{ "best_metric": null, "best_model_checkpoint": null, "epoch": 0.00038652322360368483, "eval_steps": 3, "global_step": 3, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.0001288410745345616, "grad_norm": NaN, "learning_rate": 0.0, "loss": 3.2623, "step": 1 }, { "epoch": 0.0001288410745345616, "eval_loss": 3.1917941570281982, "eval_runtime": 49.1154, "eval_samples_per_second": 266.149, "eval_steps_per_second": 33.269, "step": 1 }, { "epoch": 0.0002576821490691232, "grad_norm": NaN, "learning_rate": 0.0, "loss": 2.9077, "step": 2 }, { "epoch": 0.00038652322360368483, "grad_norm": NaN, "learning_rate": 0.0, "loss": 2.9139, "step": 3 }, { "epoch": 0.00038652322360368483, "eval_loss": 3.1917941570281982, "eval_runtime": 48.8794, "eval_samples_per_second": 267.434, "eval_steps_per_second": 33.429, "step": 3 } ], "logging_steps": 1, "max_steps": 10, "num_input_tokens_seen": 0, "num_train_epochs": 1, "save_steps": 3, "stateful_callbacks": { "TrainerControl": { "args": { "should_epoch_stop": false, "should_evaluate": false, "should_log": false, "should_save": true, "should_training_stop": false }, "attributes": {} } }, "total_flos": 333210206601216.0, "train_batch_size": 1, "trial_name": null, "trial_params": null }