| { |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 3.0, |
| "eval_steps": 500, |
| "global_step": 102, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.29, |
| "grad_norm": 0.5000045895576477, |
| "learning_rate": 8.000000000000001e-07, |
| "loss": 0.321, |
| "step": 10 |
| }, |
| { |
| "epoch": 0.59, |
| "grad_norm": 0.5869241952896118, |
| "learning_rate": 1.6000000000000001e-06, |
| "loss": 0.2957, |
| "step": 20 |
| }, |
| { |
| "epoch": 0.88, |
| "grad_norm": 0.4427128732204437, |
| "learning_rate": 2.4000000000000003e-06, |
| "loss": 0.3256, |
| "step": 30 |
| }, |
| { |
| "epoch": 1.18, |
| "grad_norm": 0.5010120272636414, |
| "learning_rate": 3.2000000000000003e-06, |
| "loss": 0.2927, |
| "step": 40 |
| }, |
| { |
| "epoch": 1.47, |
| "grad_norm": 0.4371396601200104, |
| "learning_rate": 3.920000000000001e-06, |
| "loss": 0.361, |
| "step": 50 |
| }, |
| { |
| "epoch": 1.76, |
| "grad_norm": 0.38588765263557434, |
| "learning_rate": 4.7200000000000005e-06, |
| "loss": 0.2959, |
| "step": 60 |
| }, |
| { |
| "epoch": 2.06, |
| "grad_norm": 0.48722440004348755, |
| "learning_rate": 5.5200000000000005e-06, |
| "loss": 0.3026, |
| "step": 70 |
| }, |
| { |
| "epoch": 2.35, |
| "grad_norm": 0.28636398911476135, |
| "learning_rate": 6.3200000000000005e-06, |
| "loss": 0.281, |
| "step": 80 |
| }, |
| { |
| "epoch": 2.65, |
| "grad_norm": 0.4055095314979553, |
| "learning_rate": 7.1200000000000004e-06, |
| "loss": 0.3046, |
| "step": 90 |
| }, |
| { |
| "epoch": 2.94, |
| "grad_norm": 0.373374879360199, |
| "learning_rate": 7.92e-06, |
| "loss": 0.3019, |
| "step": 100 |
| } |
| ], |
| "logging_steps": 10, |
| "max_steps": 102, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 3, |
| "save_steps": 500, |
| "total_flos": 495082765025280.0, |
| "train_batch_size": 8, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
