{ "best_metric": null, "best_model_checkpoint": null, "epoch": 0.9777777777777777, "eval_steps": 22, "global_step": 22, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.4888888888888889, "grad_norm": 0.8757419586181641, "learning_rate": 0.00018857142857142857, "loss": 2.4264, "mean_token_accuracy": 0.5001081395962135, "step": 11, "timestamp_in_seconds": 1739977815.8543055 }, { "epoch": 0.9777777777777777, "grad_norm": 0.9374493956565857, "learning_rate": 0.00016761904761904763, "loss": 2.0856, "mean_token_accuracy": 0.5345453885716823, "step": 22, "timestamp_in_seconds": 1739977832.7132454 }, { "epoch": 0.9777777777777777, "eval_loss": 1.793185830116272, "eval_mean_token_accuracy": 0.5958210001557875, "eval_runtime": 0.5093, "eval_samples_per_second": 39.266, "eval_steps_per_second": 5.89, "step": 22, "timestamp_in_seconds": 1739977833.2630043 } ], "logging_steps": 11, "max_steps": 110, "num_input_tokens_seen": 0, "num_train_epochs": 5, "save_steps": 22, "stateful_callbacks": { "TrainerControl": { "args": { "should_epoch_stop": false, "should_evaluate": false, "should_log": false, "should_save": true, "should_training_stop": false }, "attributes": {} } }, "total_flos": 1207391250800640.0, "train_batch_size": 2, "trial_name": null, "trial_params": null }