| { | |
| "best_metric": 0.2754124701023102, | |
| "best_model_checkpoint": "autotrain-uypr6-jedzx/checkpoint-1146", | |
| "epoch": 3.0, | |
| "eval_steps": 500, | |
| "global_step": 1146, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.06544502617801047, | |
| "grad_norm": 59.99160385131836, | |
| "learning_rate": 8.695652173913044e-06, | |
| "loss": 1.7298, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.13089005235602094, | |
| "grad_norm": 47.46957015991211, | |
| "learning_rate": 1.956521739130435e-05, | |
| "loss": 1.3956, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.19633507853403143, | |
| "grad_norm": 46.052276611328125, | |
| "learning_rate": 3.0434782608695656e-05, | |
| "loss": 1.0186, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.2617801047120419, | |
| "grad_norm": 34.63148880004883, | |
| "learning_rate": 4.130434782608696e-05, | |
| "loss": 0.7998, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.32722513089005234, | |
| "grad_norm": 29.743520736694336, | |
| "learning_rate": 4.9757516973811834e-05, | |
| "loss": 0.5667, | |
| "step": 125 | |
| }, | |
| { | |
| "epoch": 0.39267015706806285, | |
| "grad_norm": 67.28214263916016, | |
| "learning_rate": 4.8545101842871e-05, | |
| "loss": 0.4248, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.4581151832460733, | |
| "grad_norm": 5.239678382873535, | |
| "learning_rate": 4.7332686711930166e-05, | |
| "loss": 0.5009, | |
| "step": 175 | |
| }, | |
| { | |
| "epoch": 0.5235602094240838, | |
| "grad_norm": 39.05686950683594, | |
| "learning_rate": 4.6168768186226966e-05, | |
| "loss": 0.3557, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.5890052356020943, | |
| "grad_norm": 35.131900787353516, | |
| "learning_rate": 4.495635305528613e-05, | |
| "loss": 0.4903, | |
| "step": 225 | |
| }, | |
| { | |
| "epoch": 0.6544502617801047, | |
| "grad_norm": 62.38943862915039, | |
| "learning_rate": 4.37439379243453e-05, | |
| "loss": 0.4936, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 0.7198952879581152, | |
| "grad_norm": 83.50504302978516, | |
| "learning_rate": 4.2531522793404463e-05, | |
| "loss": 0.4041, | |
| "step": 275 | |
| }, | |
| { | |
| "epoch": 0.7853403141361257, | |
| "grad_norm": 150.03025817871094, | |
| "learning_rate": 4.131910766246363e-05, | |
| "loss": 0.5141, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.8507853403141361, | |
| "grad_norm": 6.634305953979492, | |
| "learning_rate": 4.0106692531522795e-05, | |
| "loss": 0.3613, | |
| "step": 325 | |
| }, | |
| { | |
| "epoch": 0.9162303664921466, | |
| "grad_norm": 74.62594604492188, | |
| "learning_rate": 3.889427740058196e-05, | |
| "loss": 0.5418, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 0.981675392670157, | |
| "grad_norm": 4.197720527648926, | |
| "learning_rate": 3.7681862269641126e-05, | |
| "loss": 0.3599, | |
| "step": 375 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_accuracy": 0.9015052356020943, | |
| "eval_f1_macro": 0.8726278718931084, | |
| "eval_f1_micro": 0.9015052356020943, | |
| "eval_f1_weighted": 0.9022637594375305, | |
| "eval_loss": 0.29343605041503906, | |
| "eval_precision_macro": 0.8631887848763573, | |
| "eval_precision_micro": 0.9015052356020943, | |
| "eval_precision_weighted": 0.9066730666237613, | |
| "eval_recall_macro": 0.8894872079498141, | |
| "eval_recall_micro": 0.9015052356020943, | |
| "eval_recall_weighted": 0.9015052356020943, | |
| "eval_runtime": 11.5318, | |
| "eval_samples_per_second": 265.006, | |
| "eval_steps_per_second": 16.563, | |
| "step": 382 | |
| }, | |
| { | |
| "epoch": 1.0471204188481675, | |
| "grad_norm": 30.417509078979492, | |
| "learning_rate": 3.651794374393793e-05, | |
| "loss": 0.5667, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 1.112565445026178, | |
| "grad_norm": 5.592912673950195, | |
| "learning_rate": 3.530552861299709e-05, | |
| "loss": 0.4339, | |
| "step": 425 | |
| }, | |
| { | |
| "epoch": 1.1780104712041886, | |
| "grad_norm": 149.45635986328125, | |
| "learning_rate": 3.409311348205626e-05, | |
| "loss": 0.4277, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 1.243455497382199, | |
| "grad_norm": 43.21306228637695, | |
| "learning_rate": 3.2880698351115424e-05, | |
| "loss": 0.4474, | |
| "step": 475 | |
| }, | |
| { | |
| "epoch": 1.3089005235602094, | |
| "grad_norm": 17.23322296142578, | |
| "learning_rate": 3.166828322017459e-05, | |
| "loss": 0.3334, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 1.3743455497382198, | |
| "grad_norm": 58.24462890625, | |
| "learning_rate": 3.045586808923376e-05, | |
| "loss": 0.2745, | |
| "step": 525 | |
| }, | |
| { | |
| "epoch": 1.4397905759162304, | |
| "grad_norm": 50.83113098144531, | |
| "learning_rate": 2.924345295829292e-05, | |
| "loss": 0.5247, | |
| "step": 550 | |
| }, | |
| { | |
| "epoch": 1.5052356020942408, | |
| "grad_norm": 0.8568320870399475, | |
| "learning_rate": 2.8031037827352087e-05, | |
| "loss": 0.2903, | |
| "step": 575 | |
| }, | |
| { | |
| "epoch": 1.5706806282722514, | |
| "grad_norm": 12.354284286499023, | |
| "learning_rate": 2.6818622696411256e-05, | |
| "loss": 0.3478, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 1.6361256544502618, | |
| "grad_norm": 72.40668487548828, | |
| "learning_rate": 2.560620756547042e-05, | |
| "loss": 0.3851, | |
| "step": 625 | |
| }, | |
| { | |
| "epoch": 1.7015706806282722, | |
| "grad_norm": 51.888160705566406, | |
| "learning_rate": 2.4393792434529584e-05, | |
| "loss": 0.4496, | |
| "step": 650 | |
| }, | |
| { | |
| "epoch": 1.7670157068062826, | |
| "grad_norm": 18.099403381347656, | |
| "learning_rate": 2.318137730358875e-05, | |
| "loss": 0.3424, | |
| "step": 675 | |
| }, | |
| { | |
| "epoch": 1.8324607329842932, | |
| "grad_norm": 37.54734802246094, | |
| "learning_rate": 2.1968962172647915e-05, | |
| "loss": 0.3488, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 1.8979057591623036, | |
| "grad_norm": 75.839111328125, | |
| "learning_rate": 2.075654704170708e-05, | |
| "loss": 0.4106, | |
| "step": 725 | |
| }, | |
| { | |
| "epoch": 1.9633507853403143, | |
| "grad_norm": 101.29055786132812, | |
| "learning_rate": 1.9544131910766247e-05, | |
| "loss": 0.328, | |
| "step": 750 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_accuracy": 0.8893979057591623, | |
| "eval_f1_macro": 0.8219814942957756, | |
| "eval_f1_micro": 0.8893979057591623, | |
| "eval_f1_weighted": 0.8928830409769577, | |
| "eval_loss": 0.3261115849018097, | |
| "eval_precision_macro": 0.8298661821091419, | |
| "eval_precision_micro": 0.8893979057591623, | |
| "eval_precision_weighted": 0.908029594925493, | |
| "eval_recall_macro": 0.8544707626440197, | |
| "eval_recall_micro": 0.8893979057591623, | |
| "eval_recall_weighted": 0.8893979057591623, | |
| "eval_runtime": 11.5139, | |
| "eval_samples_per_second": 265.419, | |
| "eval_steps_per_second": 16.589, | |
| "step": 764 | |
| }, | |
| { | |
| "epoch": 2.0287958115183247, | |
| "grad_norm": 32.63682174682617, | |
| "learning_rate": 1.8331716779825413e-05, | |
| "loss": 0.2345, | |
| "step": 775 | |
| }, | |
| { | |
| "epoch": 2.094240837696335, | |
| "grad_norm": 24.811006546020508, | |
| "learning_rate": 1.7119301648884578e-05, | |
| "loss": 0.2723, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 2.1596858638743455, | |
| "grad_norm": 37.76832962036133, | |
| "learning_rate": 1.5906886517943744e-05, | |
| "loss": 0.4142, | |
| "step": 825 | |
| }, | |
| { | |
| "epoch": 2.225130890052356, | |
| "grad_norm": 25.23703956604004, | |
| "learning_rate": 1.4694471387002911e-05, | |
| "loss": 0.3667, | |
| "step": 850 | |
| }, | |
| { | |
| "epoch": 2.2905759162303667, | |
| "grad_norm": 10.706388473510742, | |
| "learning_rate": 1.3482056256062075e-05, | |
| "loss": 0.291, | |
| "step": 875 | |
| }, | |
| { | |
| "epoch": 2.356020942408377, | |
| "grad_norm": 21.945785522460938, | |
| "learning_rate": 1.2269641125121243e-05, | |
| "loss": 0.3221, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 2.4214659685863875, | |
| "grad_norm": 18.858060836791992, | |
| "learning_rate": 1.1057225994180407e-05, | |
| "loss": 0.354, | |
| "step": 925 | |
| }, | |
| { | |
| "epoch": 2.486910994764398, | |
| "grad_norm": 7.743546485900879, | |
| "learning_rate": 9.844810863239573e-06, | |
| "loss": 0.3951, | |
| "step": 950 | |
| }, | |
| { | |
| "epoch": 2.5523560209424083, | |
| "grad_norm": 54.19382858276367, | |
| "learning_rate": 8.63239573229874e-06, | |
| "loss": 0.4027, | |
| "step": 975 | |
| }, | |
| { | |
| "epoch": 2.6178010471204187, | |
| "grad_norm": 31.006372451782227, | |
| "learning_rate": 7.419980601357905e-06, | |
| "loss": 0.169, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 2.683246073298429, | |
| "grad_norm": 92.00570678710938, | |
| "learning_rate": 6.207565470417071e-06, | |
| "loss": 0.3859, | |
| "step": 1025 | |
| }, | |
| { | |
| "epoch": 2.7486910994764395, | |
| "grad_norm": 33.242313385009766, | |
| "learning_rate": 4.995150339476237e-06, | |
| "loss": 0.244, | |
| "step": 1050 | |
| }, | |
| { | |
| "epoch": 2.8141361256544504, | |
| "grad_norm": 46.14966583251953, | |
| "learning_rate": 3.7827352085354028e-06, | |
| "loss": 0.2685, | |
| "step": 1075 | |
| }, | |
| { | |
| "epoch": 2.8795811518324608, | |
| "grad_norm": 2.030245542526245, | |
| "learning_rate": 2.5703200775945685e-06, | |
| "loss": 0.2737, | |
| "step": 1100 | |
| }, | |
| { | |
| "epoch": 2.945026178010471, | |
| "grad_norm": 64.09654998779297, | |
| "learning_rate": 1.3579049466537344e-06, | |
| "loss": 0.29, | |
| "step": 1125 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_accuracy": 0.9018324607329843, | |
| "eval_f1_macro": 0.8481566344537771, | |
| "eval_f1_micro": 0.9018324607329843, | |
| "eval_f1_weighted": 0.9045988585986702, | |
| "eval_loss": 0.2754124701023102, | |
| "eval_precision_macro": 0.8410035614739351, | |
| "eval_precision_micro": 0.9018324607329843, | |
| "eval_precision_weighted": 0.9137617819536253, | |
| "eval_recall_macro": 0.879811049004688, | |
| "eval_recall_micro": 0.9018324607329843, | |
| "eval_recall_weighted": 0.9018324607329843, | |
| "eval_runtime": 11.582, | |
| "eval_samples_per_second": 263.858, | |
| "eval_steps_per_second": 16.491, | |
| "step": 1146 | |
| } | |
| ], | |
| "logging_steps": 25, | |
| "max_steps": 1146, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 3, | |
| "save_steps": 500, | |
| "stateful_callbacks": { | |
| "EarlyStoppingCallback": { | |
| "args": { | |
| "early_stopping_patience": 5, | |
| "early_stopping_threshold": 0.01 | |
| }, | |
| "attributes": { | |
| "early_stopping_patience_counter": 0 | |
| } | |
| }, | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 2.8064447034753024e+16, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |