| { | |
| "best_metric": 22499751936.0, | |
| "best_model_checkpoint": "autotrain-5yjy9-m2jwk/checkpoint-3", | |
| "epoch": 3.0, | |
| "eval_steps": 500, | |
| "global_step": 3, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 1.0, | |
| "grad_norm": 7656831.0, | |
| "learning_rate": 5e-05, | |
| "loss": 37499875328.0, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_explained_variance": 1.0, | |
| "eval_loss": 22499915776.0, | |
| "eval_mae": 149999.71875, | |
| "eval_mse": 22499915776.0, | |
| "eval_r2": NaN, | |
| "eval_rmse": 149999.71875, | |
| "eval_runtime": 0.2445, | |
| "eval_samples_per_second": 4.091, | |
| "eval_steps_per_second": 4.091, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "grad_norm": 7429680.0, | |
| "learning_rate": 2.5e-05, | |
| "loss": 37499899904.0, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_explained_variance": 1.0, | |
| "eval_loss": 22499813376.0, | |
| "eval_mae": 149999.375, | |
| "eval_mse": 22499813376.0, | |
| "eval_r2": NaN, | |
| "eval_rmse": 149999.375, | |
| "eval_runtime": 0.2468, | |
| "eval_samples_per_second": 4.051, | |
| "eval_steps_per_second": 4.051, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "grad_norm": 8526306.0, | |
| "learning_rate": 0.0, | |
| "loss": 37499715584.0, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_explained_variance": 1.0, | |
| "eval_loss": 22499751936.0, | |
| "eval_mae": 149999.171875, | |
| "eval_mse": 22499751936.0, | |
| "eval_r2": NaN, | |
| "eval_rmse": 149999.171875, | |
| "eval_runtime": 0.2411, | |
| "eval_samples_per_second": 4.148, | |
| "eval_steps_per_second": 4.148, | |
| "step": 3 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 3, | |
| "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": 591994559232.0, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |