| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 7.0, | |
| "eval_steps": 500, | |
| "global_step": 28, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 1.5, | |
| "grad_norm": 0.2171144038438797, | |
| "learning_rate": 0.00017600000000000002, | |
| "loss": 2.7548, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "grad_norm": 0.33324092626571655, | |
| "learning_rate": 0.00012800000000000002, | |
| "loss": 2.6043, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 4.5, | |
| "grad_norm": 0.2771734595298767, | |
| "learning_rate": 8e-05, | |
| "loss": 2.4819, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "grad_norm": 0.30806684494018555, | |
| "learning_rate": 3.2000000000000005e-05, | |
| "loss": 2.4527, | |
| "step": 24 | |
| } | |
| ], | |
| "logging_steps": 6, | |
| "max_steps": 28, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 7, | |
| "save_steps": 500, | |
| "total_flos": 8251393802502144.0, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |