{ "best_metric": null, "best_model_checkpoint": null, "epoch": 0.0008126227398930047, "eval_steps": 3, "global_step": 3, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.00027087424663100153, "grad_norm": 5.178700923919678, "learning_rate": 2e-05, "loss": 44.4678, "step": 1 }, { "epoch": 0.00027087424663100153, "eval_loss": 11.137868881225586, "eval_runtime": 26.6049, "eval_samples_per_second": 58.448, "eval_steps_per_second": 29.243, "step": 1 }, { "epoch": 0.0005417484932620031, "grad_norm": 7.01981782913208, "learning_rate": 4e-05, "loss": 44.4444, "step": 2 }, { "epoch": 0.0008126227398930047, "grad_norm": 7.090907573699951, "learning_rate": 6e-05, "loss": 44.6979, "step": 3 }, { "epoch": 0.0008126227398930047, "eval_loss": 11.131836891174316, "eval_runtime": 26.7529, "eval_samples_per_second": 58.125, "eval_steps_per_second": 29.081, "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": 249594642432.0, "train_batch_size": 2, "trial_name": null, "trial_params": null }