| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.004916018025399427, | |
| "eval_steps": 3, | |
| "global_step": 3, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0016386726751331422, | |
| "grad_norm": 1.8315523862838745, | |
| "learning_rate": 2e-05, | |
| "loss": 1.8684, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0016386726751331422, | |
| "eval_loss": 1.9507054090499878, | |
| "eval_runtime": 72.8095, | |
| "eval_samples_per_second": 3.53, | |
| "eval_steps_per_second": 1.772, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0032773453502662844, | |
| "grad_norm": 1.7030572891235352, | |
| "learning_rate": 4e-05, | |
| "loss": 1.9973, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.004916018025399427, | |
| "grad_norm": 1.5281317234039307, | |
| "learning_rate": 6e-05, | |
| "loss": 2.0103, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.004916018025399427, | |
| "eval_loss": 1.9461408853530884, | |
| "eval_runtime": 76.6733, | |
| "eval_samples_per_second": 3.352, | |
| "eval_steps_per_second": 1.682, | |
| "step": 3 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 10, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 3, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 580633541738496.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |