| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 10.0, | |
| "eval_steps": 500, | |
| "global_step": 620, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 8.064516129032258, | |
| "grad_norm": 0.49170875549316406, | |
| "learning_rate": 9.67741935483871e-06, | |
| "loss": 2.2228, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "step": 620, | |
| "total_flos": 4.144250115588096e+16, | |
| "train_loss": 2.163431647516066, | |
| "train_runtime": 6094.6449, | |
| "train_samples_per_second": 0.814, | |
| "train_steps_per_second": 0.102 | |
| } | |
| ], | |
| "logging_steps": 500, | |
| "max_steps": 620, | |
| "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": 4.144250115588096e+16, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |