| { |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 2.957345971563981, |
| "eval_steps": 500, |
| "global_step": 78, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.3791469194312796, |
| "grad_norm": 0.2653672397136688, |
| "learning_rate": 0.00029939614409928584, |
| "loss": 0.8199, |
| "step": 10 |
| }, |
| { |
| "epoch": 0.7582938388625592, |
| "grad_norm": 0.1669384390115738, |
| "learning_rate": 0.0002787673190402799, |
| "loss": 0.6913, |
| "step": 20 |
| }, |
| { |
| "epoch": 1.1374407582938388, |
| "grad_norm": 0.13310174643993378, |
| "learning_rate": 0.00023263454721781537, |
| "loss": 0.6417, |
| "step": 30 |
| }, |
| { |
| "epoch": 1.5165876777251186, |
| "grad_norm": 0.12457551062107086, |
| "learning_rate": 0.00017013498987264832, |
| "loss": 0.6113, |
| "step": 40 |
| }, |
| { |
| "epoch": 1.8957345971563981, |
| "grad_norm": 0.13069939613342285, |
| "learning_rate": 0.0001036474508437579, |
| "loss": 0.5921, |
| "step": 50 |
| }, |
| { |
| "epoch": 2.2748815165876777, |
| "grad_norm": 0.1313541829586029, |
| "learning_rate": 4.63406026519703e-05, |
| "loss": 0.5841, |
| "step": 60 |
| }, |
| { |
| "epoch": 2.654028436018957, |
| "grad_norm": 0.12558336555957794, |
| "learning_rate": 9.564769404039419e-06, |
| "loss": 0.5766, |
| "step": 70 |
| } |
| ], |
| "logging_steps": 10, |
| "max_steps": 78, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 3, |
| "save_steps": 500, |
| "stateful_callbacks": { |
| "TrainerControl": { |
| "args": { |
| "should_epoch_stop": false, |
| "should_evaluate": false, |
| "should_log": false, |
| "should_save": true, |
| "should_training_stop": true |
| }, |
| "attributes": {} |
| } |
| }, |
| "total_flos": 1.0702567157373338e+18, |
| "train_batch_size": 2, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
