| { |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 0.0006736842105263158, |
| "eval_steps": 200, |
| "global_step": 44, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.0, |
| "grad_norm": 9.50096607208252, |
| "learning_rate": 6.123698714023271e-08, |
| "loss": 4.4392, |
| "step": 1 |
| }, |
| { |
| "epoch": 0.0, |
| "grad_norm": 9.429557800292969, |
| "learning_rate": 6.12369871402327e-07, |
| "loss": 4.58, |
| "step": 10 |
| }, |
| { |
| "epoch": 0.0, |
| "grad_norm": 9.127130508422852, |
| "learning_rate": 1.224739742804654e-06, |
| "loss": 4.465, |
| "step": 20 |
| }, |
| { |
| "epoch": 0.0, |
| "grad_norm": 8.588820457458496, |
| "learning_rate": 1.837109614206981e-06, |
| "loss": 4.4953, |
| "step": 30 |
| }, |
| { |
| "epoch": 0.0, |
| "grad_norm": 8.70195198059082, |
| "learning_rate": 2.449479485609308e-06, |
| "loss": 4.3031, |
| "step": 40 |
| } |
| ], |
| "logging_steps": 10, |
| "max_steps": 65312, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 1, |
| "save_steps": 200, |
| "total_flos": 59679826080000.0, |
| "train_batch_size": 1, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
