{ "best_metric": 2.325153350830078, "best_model_checkpoint": "miner_id_24/checkpoint-50", "epoch": 0.028425241614553724, "eval_steps": 50, "global_step": 50, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.0005685048322910744, "eval_loss": 2.708378791809082, "eval_runtime": 47.2835, "eval_samples_per_second": 15.671, "eval_steps_per_second": 3.934, "step": 1 }, { "epoch": 0.005685048322910745, "grad_norm": 2.072335958480835, "learning_rate": 4.08e-05, "loss": 2.3259, "step": 10 }, { "epoch": 0.01137009664582149, "grad_norm": 2.634218215942383, "learning_rate": 8.16e-05, "loss": 2.141, "step": 20 }, { "epoch": 0.017055144968732235, "grad_norm": 2.5346333980560303, "learning_rate": 0.0001224, "loss": 1.9537, "step": 30 }, { "epoch": 0.02274019329164298, "grad_norm": 5.2234578132629395, "learning_rate": 0.0001632, "loss": 1.9308, "step": 40 }, { "epoch": 0.028425241614553724, "grad_norm": 28.278820037841797, "learning_rate": 0.000204, "loss": 1.9311, "step": 50 }, { "epoch": 0.028425241614553724, "eval_loss": 2.325153350830078, "eval_runtime": 47.0492, "eval_samples_per_second": 15.749, "eval_steps_per_second": 3.953, "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": 9711056163176448.0, "train_batch_size": 4, "trial_name": null, "trial_params": null }