| { | |
| "best_metric": 0.9884615384615384, | |
| "best_model_checkpoint": "./results/checkpoint-30", | |
| "epoch": 1.0, | |
| "eval_steps": 5, | |
| "global_step": 38, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0, | |
| "eval_accuracy": 0.43902439024390244, | |
| "eval_f1": 0.7958371594735232, | |
| "eval_loss": 0.8333200216293335, | |
| "eval_precision": 0.43807919123841615, | |
| "eval_recall": 1.0, | |
| "eval_roc_auc": 0.5014947683109118, | |
| "eval_runtime": 52.2016, | |
| "eval_samples_per_second": 22.777, | |
| "eval_steps_per_second": 0.364, | |
| "step": 0 | |
| }, | |
| { | |
| "epoch": 0.13157894736842105, | |
| "grad_norm": 499350.4375, | |
| "learning_rate": 2.5e-05, | |
| "loss": 0.7332, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.13157894736842105, | |
| "eval_accuracy": 0.6181665264928511, | |
| "eval_f1": 0.1537744641192917, | |
| "eval_loss": 0.6050995588302612, | |
| "eval_precision": 1.0, | |
| "eval_recall": 0.12692307692307692, | |
| "eval_roc_auc": 0.5634615384615385, | |
| "eval_runtime": 52.7835, | |
| "eval_samples_per_second": 22.526, | |
| "eval_steps_per_second": 0.36, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.2631578947368421, | |
| "grad_norm": 544000.625, | |
| "learning_rate": 5e-05, | |
| "loss": 0.5445, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.2631578947368421, | |
| "eval_accuracy": 0.8275862068965517, | |
| "eval_f1": 0.9246697607997144, | |
| "eval_loss": 0.3963133990764618, | |
| "eval_precision": 0.7184466019417476, | |
| "eval_recall": 0.9961538461538462, | |
| "eval_roc_auc": 0.8463579395193745, | |
| "eval_runtime": 51.9808, | |
| "eval_samples_per_second": 22.874, | |
| "eval_steps_per_second": 0.366, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.39473684210526316, | |
| "grad_norm": 215321.078125, | |
| "learning_rate": 4.107142857142857e-05, | |
| "loss": 0.328, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.39473684210526316, | |
| "eval_accuracy": 0.928511354079058, | |
| "eval_f1": 0.9660574412532638, | |
| "eval_loss": 0.2025815099477768, | |
| "eval_precision": 0.8618968386023295, | |
| "eval_recall": 0.9961538461538462, | |
| "eval_roc_auc": 0.9360440381740831, | |
| "eval_runtime": 52.187, | |
| "eval_samples_per_second": 22.783, | |
| "eval_steps_per_second": 0.364, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.5263157894736842, | |
| "grad_norm": 447920.53125, | |
| "learning_rate": 3.2142857142857144e-05, | |
| "loss": 0.2165, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.5263157894736842, | |
| "eval_accuracy": 0.9865433137089992, | |
| "eval_f1": 0.9799382716049382, | |
| "eval_loss": 0.061642639338970184, | |
| "eval_precision": 0.9921875, | |
| "eval_recall": 0.9769230769230769, | |
| "eval_roc_auc": 0.9854720018397148, | |
| "eval_runtime": 51.8127, | |
| "eval_samples_per_second": 22.948, | |
| "eval_steps_per_second": 0.367, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.6578947368421053, | |
| "grad_norm": 41190.76953125, | |
| "learning_rate": 2.3214285714285715e-05, | |
| "loss": 0.0754, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.6578947368421053, | |
| "eval_accuracy": 0.9806560134566863, | |
| "eval_f1": 0.9854573287409109, | |
| "eval_loss": 0.050207946449518204, | |
| "eval_precision": 0.9662288930581614, | |
| "eval_recall": 0.9903846153846154, | |
| "eval_roc_auc": 0.9817393928941014, | |
| "eval_runtime": 51.4902, | |
| "eval_samples_per_second": 23.092, | |
| "eval_steps_per_second": 0.369, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.7894736842105263, | |
| "grad_norm": 14033.9931640625, | |
| "learning_rate": 1.4285714285714285e-05, | |
| "loss": 0.022, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.7894736842105263, | |
| "eval_accuracy": 0.9899074852817493, | |
| "eval_f1": 0.9884615384615384, | |
| "eval_loss": 0.03608058765530586, | |
| "eval_precision": 0.9884615384615385, | |
| "eval_recall": 0.9884615384615385, | |
| "eval_roc_auc": 0.9897464642980338, | |
| "eval_runtime": 51.3673, | |
| "eval_samples_per_second": 23.147, | |
| "eval_steps_per_second": 0.37, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.9210526315789473, | |
| "grad_norm": 249264.84375, | |
| "learning_rate": 5.357142857142857e-06, | |
| "loss": 0.1406, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.9210526315789473, | |
| "eval_accuracy": 0.9915895710681245, | |
| "eval_f1": 0.9880585516178735, | |
| "eval_loss": 0.031022196635603905, | |
| "eval_precision": 0.9941860465116279, | |
| "eval_recall": 0.9865384615384616, | |
| "eval_roc_auc": 0.9910270783028631, | |
| "eval_runtime": 50.7403, | |
| "eval_samples_per_second": 23.433, | |
| "eval_steps_per_second": 0.374, | |
| "step": 35 | |
| } | |
| ], | |
| "logging_steps": 5, | |
| "max_steps": 38, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 150, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 8.0526013794091e+16, | |
| "train_batch_size": 32, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |