| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 7.6923076923076925, | |
| "eval_steps": 500, | |
| "global_step": 500, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 1.5384615384615383, | |
| "grad_norm": 28.85655403137207, | |
| "learning_rate": 9.9812e-06, | |
| "loss": 1.0794, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 3.076923076923077, | |
| "grad_norm": 40.480037689208984, | |
| "learning_rate": 9.961400000000001e-06, | |
| "loss": 1.1026, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 4.615384615384615, | |
| "grad_norm": 22.348379135131836, | |
| "learning_rate": 9.941600000000002e-06, | |
| "loss": 1.1211, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 6.153846153846154, | |
| "grad_norm": 49.462806701660156, | |
| "learning_rate": 9.921600000000002e-06, | |
| "loss": 1.1217, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 7.6923076923076925, | |
| "grad_norm": 37.26523208618164, | |
| "learning_rate": 9.901600000000002e-06, | |
| "loss": 1.0993, | |
| "step": 500 | |
| } | |
| ], | |
| "logging_steps": 100, | |
| "max_steps": 50000, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 770, | |
| "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": 1.91121583104e+18, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |