| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.0007303114356939714, | |
| "eval_steps": 13, | |
| "global_step": 26, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 2.8088901372845056e-05, | |
| "eval_loss": 0.7164075374603271, | |
| "eval_runtime": 964.0198, | |
| "eval_samples_per_second": 15.549, | |
| "eval_steps_per_second": 7.775, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.00028088901372845055, | |
| "grad_norm": 0.7382564544677734, | |
| "learning_rate": 0.00019396926207859084, | |
| "loss": 0.5811, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0003651557178469857, | |
| "eval_loss": 0.4477322995662689, | |
| "eval_runtime": 961.1483, | |
| "eval_samples_per_second": 15.596, | |
| "eval_steps_per_second": 7.798, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.0005617780274569011, | |
| "grad_norm": 0.35799071192741394, | |
| "learning_rate": 0.00015000000000000001, | |
| "loss": 0.3801, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.0007303114356939714, | |
| "eval_loss": 0.3870624005794525, | |
| "eval_runtime": 962.4524, | |
| "eval_samples_per_second": 15.575, | |
| "eval_steps_per_second": 7.787, | |
| "step": 26 | |
| } | |
| ], | |
| "logging_steps": 10, | |
| "max_steps": 50, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 13, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 9135190211297280.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |