{ "best_metric": 1.3284010887145996, "best_model_checkpoint": "miner_id_24/checkpoint-10", "epoch": 0.0017139429257005741, "eval_steps": 5, "global_step": 10, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.0001713942925700574, "eval_loss": 1.3596421480178833, "eval_runtime": 583.9591, "eval_samples_per_second": 4.207, "eval_steps_per_second": 2.105, "step": 1 }, { "epoch": 0.0005141828777101723, "grad_norm": 5.756150722503662, "learning_rate": 6e-05, "loss": 5.3785, "step": 3 }, { "epoch": 0.0008569714628502871, "eval_loss": 1.350292682647705, "eval_runtime": 590.0216, "eval_samples_per_second": 4.164, "eval_steps_per_second": 2.083, "step": 5 }, { "epoch": 0.0010283657554203446, "grad_norm": 3711.65625, "learning_rate": 9.96057350657239e-05, "loss": 4.7408, "step": 6 }, { "epoch": 0.0015425486331305167, "grad_norm": 7608.09375, "learning_rate": 9.381533400219318e-05, "loss": 5.116, "step": 9 }, { "epoch": 0.0017139429257005741, "eval_loss": 1.3284010887145996, "eval_runtime": 587.3458, "eval_samples_per_second": 4.183, "eval_steps_per_second": 2.092, "step": 10 } ], "logging_steps": 3, "max_steps": 30, "num_input_tokens_seen": 0, "num_train_epochs": 1, "save_steps": 10, "stateful_callbacks": { "EarlyStoppingCallback": { "args": { "early_stopping_patience": 1, "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": 6808424939520000.0, "train_batch_size": 2, "trial_name": null, "trial_params": null }