| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.0501222984081158, | |
| "eval_steps": 500, | |
| "global_step": 2500, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.01002445968162316, | |
| "grad_norm": 0.4234631359577179, | |
| "learning_rate": 2.969926620955131e-05, | |
| "loss": 0.0295, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.02004891936324632, | |
| "grad_norm": 0.30727919936180115, | |
| "learning_rate": 2.939853241910261e-05, | |
| "loss": 0.0263, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.03007337904486948, | |
| "grad_norm": 1.893353819847107, | |
| "learning_rate": 2.9097798628653917e-05, | |
| "loss": 0.0239, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 0.04009783872649264, | |
| "grad_norm": 0.4890647232532501, | |
| "learning_rate": 2.879706483820522e-05, | |
| "loss": 0.0234, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 0.0501222984081158, | |
| "grad_norm": 0.25260698795318604, | |
| "learning_rate": 2.849633104775653e-05, | |
| "loss": 0.0227, | |
| "step": 2500 | |
| } | |
| ], | |
| "logging_steps": 500, | |
| "max_steps": 49878, | |
| "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": 16, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |