| { |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 5.970149253731344, |
| "eval_steps": 500, |
| "global_step": 800, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.746268656716418, |
| "grad_norm": 0.2015659064054489, |
| "learning_rate": 3.73134328358209e-06, |
| "loss": 0.1198, |
| "step": 100 |
| }, |
| { |
| "epoch": 1.4925373134328357, |
| "grad_norm": 0.16025546193122864, |
| "learning_rate": 7.46268656716418e-06, |
| "loss": 0.0693, |
| "step": 200 |
| }, |
| { |
| "epoch": 2.2388059701492535, |
| "grad_norm": 0.1018073558807373, |
| "learning_rate": 9.867330016583748e-06, |
| "loss": 0.0496, |
| "step": 300 |
| }, |
| { |
| "epoch": 2.9850746268656714, |
| "grad_norm": 0.100601427257061, |
| "learning_rate": 9.45273631840796e-06, |
| "loss": 0.0341, |
| "step": 400 |
| }, |
| { |
| "epoch": 3.7313432835820897, |
| "grad_norm": 0.0992753654718399, |
| "learning_rate": 9.038142620232173e-06, |
| "loss": 0.0216, |
| "step": 500 |
| }, |
| { |
| "epoch": 4.477611940298507, |
| "grad_norm": 0.08199736475944519, |
| "learning_rate": 8.623548922056384e-06, |
| "loss": 0.0187, |
| "step": 600 |
| }, |
| { |
| "epoch": 5.223880597014926, |
| "grad_norm": 0.08397415280342102, |
| "learning_rate": 8.208955223880599e-06, |
| "loss": 0.0166, |
| "step": 700 |
| }, |
| { |
| "epoch": 5.970149253731344, |
| "grad_norm": 0.13193649053573608, |
| "learning_rate": 7.79436152570481e-06, |
| "loss": 0.013, |
| "step": 800 |
| } |
| ], |
| "logging_steps": 100, |
| "max_steps": 2680, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 20, |
| "save_steps": 800, |
| "total_flos": 0.0, |
| "train_batch_size": 8, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
