| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 2.06282722513089, | |
| "eval_steps": 25, | |
| "global_step": 6, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.33507853403141363, | |
| "grad_norm": 3.506351947784424, | |
| "learning_rate": 0.0002819134295108992, | |
| "loss": 3.5743, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.33507853403141363, | |
| "eval_loss": 3.344470262527466, | |
| "eval_runtime": 0.2886, | |
| "eval_samples_per_second": 173.265, | |
| "eval_steps_per_second": 45.049, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.6701570680628273, | |
| "grad_norm": 1.5725631713867188, | |
| "learning_rate": 0.00023249999999999999, | |
| "loss": 3.2503, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 1.031413612565445, | |
| "grad_norm": 1.3663052320480347, | |
| "learning_rate": 0.000165, | |
| "loss": 3.5226, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 1.3664921465968587, | |
| "grad_norm": 1.04362154006958, | |
| "learning_rate": 9.750000000000003e-05, | |
| "loss": 3.0157, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 1.7015706806282722, | |
| "grad_norm": 0.90383380651474, | |
| "learning_rate": 4.808657048910077e-05, | |
| "loss": 2.9952, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 2.06282722513089, | |
| "grad_norm": 0.8591496348381042, | |
| "learning_rate": 2.9999999999999997e-05, | |
| "loss": 3.1916, | |
| "step": 6 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 6, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 3, | |
| "save_steps": 50, | |
| "stateful_callbacks": { | |
| "EarlyStoppingCallback": { | |
| "args": { | |
| "early_stopping_patience": 1, | |
| "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": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 2665681652809728.0, | |
| "train_batch_size": 1, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |