| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 2.001000500250125, | |
| "eval_steps": 500, | |
| "global_step": 4000, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.25, | |
| "grad_norm": 40.72060012817383, | |
| "learning_rate": 1.8999499749874938e-05, | |
| "loss": 0.416, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.5, | |
| "grad_norm": 0.45640167593955994, | |
| "learning_rate": 1.7998999499749875e-05, | |
| "loss": 0.259, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.75, | |
| "grad_norm": 24.118961334228516, | |
| "learning_rate": 1.6998499249624815e-05, | |
| "loss": 0.2726, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "grad_norm": 43.76200485229492, | |
| "learning_rate": 1.599799899949975e-05, | |
| "loss": 0.2471, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 1.25, | |
| "grad_norm": 31.93831443786621, | |
| "learning_rate": 1.4997498749374688e-05, | |
| "loss": 0.1518, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 1.5, | |
| "grad_norm": 0.02012985199689865, | |
| "learning_rate": 1.3996998499249626e-05, | |
| "loss": 0.1421, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 1.75, | |
| "grad_norm": 0.22942015528678894, | |
| "learning_rate": 1.2996498249124563e-05, | |
| "loss": 0.1463, | |
| "step": 3500 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "grad_norm": 0.18562756478786469, | |
| "learning_rate": 1.19959979989995e-05, | |
| "loss": 0.1512, | |
| "step": 4000 | |
| } | |
| ], | |
| "logging_steps": 500, | |
| "max_steps": 9995, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 5, | |
| "save_steps": 500, | |
| "total_flos": 7454518975260672.0, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |