{ "best_metric": 0.9860424995422363, "best_model_checkpoint": "miner_id_24/checkpoint-10", "epoch": 0.0017617264919621229, "eval_steps": 5, "global_step": 10, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.0001761726491962123, "eval_loss": 1.2554974555969238, "eval_runtime": 773.1604, "eval_samples_per_second": 3.093, "eval_steps_per_second": 1.547, "step": 1 }, { "epoch": 0.0005285179475886368, "grad_norm": 1.7705259323120117, "learning_rate": 6e-05, "loss": 4.7927, "step": 3 }, { "epoch": 0.0008808632459810614, "eval_loss": 1.1834067106246948, "eval_runtime": 780.6272, "eval_samples_per_second": 3.063, "eval_steps_per_second": 1.532, "step": 5 }, { "epoch": 0.0010570358951772737, "grad_norm": 2.296821117401123, "learning_rate": 9.96057350657239e-05, "loss": 5.1837, "step": 6 }, { "epoch": 0.0015855538427659106, "grad_norm": 1.795020341873169, "learning_rate": 9.381533400219318e-05, "loss": 4.4933, "step": 9 }, { "epoch": 0.0017617264919621229, "eval_loss": 0.9860424995422363, "eval_runtime": 780.0353, "eval_samples_per_second": 3.065, "eval_steps_per_second": 1.533, "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": 1.14344142569472e+16, "train_batch_size": 2, "trial_name": null, "trial_params": null }