| { | |
| "best_global_step": null, | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.1859888406695598, | |
| "eval_steps": 0, | |
| "global_step": 1500, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.06199628022318661, | |
| "grad_norm": 18.962848663330078, | |
| "learning_rate": 9.940000000000001e-07, | |
| "loss": 0.62, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.12399256044637322, | |
| "grad_norm": 30.33436393737793, | |
| "learning_rate": 1.9880000000000003e-06, | |
| "loss": 0.3153, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.1859888406695598, | |
| "grad_norm": 140.38357543945312, | |
| "learning_rate": 2.9880000000000004e-06, | |
| "loss": 0.2382, | |
| "step": 1500 | |
| } | |
| ], | |
| "logging_steps": 500, | |
| "max_steps": 8065, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 500, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 0.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |