{ "best_global_step": null, "best_metric": null, "best_model_checkpoint": null, "epoch": 3.0, "eval_steps": 500, "global_step": 45, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 1.3448275862068966, "grad_norm": 24.302814483642578, "learning_rate": 1.288888888888889e-05, "loss": 10.5505, "step": 20 }, { "epoch": 2.689655172413793, "grad_norm": 25.50529670715332, "learning_rate": 4.000000000000001e-06, "loss": 7.6317, "step": 40 } ], "logging_steps": 20, "max_steps": 45, "num_input_tokens_seen": 0, "num_train_epochs": 3, "save_steps": 200, "stateful_callbacks": { "TrainerControl": { "args": { "should_epoch_stop": false, "should_evaluate": false, "should_log": false, "should_save": true, "should_training_stop": true }, "attributes": {} } }, "total_flos": 2992283273134080.0, "train_batch_size": 2, "trial_name": null, "trial_params": null }