| { | |
| "best_metric": 0.022922784090042114, | |
| "best_model_checkpoint": "autotrain-cpn5h-33x3s/checkpoint-8", | |
| "epoch": 4.0, | |
| "eval_steps": 500, | |
| "global_step": 8, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.5, | |
| "grad_norm": 7.581804275512695, | |
| "learning_rate": 5e-05, | |
| "loss": 0.4876, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "grad_norm": 5.196318626403809, | |
| "learning_rate": 4.2857142857142856e-05, | |
| "loss": 0.3909, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_accuracy": 1.0, | |
| "eval_auc": 1.0, | |
| "eval_f1": 1.0, | |
| "eval_loss": 0.18836069107055664, | |
| "eval_precision": 1.0, | |
| "eval_recall": 1.0, | |
| "eval_runtime": 1.1078, | |
| "eval_samples_per_second": 3.611, | |
| "eval_steps_per_second": 0.903, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 1.5, | |
| "grad_norm": 4.314671516418457, | |
| "learning_rate": 3.571428571428572e-05, | |
| "loss": 0.2379, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "grad_norm": 2.411983013153076, | |
| "learning_rate": 2.857142857142857e-05, | |
| "loss": 0.1229, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_accuracy": 1.0, | |
| "eval_auc": 1.0, | |
| "eval_f1": 1.0, | |
| "eval_loss": 0.06231320649385452, | |
| "eval_precision": 1.0, | |
| "eval_recall": 1.0, | |
| "eval_runtime": 1.4212, | |
| "eval_samples_per_second": 2.815, | |
| "eval_steps_per_second": 0.704, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 2.5, | |
| "grad_norm": 1.4945460557937622, | |
| "learning_rate": 2.1428571428571428e-05, | |
| "loss": 0.0794, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "grad_norm": 1.273388385772705, | |
| "learning_rate": 1.4285714285714285e-05, | |
| "loss": 0.0678, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_accuracy": 1.0, | |
| "eval_auc": 1.0, | |
| "eval_f1": 1.0, | |
| "eval_loss": 0.030503973364830017, | |
| "eval_precision": 1.0, | |
| "eval_recall": 1.0, | |
| "eval_runtime": 1.2483, | |
| "eval_samples_per_second": 3.204, | |
| "eval_steps_per_second": 0.801, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 3.5, | |
| "grad_norm": 0.8340377807617188, | |
| "learning_rate": 7.142857142857143e-06, | |
| "loss": 0.0427, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "grad_norm": 0.6113947629928589, | |
| "learning_rate": 0.0, | |
| "loss": 0.0319, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_accuracy": 1.0, | |
| "eval_auc": 1.0, | |
| "eval_f1": 1.0, | |
| "eval_loss": 0.022922784090042114, | |
| "eval_precision": 1.0, | |
| "eval_recall": 1.0, | |
| "eval_runtime": 1.0262, | |
| "eval_samples_per_second": 3.898, | |
| "eval_steps_per_second": 0.974, | |
| "step": 8 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 8, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 4, | |
| "save_steps": 500, | |
| "stateful_callbacks": { | |
| "EarlyStoppingCallback": { | |
| "args": { | |
| "early_stopping_patience": 5, | |
| "early_stopping_threshold": 0.01 | |
| }, | |
| "attributes": { | |
| "early_stopping_patience_counter": 1 | |
| } | |
| }, | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 4209776885760.0, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |