{ "best_metric": null, "best_model_checkpoint": null, "epoch": 4.0, "eval_steps": 500, "global_step": 4, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 1.0, "grad_norm": Infinity, "learning_rate": 0.0001, "loss": 3.4942, "step": 1 }, { "epoch": 2.0, "grad_norm": 90.76869201660156, "learning_rate": 7.500000000000001e-05, "loss": 3.5171, "step": 2 }, { "epoch": 3.0, "grad_norm": 52.46024703979492, "learning_rate": 5e-05, "loss": 3.0473, "step": 3 }, { "epoch": 4.0, "grad_norm": 12.389888763427734, "learning_rate": 2.5e-05, "loss": 2.8469, "step": 4 }, { "epoch": 4.0, "step": 4, "total_flos": 333548660400.0, "train_loss": 3.2263943552970886, "train_runtime": 27.0103, "train_samples_per_second": 0.74, "train_steps_per_second": 0.148 } ], "logging_steps": 1, "max_steps": 4, "num_input_tokens_seen": 0, "num_train_epochs": 4, "save_steps": 500, "stateful_callbacks": { "TrainerControl": { "args": { "should_epoch_stop": false, "should_evaluate": false, "should_log": false, "should_save": true, "should_training_stop": true }, "attributes": {} } }, "total_flos": 333548660400.0, "train_batch_size": 2, "trial_name": null, "trial_params": null }