| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 2.9995129079396006, | |
| "eval_steps": 500, | |
| "global_step": 3078, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.4870920603994155, | |
| "grad_norm": 0.6049914360046387, | |
| "learning_rate": 0.00019316938294480988, | |
| "loss": 7.0235, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.974184120798831, | |
| "grad_norm": 0.5930731296539307, | |
| "learning_rate": 0.00016145696457272202, | |
| "loss": 6.4537, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 1.4617632732586459, | |
| "grad_norm": 0.6954319477081299, | |
| "learning_rate": 0.00011243098608364038, | |
| "loss": 5.8788, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 1.9488553336580614, | |
| "grad_norm": 0.7703619003295898, | |
| "learning_rate": 5.990296960148566e-05, | |
| "loss": 5.7091, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 2.4364344861178764, | |
| "grad_norm": 0.9019376635551453, | |
| "learning_rate": 1.8671025926443465e-05, | |
| "loss": 5.1422, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 2.9235265465172917, | |
| "grad_norm": 0.9139459729194641, | |
| "learning_rate": 3.509538621403463e-07, | |
| "loss": 5.0502, | |
| "step": 3000 | |
| } | |
| ], | |
| "logging_steps": 500, | |
| "max_steps": 3078, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 3, | |
| "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": 4.74550444855237e+18, | |
| "train_batch_size": 4, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |