{ "best_global_step": null, "best_metric": null, "best_model_checkpoint": null, "epoch": 0.039603960396039604, "eval_steps": 500, "global_step": 50, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.007920792079207921, "grad_norm": 1.0817395448684692, "learning_rate": 0.00045000000000000004, "loss": 1.3794532775878907, "step": 10 }, { "epoch": 0.015841584158415842, "grad_norm": 0.5635583400726318, "learning_rate": 0.00045000000000000004, "loss": 0.805211353302002, "step": 20 }, { "epoch": 0.023762376237623763, "grad_norm": 0.5437660813331604, "learning_rate": 0.00039444444444444444, "loss": 0.8068445205688477, "step": 30 }, { "epoch": 0.031683168316831684, "grad_norm": 0.39760076999664307, "learning_rate": 0.0003388888888888889, "loss": 0.7344035625457763, "step": 40 }, { "epoch": 0.039603960396039604, "grad_norm": 0.4437391757965088, "learning_rate": 0.00028333333333333335, "loss": 0.7755752563476562, "step": 50 } ], "logging_steps": 10, "max_steps": 100, "num_input_tokens_seen": 0, "num_train_epochs": 1, "save_steps": 50, "stateful_callbacks": { "TrainerControl": { "args": { "should_epoch_stop": false, "should_evaluate": false, "should_log": false, "should_save": true, "should_training_stop": false }, "attributes": {} } }, "total_flos": 128422622822400.0, "train_batch_size": 1, "trial_name": null, "trial_params": null }