0 20241027-10:04:57 test_accuracy 144 model 0 nb_correct 0 / 2500 (0.00%) 20241027-10:04:57 quiz_set nb_w_quizzes 150 nb_c_quizzes 0 20241027-10:05:11 wrote reasoning.pth 20241027-10:05:11 quiz_set nb_w_quizzes 256 nb_c_quizzes 0 20241027-10:05:14 quiz_set nb_w_quizzes 50000 nb_c_quizzes 0 20241027-10:13:22 train_loss 145 model 0 1268.5288 20241027-10:13:22 quiz_set nb_w_quizzes 2500 nb_c_quizzes 0 20241027-10:13:29 test_loss 145 model 0 1236.144 20241027-10:13:29 quiz_set nb_w_quizzes 2500 nb_c_quizzes 0 20241027-10:13:37 test_accuracy 145 model 0 nb_correct 0 / 2500 (0.00%) 20241027-10:13:37 quiz_set nb_w_quizzes 150 nb_c_quizzes 0 20241027-10:13:53 wrote reasoning.pth 20241027-10:13:53 quiz_set nb_w_quizzes 256 nb_c_quizzes 0 20241027-10:13:57 quiz_set nb_w_quizzes 50000 nb_c_quizzes 0 20241027-10:21:59 train_loss 146 model 0 1273.7624 20241027-10:21:59 quiz_set nb_w_quizzes 2500 nb_c_quizzes 0 20241027-10:22:06 test_loss 146 model 0 1425.696 20241027-10:22:06 quiz_set nb_w_quizzes 2500 nb_c_quizzes 0 20241027-10:22:14 test_accuracy 146 model 0 nb_correct 0 / 2500 (0.00%) 20241027-10:22:14 quiz_set nb_w_quizzes 150 nb_c_quizzes 0 20241027-10:22:31 wrote reasoning.pth 20241027-10:22:31 quiz_set nb_w_quizzes 256 nb_c_quizzes 0 20241027-10:22:34 quiz_set nb_w_quizzes 50000 nb_c_quizzes 0 20241027-10:30:45 train_loss 147 model 0 1290.6976 20241027-10:30:45 quiz_set nb_w_quizzes 2500 nb_c_quizzes 0 20241027-10:30:53 test_loss 147 model 0 2343.456 20241027-10:30:53 quiz_set nb_w_quizzes 2500 nb_c_quizzes 0 20241027-10:31:01 test_accuracy 147 model 0 nb_correct 0 / 2500 (0.00%) 20241027-10:31:01 quiz_set nb_w_quizzes 150 nb_c_quizzes 0 20241027-10:31:17 wrote reasoning.pth 20241027-10:31:17 quiz_set nb_w_quizzes 256 nb_c_quizzes 0 20241027-10:31:20 quiz_set nb_w_quizzes 50000 nb_c_quizzes 0 20241027-10:39:36 train_loss 148 model 0 1302.3992 20241027-10:39:36 quiz_set nb_w_quizzes 2500 nb_c_quizzes 0 20241027-10:39:44 test_loss 148 model 0 2396.416 20241027-10:39:44 quiz_set nb_w_quizzes 2500 nb_c_quizzes 0 20241027-10:39:52 test_accuracy 148 model 0 nb_correct 0 / 2500 (0.00%) 20241027-10:39:52 quiz_set nb_w_quizzes 150 nb_c_quizzes 0 20241027-10:40:08 wrote reasoning.pth 20241027-10:40:08 quiz_set nb_w_quizzes 256 nb_c_quizzes 0 20241027-10:40:11 quiz_set nb_w_quizzes 50000 nb_c_quizzes 0 20241027-10:48:17 train_loss 149 model 0 1316.8728 20241027-10:48:17 quiz_set nb_w_quizzes 2500 nb_c_quizzes 0 20241027-10:48:25 test_loss 149 model 0 3997.28 20241027-10:48:25 quiz_set nb_w_quizzes 2500 nb_c_quizzes 0 20241027-10:48:33 test_accuracy 149 model 0 nb_correct 0 / 2500 (0.00%) 20241027-10:48:33 quiz_set nb_w_quizzes 150 nb_c_quizzes 0 20241027-10:48:49 wrote reasoning.pth 20241027-10:48:49 quiz_set nb_w_quizzes 256 nb_c_quizzes 0 20241027-10:48:53 quiz_set nb_w_quizzes 50000 nb_c_quizzes 0 20241027-10:56:50 train_loss 150 model 0 1376.9684 20241027-10:56:50 quiz_set nb_w_quizzes 2500 nb_c_quizzes 0 20241027-10:56:58 test_loss 150 model 0 1762.752 20241027-10:56:58 quiz_set nb_w_quizzes 2500 nb_c_quizzes 0 20241027-10:57:06 test_accuracy 150 model 0 nb_correct 0 / 2500 (0.00%) 20241027-10:57:06 quiz_set nb_w_quizzes 150 nb_c_quizzes 0 20241027-10:57:22 wrote reasoning.pth 20241027-10:57:22 quiz_set nb_w_quizzes 256 nb_c_quizzes 0 20241027-10:57:25 quiz_set nb_w_quizzes 50000 nb_c_quizzes 0 20241027-11:05:42 train_loss 151 model 0 1435.8816 20241027-11:05:42 quiz_set nb_w_quizzes 2500 nb_c_quizzes 0 20241027-11:05:49 test_loss 151 model 0 3199.456 20241027-11:05:49 quiz_set nb_w_quizzes 2500 nb_c_quizzes 0 20241027-11:05:57 test_accuracy 151 model 0 nb_correct 0 / 2500 (0.00%) 20241027-11:05:57 quiz_set nb_w_quizzes 150 nb_c_quizzes 0 20241027-11:06:13 wrote reasoning.pth 20241027-11:06:13 quiz_set nb_w_quizzes 256 nb_c_quizzes 0 20241027-11:06:17 quiz_set nb_w_quizzes 50000 nb_c_quizzes 0 20241027-11:14:35 train_loss 152 model 0 1474.7148 20241027-11:14:35 quiz_set nb_w_quizzes 2500 nb_c_quizzes 0 20241027-11:14:42 test_loss 152 model 0 3897.152 20241027-11:14:43 quiz_set nb_w_quizzes 2500 nb_c_quizzes 0 20241027-11:14:50 test_accuracy 152 model 0 nb_correct 0 / 2500 (0.00%) 20241027-11:14:50 quiz_set nb_w_quizzes 150 nb_c_quizzes 0 20241027-11:15:07 wrote reasoning.pth 20241027-11:15:07 quiz_set nb_w_quizzes 256 nb_c_quizzes 0 20241027-11:15:10 quiz_set nb_w_quizzes 50000 nb_c_quizzes 0 20241027-11:23:17 train_loss 153 model 0 1479.3144 20241027-11:23:18 quiz_set nb_w_quizzes 2500 nb_c_quizzes 0 20241027-11:23:25 test_loss 153 model 0 2079.04 20241027-11:23:25 quiz_set nb_w_quizzes 2500 nb_c_quizzes 0 20241027-11:23:33 test_accuracy 153 model 0 nb_correct 0 / 2500 (0.00%) 20241027-11:23:33 quiz_set nb_w_quizzes 150 nb_c_quizzes 0 20241027-11:23:50 wrote reasoning.pth 20241027-11:23:50 quiz_set nb_w_quizzes 256 nb_c_quizzes 0 20241027-11:23:53 quiz_set nb_w_quizzes 50000 nb_c_quizzes 0 20241027-11:31:43 train_loss 154 model 0 1505.082 20241027-11:31:43 quiz_set nb_w_quizzes 2500 nb_c_quizzes 0 20241027-11:31:51 test_loss 154 model 0 2492.608 20241027-11:31:51 quiz_set nb_w_quizzes 2500 nb_c_quizzes 0 20241027-11:31:58 test_accuracy 154 model 0 nb_correct 0 / 2500 (0.00%) 20241027-11:31:58 quiz_set nb_w_quizzes 150 nb_c_quizzes 0 20241027-11:32:15 wrote reasoning.pth 20241027-11:32:15 quiz_set nb_w_quizzes 256 nb_c_quizzes 0 20241027-11:32:18 quiz_set nb_w_quizzes 50000 nb_c_quizzes 0 20241027-11:40:02 train_loss 155 model 0 1548.2824 20241027-11:40:02 quiz_set nb_w_quizzes 2500 nb_c_quizzes 0 20241027-11:40:10 test_loss 155 model 0 2114.112 20241027-11:40:10 quiz_set nb_w_quizzes 2500 nb_c_quizzes 0 20241027-11:40:18 test_accuracy 155 model 0 nb_correct 0 / 2500 (0.00%) 20241027-11:40:18 quiz_set nb_w_quizzes 150 nb_c_quizzes 0 20241027-11:40:34 wrote reasoning.pth 20241027-11:40:34 quiz_set nb_w_quizzes 256 nb_c_quizzes 0 20241027-11:40:37 quiz_set nb_w_quizzes 50000 nb_c_quizzes 0 20241027-11:48:57 train_loss 156 model 0 1518.876 20241027-11:48:57 quiz_set nb_w_quizzes 2500 nb_c_quizzes 0 20241027-11:49:05 test_loss 156 model 0 1520.176 20241027-11:49:05 quiz_set nb_w_quizzes 2500 nb_c_quizzes 0 20241027-11:49:13 test_accuracy 156 model 0 nb_correct 0 / 2500 (0.00%) 20241027-11:49:13 quiz_set nb_w_quizzes 150 nb_c_quizzes 0 20241027-11:49:29 wrote reasoning.pth 20241027-11:49:29 quiz_set nb_w_quizzes 256 nb_c_quizzes 0 20241027-11:49:33 quiz_set nb_w_quizzes 50000 nb_c_quizzes 0 20241027-11:57:19 train_loss 157 model 0 1511.3276 20241027-11:57:19 quiz_set nb_w_quizzes 2500 nb_c_quizzes 0 20241027-11:57:27 test_loss 157 model 0 2240.224 20241027-11:57:27 quiz_set nb_w_quizzes 2500 nb_c_quizzes 0 20241027-11:57:35 test_accuracy 157 model 0 nb_correct 0 / 2500 (0.00%) 20241027-11:57:35 quiz_set nb_w_quizzes 150 nb_c_quizzes 0 20241027-11:57:51 wrote reasoning.pth 20241027-11:57:51 quiz_set nb_w_quizzes 256 nb_c_quizzes 0 20241027-11:57:54 quiz_set nb_w_quizzes 50000 nb_c_quizzes 0 20241027-12:06:11 train_loss 158 model 0 1567.2324 20241027-12:06:11 quiz_set nb_w_quizzes 2500 nb_c_quizzes 0 20241027-12:06:19 test_loss 158 model 0 3678.976 20241027-12:06:19 quiz_set nb_w_quizzes 2500 nb_c_quizzes 0 20241027-12:06:27 test_accuracy 158 model 0 nb_correct 0 / 2500 (0.00%) 20241027-12:06:27 quiz_set nb_w_quizzes 150 nb_c_quizzes 0 20241027-12:06:43 wrote reasoning.pth 20241027-12:06:43 quiz_set nb_w_quizzes 256 nb_c_quizzes 0 20241027-12:06:46 quiz_set nb_w_quizzes 50000 nb_c_quizzes 0 20241027-12:14:59 train_loss 159 model 0 1605.5896 20241027-12:14:59 quiz_set nb_w_quizzes 2500 nb_c_quizzes 0 20241027-12:15:07 test_loss 159 model 0 2755.68 20241027-12:15:07 quiz_set nb_w_quizzes 2500 nb_c_quizzes 0 20241027-12:15:15 test_accuracy 159 model 0 nb_correct 0 / 2500 (0.00%) 20241027-12:15:15 quiz_set nb_w_quizzes 150 nb_c_quizzes 0 20241027-12:15:31 wrote reasoning.pth 20241027-12:15:31 quiz_set nb_w_quizzes 256 nb_c_quizzes 0 20241027-12:15:35 quiz_set nb_w_quizzes 50000 nb_c_quizzes 0 20241027-12:23:31 train_loss 160 model 0 1627.5744 20241027-12:23:31 quiz_set nb_w_quizzes 2500 nb_c_quizzes 0 20241027-12:23:39 test_loss 160 model 0 3838.368 20241027-12:23:39 quiz_set nb_w_quizzes 2500 nb_c_quizzes 0 20241027-12:23:47 test_accuracy 160 model 0 nb_correct 0 / 2500 (0.00%) 20241027-12:23:47 quiz_set nb_w_quizzes 150 nb_c_quizzes 0 20241027-12:24:03 wrote reasoning.pth 20241027-12:24:03 quiz_set nb_w_quizzes 256 nb_c_quizzes 0 20241027-12:24:07 quiz_set nb_w_quizzes 50000 nb_c_quizzes 0 20241027-12:31:47 train_loss 161 model 0 1671.2904 20241027-12:31:47 quiz_set nb_w_quizzes 2500 nb_c_quizzes 0 20241027-12:31:55 test_loss 161 model 0 1841.456 20241027-12:31:55 quiz_set nb_w_quizzes 2500 nb_c_quizzes 0 20241027-12:32:03 test_accuracy 161 model 0 nb_correct 0 / 2500 (0.00%) 20241027-12:32:03 quiz_set nb_w_quizzes 150 nb_c_quizzes 0 20241027-12:32:19 wrote reasoning.pth 20241027-12:32:19 quiz_set nb_w_quizzes 256 nb_c_quizzes 0 20241027-12:32:23 quiz_set nb_w_quizzes 50000 nb_c_quizzes 0