{ "best_metric": null, "best_model_checkpoint": null, "epoch": 0.0016825574873808188, "eval_steps": 3, "global_step": 3, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.0005608524957936063, "grad_norm": 0.01451126579195261, "learning_rate": 2e-05, "loss": 11.9315, "step": 1 }, { "epoch": 0.0005608524957936063, "eval_loss": 11.931306838989258, "eval_runtime": 2.6729, "eval_samples_per_second": 280.967, "eval_steps_per_second": 140.67, "step": 1 }, { "epoch": 0.0011217049915872126, "grad_norm": 0.008208751678466797, "learning_rate": 4e-05, "loss": 11.9304, "step": 2 }, { "epoch": 0.0016825574873808188, "grad_norm": 0.01280900463461876, "learning_rate": 6e-05, "loss": 11.9319, "step": 3 }, { "epoch": 0.0016825574873808188, "eval_loss": 11.931303977966309, "eval_runtime": 2.7222, "eval_samples_per_second": 275.878, "eval_steps_per_second": 138.123, "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": 384024576.0, "train_batch_size": 2, "trial_name": null, "trial_params": null }