{ "best_metric": 6.864169597625732, "best_model_checkpoint": "miner_id_24/checkpoint-50", "epoch": 0.011763321962122103, "eval_steps": 50, "global_step": 50, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.00023526643924244207, "eval_loss": 6.933060169219971, "eval_runtime": 3.2084, "eval_samples_per_second": 557.906, "eval_steps_per_second": 139.632, "step": 1 }, { "epoch": 0.0023526643924244206, "grad_norm": 0.6924540996551514, "learning_rate": 4.2800000000000004e-05, "loss": 6.9289, "step": 10 }, { "epoch": 0.004705328784848841, "grad_norm": 0.6077510118484497, "learning_rate": 8.560000000000001e-05, "loss": 6.9322, "step": 20 }, { "epoch": 0.007057993177273262, "grad_norm": 0.5621480941772461, "learning_rate": 0.0001284, "loss": 6.9184, "step": 30 }, { "epoch": 0.009410657569697682, "grad_norm": 0.8597236275672913, "learning_rate": 0.00017120000000000001, "loss": 6.8977, "step": 40 }, { "epoch": 0.011763321962122103, "grad_norm": 0.7145811319351196, "learning_rate": 0.000214, "loss": 6.8562, "step": 50 }, { "epoch": 0.011763321962122103, "eval_loss": 6.864169597625732, "eval_runtime": 3.1888, "eval_samples_per_second": 561.335, "eval_steps_per_second": 140.491, "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": 120141004800.0, "train_batch_size": 4, "trial_name": null, "trial_params": null }