| { |
| "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": 0.18415939807891846, |
| "learning_rate": 2.9999999999999997e-05, |
| "loss": 3.8654, |
| "step": 10 |
| }, |
| { |
| "epoch": 0.84, |
| "grad_norm": 0.23708771169185638, |
| "learning_rate": 5.9999999999999995e-05, |
| "loss": 3.8218, |
| "step": 20 |
| }, |
| { |
| "epoch": 1.25, |
| "grad_norm": 0.3239809572696686, |
| "learning_rate": 8.999999999999999e-05, |
| "loss": 3.725, |
| "step": 30 |
| }, |
| { |
| "epoch": 1.67, |
| "grad_norm": 0.38910844922065735, |
| "learning_rate": 0.00011999999999999999, |
| "loss": 3.4953, |
| "step": 40 |
| }, |
| { |
| "epoch": 2.09, |
| "grad_norm": 0.520912230014801, |
| "learning_rate": 0.00015, |
| "loss": 3.0984, |
| "step": 50 |
| }, |
| { |
| "epoch": 2.51, |
| "grad_norm": 0.6063631772994995, |
| "learning_rate": 0.00017999999999999998, |
| "loss": 2.5316, |
| "step": 60 |
| }, |
| { |
| "epoch": 2.92, |
| "grad_norm": 0.4615532457828522, |
| "learning_rate": 0.00020999999999999998, |
| "loss": 1.8987, |
| "step": 70 |
| }, |
| { |
| "epoch": 3.34, |
| "grad_norm": 0.16907210648059845, |
| "learning_rate": 0.00023999999999999998, |
| "loss": 1.6041, |
| "step": 80 |
| }, |
| { |
| "epoch": 3.76, |
| "grad_norm": 0.11257671564817429, |
| "learning_rate": 0.00027, |
| "loss": 1.4732, |
| "step": 90 |
| }, |
| { |
| "epoch": 4.18, |
| "grad_norm": 0.08190377801656723, |
| "learning_rate": 0.0003, |
| "loss": 1.4341, |
| "step": 100 |
| } |
| ], |
| "logging_steps": 10, |
| "max_steps": 175, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 8, |
| "save_steps": 100, |
| "total_flos": 1.863006384782131e+16, |
| "train_batch_size": 4, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
