{ "best_metric": null, "best_model_checkpoint": null, "epoch": 0.010968921389396709, "eval_steps": 3, "global_step": 3, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.003656307129798903, "grad_norm": 0.09328000247478485, "learning_rate": 2e-05, "loss": 10.3619, "step": 1 }, { "epoch": 0.003656307129798903, "eval_loss": 10.363189697265625, "eval_runtime": 0.5775, "eval_samples_per_second": 798.302, "eval_steps_per_second": 100.437, "step": 1 }, { "epoch": 0.007312614259597806, "grad_norm": 0.08740244060754776, "learning_rate": 4e-05, "loss": 10.36, "step": 2 }, { "epoch": 0.010968921389396709, "grad_norm": 0.08197702467441559, "learning_rate": 6e-05, "loss": 10.3704, "step": 3 }, { "epoch": 0.010968921389396709, "eval_loss": 10.363097190856934, "eval_runtime": 0.5623, "eval_samples_per_second": 819.818, "eval_steps_per_second": 103.144, "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": 1255258718208.0, "train_batch_size": 1, "trial_name": null, "trial_params": null }