| { |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 0.24907063197026022, |
| "eval_steps": 500, |
| "global_step": 67, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.03717472118959108, |
| "grad_norm": 13.546404838562012, |
| "learning_rate": 1.8587360594795542e-07, |
| "loss": 2.8346, |
| "step": 10 |
| }, |
| { |
| "epoch": 0.07434944237918216, |
| "grad_norm": 19.084455490112305, |
| "learning_rate": 3.7174721189591085e-07, |
| "loss": 2.7026, |
| "step": 20 |
| }, |
| { |
| "epoch": 0.11152416356877323, |
| "grad_norm": 13.80436897277832, |
| "learning_rate": 5.576208178438662e-07, |
| "loss": 2.6825, |
| "step": 30 |
| }, |
| { |
| "epoch": 0.14869888475836432, |
| "grad_norm": 12.587150573730469, |
| "learning_rate": 7.434944237918217e-07, |
| "loss": 2.6652, |
| "step": 40 |
| }, |
| { |
| "epoch": 0.18587360594795538, |
| "grad_norm": 21.958721160888672, |
| "learning_rate": 9.29368029739777e-07, |
| "loss": 2.5917, |
| "step": 50 |
| }, |
| { |
| "epoch": 0.22304832713754646, |
| "grad_norm": 13.547331809997559, |
| "learning_rate": 1.1152416356877324e-06, |
| "loss": 2.5062, |
| "step": 60 |
| } |
| ], |
| "logging_steps": 10, |
| "max_steps": 2690, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 10, |
| "save_steps": 500, |
| "stateful_callbacks": { |
| "TrainerControl": { |
| "args": { |
| "should_epoch_stop": false, |
| "should_evaluate": false, |
| "should_log": false, |
| "should_save": false, |
| "should_training_stop": false |
| }, |
| "attributes": {} |
| } |
| }, |
| "total_flos": 28652861008152.0, |
| "train_batch_size": 3, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
