| { | |
| "best_metric": 0.25045502185821533, | |
| "best_model_checkpoint": "ontonotes_roberta-large/checkpoint-108138", | |
| "epoch": 3.0, | |
| "eval_steps": 500, | |
| "global_step": 108138, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 1.0, | |
| "grad_norm": 2.651404619216919, | |
| "learning_rate": 1.960019974477057e-05, | |
| "loss": 0.4522, | |
| "step": 36046 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_loss": 0.28564417362213135, | |
| "eval_runtime": 161.0463, | |
| "eval_samples_per_second": 165.884, | |
| "eval_steps_per_second": 20.739, | |
| "step": 36046 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "grad_norm": 0.05408318713307381, | |
| "learning_rate": 1.920034400488265e-05, | |
| "loss": 0.2819, | |
| "step": 72092 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_loss": 0.25353872776031494, | |
| "eval_runtime": 159.5889, | |
| "eval_samples_per_second": 167.399, | |
| "eval_steps_per_second": 20.929, | |
| "step": 72092 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "grad_norm": 6.422146320343018, | |
| "learning_rate": 1.8800466071131334e-05, | |
| "loss": 0.2472, | |
| "step": 108138 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_loss": 0.25045502185821533, | |
| "eval_runtime": 160.8762, | |
| "eval_samples_per_second": 166.059, | |
| "eval_steps_per_second": 20.761, | |
| "step": 108138 | |
| } | |
| ], | |
| "logging_steps": 500, | |
| "max_steps": 1802300, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 50, | |
| "save_steps": 500, | |
| "stateful_callbacks": { | |
| "EarlyStoppingCallback": { | |
| "args": { | |
| "early_stopping_patience": 5, | |
| "early_stopping_threshold": 0.0 | |
| }, | |
| "attributes": { | |
| "early_stopping_patience_counter": 0 | |
| } | |
| }, | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 1.0473132168385466e+17, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |