| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 2.032520325203252, | |
| "eval_steps": 500, | |
| "global_step": 500, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.1, | |
| "grad_norm": 0.7537718524378184, | |
| "learning_rate": 4.998825837977733e-05, | |
| "loss": 1.0335, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "grad_norm": 0.5115893351462029, | |
| "learning_rate": 4.9951068336359185e-05, | |
| "loss": 0.9543, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.3, | |
| "grad_norm": 0.3655365544393326, | |
| "learning_rate": 4.9888447388643216e-05, | |
| "loss": 0.889, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.41, | |
| "grad_norm": 0.3802482724658219, | |
| "learning_rate": 4.980045936184552e-05, | |
| "loss": 0.8824, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.51, | |
| "grad_norm": 0.46128857579583404, | |
| "learning_rate": 4.968719393609757e-05, | |
| "loss": 0.8812, | |
| "step": 125 | |
| }, | |
| { | |
| "epoch": 0.61, | |
| "grad_norm": 0.4675840689300933, | |
| "learning_rate": 4.954876655504144e-05, | |
| "loss": 0.8626, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.71, | |
| "grad_norm": 0.5174033092078555, | |
| "learning_rate": 4.938531830816607e-05, | |
| "loss": 0.8542, | |
| "step": 175 | |
| }, | |
| { | |
| "epoch": 0.81, | |
| "grad_norm": 0.47966453174679635, | |
| "learning_rate": 4.919701578700444e-05, | |
| "loss": 0.8615, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.91, | |
| "grad_norm": 0.5800019356792034, | |
| "learning_rate": 4.898405091533834e-05, | |
| "loss": 0.8198, | |
| "step": 225 | |
| }, | |
| { | |
| "epoch": 1.02, | |
| "grad_norm": 0.5068384935929343, | |
| "learning_rate": 4.874664075358366e-05, | |
| "loss": 0.835, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 1.12, | |
| "grad_norm": 0.5665554500957887, | |
| "learning_rate": 4.84850272775557e-05, | |
| "loss": 0.833, | |
| "step": 275 | |
| }, | |
| { | |
| "epoch": 1.22, | |
| "grad_norm": 0.6225574393610873, | |
| "learning_rate": 4.8199477131839854e-05, | |
| "loss": 0.8362, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 1.32, | |
| "grad_norm": 0.5883987854013639, | |
| "learning_rate": 4.789028135801918e-05, | |
| "loss": 0.8315, | |
| "step": 325 | |
| }, | |
| { | |
| "epoch": 1.42, | |
| "grad_norm": 0.6212622090526995, | |
| "learning_rate": 4.7557755098035814e-05, | |
| "loss": 0.8082, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 1.52, | |
| "grad_norm": 0.6254380356435723, | |
| "learning_rate": 4.720223727298845e-05, | |
| "loss": 0.8112, | |
| "step": 375 | |
| }, | |
| { | |
| "epoch": 1.63, | |
| "grad_norm": 0.7114667768707209, | |
| "learning_rate": 4.682409023769342e-05, | |
| "loss": 0.8141, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 1.73, | |
| "grad_norm": 0.7156140969579615, | |
| "learning_rate": 4.6423699411361474e-05, | |
| "loss": 0.8214, | |
| "step": 425 | |
| }, | |
| { | |
| "epoch": 1.83, | |
| "grad_norm": 0.6560300477797654, | |
| "learning_rate": 4.600147288476647e-05, | |
| "loss": 0.819, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 1.93, | |
| "grad_norm": 0.6220749749772762, | |
| "learning_rate": 4.5557841004306625e-05, | |
| "loss": 0.8177, | |
| "step": 475 | |
| }, | |
| { | |
| "epoch": 2.03, | |
| "grad_norm": 0.7459915153227248, | |
| "learning_rate": 4.509325593338203e-05, | |
| "loss": 0.8207, | |
| "step": 500 | |
| } | |
| ], | |
| "logging_steps": 25, | |
| "max_steps": 2460, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 10, | |
| "save_steps": 500, | |
| "total_flos": 152390335463424.0, | |
| "train_batch_size": 1, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |