| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 1.0, | |
| "eval_steps": 500, | |
| "global_step": 20, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.05, | |
| "learning_rate": 0.0001, | |
| "loss": 2.1566, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.25, | |
| "learning_rate": 0.00018660254037844388, | |
| "loss": 2.2312, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.5, | |
| "learning_rate": 0.00011736481776669306, | |
| "loss": 2.0678, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.75, | |
| "learning_rate": 3.5721239031346066e-05, | |
| "loss": 2.1481, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "learning_rate": 0.0, | |
| "loss": 2.1518, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_loss": 2.047029972076416, | |
| "eval_runtime": 6.0766, | |
| "eval_samples_per_second": 3.291, | |
| "eval_steps_per_second": 3.291, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "step": 20, | |
| "total_flos": 1434058374512640.0, | |
| "train_loss": 2.146018850803375, | |
| "train_runtime": 37.3509, | |
| "train_samples_per_second": 0.535, | |
| "train_steps_per_second": 0.535 | |
| } | |
| ], | |
| "logging_steps": 5, | |
| "max_steps": 20, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 100, | |
| "total_flos": 1434058374512640.0, | |
| "train_batch_size": 1, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |