| { |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 0.0003698224852071006, |
| "eval_steps": 1, |
| "global_step": 2, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.0001849112426035503, |
| "grad_norm": 1.7985665798187256, |
| "learning_rate": 2e-05, |
| "loss": 1.6741, |
| "step": 1 |
| }, |
| { |
| "epoch": 0.0001849112426035503, |
| "eval_loss": 1.4593884944915771, |
| "eval_runtime": 23.5176, |
| "eval_samples_per_second": 12.119, |
| "eval_steps_per_second": 12.119, |
| "step": 1 |
| }, |
| { |
| "epoch": 0.0003698224852071006, |
| "grad_norm": 1.3028101921081543, |
| "learning_rate": 4e-05, |
| "loss": 1.5244, |
| "step": 2 |
| }, |
| { |
| "epoch": 0.0003698224852071006, |
| "eval_loss": 1.4595413208007812, |
| "eval_runtime": 23.1928, |
| "eval_samples_per_second": 12.288, |
| "eval_steps_per_second": 12.288, |
| "step": 2 |
| } |
| ], |
| "logging_steps": 1, |
| "max_steps": 2, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 1, |
| "save_steps": 1, |
| "stateful_callbacks": { |
| "TrainerControl": { |
| "args": { |
| "should_epoch_stop": false, |
| "should_evaluate": false, |
| "should_log": false, |
| "should_save": true, |
| "should_training_stop": true |
| }, |
| "attributes": {} |
| } |
| }, |
| "total_flos": 46174681694208.0, |
| "train_batch_size": 1, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
