{ "best_global_step": null, "best_metric": null, "best_model_checkpoint": null, "epoch": 0.2, "eval_steps": 500, "global_step": 50, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.04, "grad_norm": 0.7557973265647888, "learning_rate": 0.00018222222222222224, "loss": 1.6374, "step": 10 }, { "epoch": 0.08, "grad_norm": 0.46449410915374756, "learning_rate": 0.0001377777777777778, "loss": 0.5202, "step": 20 }, { "epoch": 0.12, "grad_norm": 0.3183814287185669, "learning_rate": 9.333333333333334e-05, "loss": 0.3959, "step": 30 }, { "epoch": 0.16, "grad_norm": 0.339102566242218, "learning_rate": 4.888888888888889e-05, "loss": 0.3556, "step": 40 }, { "epoch": 0.2, "grad_norm": 0.2479727566242218, "learning_rate": 4.444444444444445e-06, "loss": 0.3488, "step": 50 } ], "logging_steps": 10, "max_steps": 50, "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": true }, "attributes": {} } }, "total_flos": 7961420757110784.0, "train_batch_size": 2, "trial_name": null, "trial_params": null }