{ "best_metric": 1.2990323305130005, "best_model_checkpoint": "miner_id_24/checkpoint-50", "epoch": 0.034916201117318434, "eval_steps": 50, "global_step": 50, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.0006983240223463687, "eval_loss": 1.370945930480957, "eval_runtime": 52.3088, "eval_samples_per_second": 11.528, "eval_steps_per_second": 2.887, "step": 1 }, { "epoch": 0.006983240223463687, "grad_norm": 0.8107507228851318, "learning_rate": 4.22e-05, "loss": 1.0747, "step": 10 }, { "epoch": 0.013966480446927373, "grad_norm": 0.5126632452011108, "learning_rate": 8.44e-05, "loss": 0.9055, "step": 20 }, { "epoch": 0.02094972067039106, "grad_norm": 0.6242287158966064, "learning_rate": 0.0001266, "loss": 0.9136, "step": 30 }, { "epoch": 0.027932960893854747, "grad_norm": 0.6027160882949829, "learning_rate": 0.0001688, "loss": 0.8772, "step": 40 }, { "epoch": 0.034916201117318434, "grad_norm": 1.1633682250976562, "learning_rate": 0.000211, "loss": 2.2737, "step": 50 }, { "epoch": 0.034916201117318434, "eval_loss": 1.2990323305130005, "eval_runtime": 52.3291, "eval_samples_per_second": 11.523, "eval_steps_per_second": 2.886, "step": 50 } ], "logging_steps": 10, "max_steps": 500, "num_input_tokens_seen": 0, "num_train_epochs": 1, "save_steps": 50, "stateful_callbacks": { "EarlyStoppingCallback": { "args": { "early_stopping_patience": 3, "early_stopping_threshold": 0.0 }, "attributes": { "early_stopping_patience_counter": 0 } }, "TrainerControl": { "args": { "should_epoch_stop": false, "should_evaluate": false, "should_log": false, "should_save": true, "should_training_stop": false }, "attributes": {} } }, "total_flos": 1.395228272492544e+16, "train_batch_size": 4, "trial_name": null, "trial_params": null }