| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.9866666666666667, | |
| "eval_steps": 500, | |
| "global_step": 37, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.03, | |
| "learning_rate": 5e-05, | |
| "loss": 2.2275, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.13, | |
| "learning_rate": 0.00019954719225730847, | |
| "loss": 1.9848, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.27, | |
| "learning_rate": 0.00018412535328311814, | |
| "loss": 0.6529, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "learning_rate": 0.00015000000000000001, | |
| "loss": 0.2662, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.53, | |
| "learning_rate": 0.00010475819158237425, | |
| "loss": 0.238, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.67, | |
| "learning_rate": 5.845849869981137e-05, | |
| "loss": 0.2332, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.8, | |
| "learning_rate": 2.139469052572127e-05, | |
| "loss": 0.2287, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.93, | |
| "learning_rate": 1.8071302737293295e-06, | |
| "loss": 0.203, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.99, | |
| "eval_loss": 0.22467635571956635, | |
| "eval_runtime": 9.0559, | |
| "eval_samples_per_second": 22.085, | |
| "eval_steps_per_second": 2.761, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.99, | |
| "step": 37, | |
| "total_flos": 20586009395200.0, | |
| "train_loss": 0.5330296472923176, | |
| "train_runtime": 203.4112, | |
| "train_samples_per_second": 2.95, | |
| "train_steps_per_second": 0.182 | |
| } | |
| ], | |
| "logging_steps": 5, | |
| "max_steps": 37, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 500, | |
| "total_flos": 20586009395200.0, | |
| "train_batch_size": 4, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |