| { | |
| "best_metric": 0.893719494342804, | |
| "best_model_checkpoint": "autotrain-jr45n-23iwd/checkpoint-21", | |
| "epoch": 3.0, | |
| "eval_steps": 500, | |
| "global_step": 21, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.14285714285714285, | |
| "grad_norm": 13.014251708984375, | |
| "learning_rate": 1.6666666666666667e-05, | |
| "loss": 1.574, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.2857142857142857, | |
| "grad_norm": 6.878973007202148, | |
| "learning_rate": 3.3333333333333335e-05, | |
| "loss": 1.436, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.42857142857142855, | |
| "grad_norm": 8.282319068908691, | |
| "learning_rate": 5e-05, | |
| "loss": 1.5673, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.5714285714285714, | |
| "grad_norm": 9.62940502166748, | |
| "learning_rate": 4.722222222222222e-05, | |
| "loss": 1.2444, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.7142857142857143, | |
| "grad_norm": 11.141054153442383, | |
| "learning_rate": 4.4444444444444447e-05, | |
| "loss": 1.665, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.8571428571428571, | |
| "grad_norm": 10.266294479370117, | |
| "learning_rate": 4.166666666666667e-05, | |
| "loss": 1.3428, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "grad_norm": 18.852968215942383, | |
| "learning_rate": 3.888888888888889e-05, | |
| "loss": 1.4157, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_accuracy": 0.7857142857142857, | |
| "eval_f1_macro": 0.6375, | |
| "eval_f1_micro": 0.7857142857142857, | |
| "eval_f1_weighted": 0.7285714285714285, | |
| "eval_loss": 1.2462433576583862, | |
| "eval_precision_macro": 0.6041666666666666, | |
| "eval_precision_micro": 0.7857142857142857, | |
| "eval_precision_weighted": 0.6904761904761905, | |
| "eval_recall_macro": 0.6875, | |
| "eval_recall_micro": 0.7857142857142857, | |
| "eval_recall_weighted": 0.7857142857142857, | |
| "eval_runtime": 2.3828, | |
| "eval_samples_per_second": 5.875, | |
| "eval_steps_per_second": 0.42, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 1.1428571428571428, | |
| "grad_norm": 9.181815147399902, | |
| "learning_rate": 3.611111111111111e-05, | |
| "loss": 1.3051, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 1.2857142857142856, | |
| "grad_norm": 7.824043273925781, | |
| "learning_rate": 3.3333333333333335e-05, | |
| "loss": 1.2258, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 1.4285714285714286, | |
| "grad_norm": 7.767913341522217, | |
| "learning_rate": 3.055555555555556e-05, | |
| "loss": 1.3915, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 1.5714285714285714, | |
| "grad_norm": 10.508928298950195, | |
| "learning_rate": 2.777777777777778e-05, | |
| "loss": 1.1089, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 1.7142857142857144, | |
| "grad_norm": 15.723339080810547, | |
| "learning_rate": 2.5e-05, | |
| "loss": 1.1304, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 1.8571428571428572, | |
| "grad_norm": 9.557744979858398, | |
| "learning_rate": 2.2222222222222223e-05, | |
| "loss": 1.1083, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "grad_norm": 20.124605178833008, | |
| "learning_rate": 1.9444444444444445e-05, | |
| "loss": 1.2587, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_accuracy": 0.6428571428571429, | |
| "eval_f1_macro": 0.5038461538461538, | |
| "eval_f1_micro": 0.6428571428571429, | |
| "eval_f1_weighted": 0.5758241758241758, | |
| "eval_loss": 1.00484299659729, | |
| "eval_precision_macro": 0.6111111111111112, | |
| "eval_precision_micro": 0.6428571428571429, | |
| "eval_precision_weighted": 0.6984126984126985, | |
| "eval_recall_macro": 0.5625, | |
| "eval_recall_micro": 0.6428571428571429, | |
| "eval_recall_weighted": 0.6428571428571429, | |
| "eval_runtime": 2.4717, | |
| "eval_samples_per_second": 5.664, | |
| "eval_steps_per_second": 0.405, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 2.142857142857143, | |
| "grad_norm": 12.81100845336914, | |
| "learning_rate": 1.6666666666666667e-05, | |
| "loss": 1.2278, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 2.2857142857142856, | |
| "grad_norm": 9.036030769348145, | |
| "learning_rate": 1.388888888888889e-05, | |
| "loss": 0.9014, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 2.4285714285714284, | |
| "grad_norm": 11.079411506652832, | |
| "learning_rate": 1.1111111111111112e-05, | |
| "loss": 0.8781, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 2.571428571428571, | |
| "grad_norm": 8.225976943969727, | |
| "learning_rate": 8.333333333333334e-06, | |
| "loss": 0.8964, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 2.7142857142857144, | |
| "grad_norm": 11.431103706359863, | |
| "learning_rate": 5.555555555555556e-06, | |
| "loss": 0.9341, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 2.857142857142857, | |
| "grad_norm": 6.8565449714660645, | |
| "learning_rate": 2.777777777777778e-06, | |
| "loss": 0.9554, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "grad_norm": 10.979363441467285, | |
| "learning_rate": 0.0, | |
| "loss": 1.0157, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_accuracy": 0.7857142857142857, | |
| "eval_f1_macro": 0.6365079365079365, | |
| "eval_f1_micro": 0.7857142857142857, | |
| "eval_f1_weighted": 0.727437641723356, | |
| "eval_loss": 0.893719494342804, | |
| "eval_precision_macro": 0.6166666666666667, | |
| "eval_precision_micro": 0.7857142857142857, | |
| "eval_precision_weighted": 0.7047619047619048, | |
| "eval_recall_macro": 0.6875, | |
| "eval_recall_micro": 0.7857142857142857, | |
| "eval_recall_weighted": 0.7857142857142857, | |
| "eval_runtime": 2.4283, | |
| "eval_samples_per_second": 5.765, | |
| "eval_steps_per_second": 0.412, | |
| "step": 21 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 21, | |
| "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": 11050862764032.0, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |