| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 10.0, | |
| "eval_steps": 500, | |
| "global_step": 1610, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 3.1055900621118013, | |
| "grad_norm": 2.380723476409912, | |
| "learning_rate": 3.4472049689440996e-05, | |
| "loss": 1.0678, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 6.211180124223603, | |
| "grad_norm": 2.099438428878784, | |
| "learning_rate": 1.894409937888199e-05, | |
| "loss": 0.7287, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 9.316770186335404, | |
| "grad_norm": 1.4192956686019897, | |
| "learning_rate": 3.4161490683229816e-06, | |
| "loss": 0.6669, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "step": 1610, | |
| "total_flos": 1519376405004288.0, | |
| "train_loss": 0.8102951523680124, | |
| "train_runtime": 150.8906, | |
| "train_samples_per_second": 341.241, | |
| "train_steps_per_second": 10.67 | |
| } | |
| ], | |
| "logging_steps": 500, | |
| "max_steps": 1610, | |
| "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": 1519376405004288.0, | |
| "train_batch_size": 32, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |