| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.9863013698630136, | |
| "eval_steps": 500, | |
| "global_step": 27, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0365296803652968, | |
| "grad_norm": 21.481753895151215, | |
| "learning_rate": 3.3333333333333333e-06, | |
| "loss": 1.6412, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.365296803652968, | |
| "grad_norm": 2.2500616965036078, | |
| "learning_rate": 8.043807145043604e-06, | |
| "loss": 1.4447, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.730593607305936, | |
| "grad_norm": 0.9544323271736276, | |
| "learning_rate": 1.956192854956397e-06, | |
| "loss": 1.2269, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.9863013698630136, | |
| "step": 27, | |
| "total_flos": 1954629550080.0, | |
| "train_loss": 1.3019332091013591, | |
| "train_runtime": 388.8606, | |
| "train_samples_per_second": 4.505, | |
| "train_steps_per_second": 0.069 | |
| } | |
| ], | |
| "logging_steps": 10, | |
| "max_steps": 27, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 100, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 1954629550080.0, | |
| "train_batch_size": 1, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |