{ "best_metric": 11.5, "best_model_checkpoint": "miner_id_24/checkpoint-10", "epoch": 0.0014116816657843657, "eval_steps": 5, "global_step": 10, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.00014116816657843657, "eval_loss": 11.5, "eval_runtime": 43.8797, "eval_samples_per_second": 67.981, "eval_steps_per_second": 34.002, "step": 1 }, { "epoch": 0.00042350449973530967, "grad_norm": 1.9433709894656204e-05, "learning_rate": 0.00012, "loss": 46.0, "step": 3 }, { "epoch": 0.0007058408328921829, "eval_loss": 11.5, "eval_runtime": 44.5231, "eval_samples_per_second": 66.999, "eval_steps_per_second": 33.511, "step": 5 }, { "epoch": 0.0008470089994706193, "grad_norm": 1.735346631903667e-05, "learning_rate": 0.0001992114701314478, "loss": 46.0, "step": 6 }, { "epoch": 0.001270513499205929, "grad_norm": 3.283464593550889e-06, "learning_rate": 0.00018763066800438636, "loss": 46.0, "step": 9 }, { "epoch": 0.0014116816657843657, "eval_loss": 11.5, "eval_runtime": 44.411, "eval_samples_per_second": 67.168, "eval_steps_per_second": 33.595, "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": 728103616512.0, "train_batch_size": 2, "trial_name": null, "trial_params": null }