| { |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 9.23076923076923, |
| "eval_steps": 500, |
| "global_step": 60, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 1.5384615384615383, |
| "grad_norm": 3.103752613067627, |
| "learning_rate": 1.1750000000000001e-05, |
| "loss": 0.5298, |
| "step": 10 |
| }, |
| { |
| "epoch": 3.076923076923077, |
| "grad_norm": 3.421727180480957, |
| "learning_rate": 9.4e-06, |
| "loss": 0.0743, |
| "step": 20 |
| }, |
| { |
| "epoch": 4.615384615384615, |
| "grad_norm": 0.5470479726791382, |
| "learning_rate": 7.05e-06, |
| "loss": 0.019, |
| "step": 30 |
| }, |
| { |
| "epoch": 6.153846153846154, |
| "grad_norm": 0.8602386116981506, |
| "learning_rate": 4.7e-06, |
| "loss": 0.0056, |
| "step": 40 |
| }, |
| { |
| "epoch": 7.6923076923076925, |
| "grad_norm": 0.38434720039367676, |
| "learning_rate": 2.35e-06, |
| "loss": 0.0035, |
| "step": 50 |
| }, |
| { |
| "epoch": 9.23076923076923, |
| "grad_norm": 0.28509363532066345, |
| "learning_rate": 0.0, |
| "loss": 0.0016, |
| "step": 60 |
| } |
| ], |
| "logging_steps": 10, |
| "max_steps": 60, |
| "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": true, |
| "should_training_stop": true |
| }, |
| "attributes": {} |
| } |
| }, |
| "total_flos": 0.0, |
| "train_batch_size": 128, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
