| { |
| "best_global_step": null, |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 1.0, |
| "eval_steps": 0, |
| "global_step": 3, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.3333333333333333, |
| "grad_norm": 0.02457178384065628, |
| "learning_rate": 1e-05, |
| "loss": 0.8782, |
| "step": 1 |
| }, |
| { |
| "epoch": 0.6666666666666666, |
| "grad_norm": 0.03207142651081085, |
| "learning_rate": 7.500000000000001e-06, |
| "loss": 0.8059, |
| "step": 2 |
| }, |
| { |
| "epoch": 1.0, |
| "grad_norm": 0.025784870609641075, |
| "learning_rate": 2.5000000000000015e-06, |
| "loss": 0.8975, |
| "step": 3 |
| } |
| ], |
| "logging_steps": 1.0, |
| "max_steps": 3, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 1, |
| "save_steps": 0, |
| "stateful_callbacks": { |
| "TrainerControl": { |
| "args": { |
| "should_epoch_stop": false, |
| "should_evaluate": false, |
| "should_log": false, |
| "should_save": true, |
| "should_training_stop": true |
| }, |
| "attributes": {} |
| } |
| }, |
| "total_flos": 3.2625959713846067e+18, |
| "train_batch_size": 1, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
