| { | |
| "best_metric": 0.16582228243350983, | |
| "best_model_checkpoint": "autotrain-jq0ww-5g421/checkpoint-6", | |
| "epoch": 3.0, | |
| "eval_steps": 500, | |
| "global_step": 6, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.5, | |
| "grad_norm": 8.570414543151855, | |
| "learning_rate": 5e-05, | |
| "loss": 0.7037, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "grad_norm": 7.788650989532471, | |
| "learning_rate": 4e-05, | |
| "loss": 0.6993, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_accuracy": 1.0, | |
| "eval_auc": 1.0, | |
| "eval_f1": 1.0, | |
| "eval_loss": 0.45410236716270447, | |
| "eval_precision": 1.0, | |
| "eval_recall": 1.0, | |
| "eval_runtime": 0.7226, | |
| "eval_samples_per_second": 5.535, | |
| "eval_steps_per_second": 1.384, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 1.5, | |
| "grad_norm": 6.876282215118408, | |
| "learning_rate": 3e-05, | |
| "loss": 0.4835, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "grad_norm": 15.491480827331543, | |
| "learning_rate": 2e-05, | |
| "loss": 0.418, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_accuracy": 1.0, | |
| "eval_auc": 1.0, | |
| "eval_f1": 1.0, | |
| "eval_loss": 0.22139890491962433, | |
| "eval_precision": 1.0, | |
| "eval_recall": 1.0, | |
| "eval_runtime": 0.7167, | |
| "eval_samples_per_second": 5.581, | |
| "eval_steps_per_second": 1.395, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 2.5, | |
| "grad_norm": 4.253661155700684, | |
| "learning_rate": 1e-05, | |
| "loss": 0.2882, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "grad_norm": 3.662368059158325, | |
| "learning_rate": 0.0, | |
| "loss": 0.219, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_accuracy": 1.0, | |
| "eval_auc": 1.0, | |
| "eval_f1": 1.0, | |
| "eval_loss": 0.16582228243350983, | |
| "eval_precision": 1.0, | |
| "eval_recall": 1.0, | |
| "eval_runtime": 0.7175, | |
| "eval_samples_per_second": 5.575, | |
| "eval_steps_per_second": 1.394, | |
| "step": 6 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 6, | |
| "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": 3157332664320.0, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |