{ "best_metric": 4.929401397705078, "best_model_checkpoint": "miner_id_24/checkpoint-10", "epoch": 0.00016036820539959748, "eval_steps": 5, "global_step": 10, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 1.6036820539959746e-05, "eval_loss": 5.815370559692383, "eval_runtime": 893.8373, "eval_samples_per_second": 29.374, "eval_steps_per_second": 14.687, "step": 1 }, { "epoch": 4.811046161987924e-05, "grad_norm": 13.024637222290039, "learning_rate": 6e-05, "loss": 23.9765, "step": 3 }, { "epoch": 8.018410269979874e-05, "eval_loss": 5.52920389175415, "eval_runtime": 897.299, "eval_samples_per_second": 29.261, "eval_steps_per_second": 14.631, "step": 5 }, { "epoch": 9.622092323975848e-05, "grad_norm": 11.284300804138184, "learning_rate": 9.96057350657239e-05, "loss": 22.9837, "step": 6 }, { "epoch": 0.00014433138485963774, "grad_norm": 10.9056396484375, "learning_rate": 9.381533400219318e-05, "loss": 20.9837, "step": 9 }, { "epoch": 0.00016036820539959748, "eval_loss": 4.929401397705078, "eval_runtime": 894.1386, "eval_samples_per_second": 29.365, "eval_steps_per_second": 14.682, "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": 151685494210560.0, "train_batch_size": 2, "trial_name": null, "trial_params": null }