| { |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 4.177545691906005, |
| "eval_steps": 500, |
| "global_step": 100, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.42, |
| "grad_norm": 0.1815568506717682, |
| "learning_rate": 2.9999999999999997e-05, |
| "loss": 3.8657, |
| "step": 10 |
| }, |
| { |
| "epoch": 0.84, |
| "grad_norm": 0.23455914855003357, |
| "learning_rate": 5.9999999999999995e-05, |
| "loss": 3.8223, |
| "step": 20 |
| }, |
| { |
| "epoch": 1.25, |
| "grad_norm": 0.32260793447494507, |
| "learning_rate": 8.999999999999999e-05, |
| "loss": 3.7255, |
| "step": 30 |
| }, |
| { |
| "epoch": 1.67, |
| "grad_norm": 0.38705918192863464, |
| "learning_rate": 0.00011999999999999999, |
| "loss": 3.4952, |
| "step": 40 |
| }, |
| { |
| "epoch": 2.09, |
| "grad_norm": 0.5273059606552124, |
| "learning_rate": 0.00015, |
| "loss": 3.098, |
| "step": 50 |
| }, |
| { |
| "epoch": 2.51, |
| "grad_norm": 0.6030514240264893, |
| "learning_rate": 0.00017999999999999998, |
| "loss": 2.5299, |
| "step": 60 |
| }, |
| { |
| "epoch": 2.92, |
| "grad_norm": 0.459722101688385, |
| "learning_rate": 0.00020999999999999998, |
| "loss": 1.899, |
| "step": 70 |
| }, |
| { |
| "epoch": 3.34, |
| "grad_norm": 0.1655016839504242, |
| "learning_rate": 0.00023999999999999998, |
| "loss": 1.6018, |
| "step": 80 |
| }, |
| { |
| "epoch": 3.76, |
| "grad_norm": 0.10938003659248352, |
| "learning_rate": 0.00027, |
| "loss": 1.4726, |
| "step": 90 |
| }, |
| { |
| "epoch": 4.18, |
| "grad_norm": 0.09813433140516281, |
| "learning_rate": 0.0003, |
| "loss": 1.4336, |
| "step": 100 |
| } |
| ], |
| "logging_steps": 10, |
| "max_steps": 300, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 14, |
| "save_steps": 100, |
| "total_flos": 1.863006384782131e+16, |
| "train_batch_size": 4, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
