| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.05779383161989442, | |
| "eval_steps": 10, | |
| "global_step": 26, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0022228396776882466, | |
| "eval_loss": 10.376819610595703, | |
| "eval_runtime": 8.0656, | |
| "eval_samples_per_second": 375.791, | |
| "eval_steps_per_second": 46.989, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.02222839677688247, | |
| "grad_norm": 0.9294033050537109, | |
| "learning_rate": 9.330127018922194e-05, | |
| "loss": 166.0306, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.02222839677688247, | |
| "eval_loss": 10.375858306884766, | |
| "eval_runtime": 8.057, | |
| "eval_samples_per_second": 376.194, | |
| "eval_steps_per_second": 47.04, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.04445679355376494, | |
| "grad_norm": 0.9761950969696045, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 166.0063, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.04445679355376494, | |
| "eval_loss": 10.374831199645996, | |
| "eval_runtime": 8.2696, | |
| "eval_samples_per_second": 366.524, | |
| "eval_steps_per_second": 45.831, | |
| "step": 20 | |
| } | |
| ], | |
| "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": 21353126166528.0, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |