{ "best_metric": 1.9405193328857422, "best_model_checkpoint": "miner_id_24/checkpoint-10", "epoch": 0.029850746268656716, "eval_steps": 5, "global_step": 10, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.0029850746268656717, "eval_loss": 1.991752028465271, "eval_runtime": 9.8496, "eval_samples_per_second": 14.315, "eval_steps_per_second": 7.208, "step": 1 }, { "epoch": 0.008955223880597015, "grad_norm": 0.3167933523654938, "learning_rate": 0.00012, "loss": 2.0488, "step": 3 }, { "epoch": 0.014925373134328358, "eval_loss": 1.967607855796814, "eval_runtime": 9.858, "eval_samples_per_second": 14.303, "eval_steps_per_second": 7.202, "step": 5 }, { "epoch": 0.01791044776119403, "grad_norm": 0.304219514131546, "learning_rate": 0.0001992114701314478, "loss": 1.965, "step": 6 }, { "epoch": 0.026865671641791045, "grad_norm": 0.31642717123031616, "learning_rate": 0.00018763066800438636, "loss": 1.9491, "step": 9 }, { "epoch": 0.029850746268656716, "eval_loss": 1.9405193328857422, "eval_runtime": 10.1439, "eval_samples_per_second": 13.9, "eval_steps_per_second": 6.999, "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": 1029368772034560.0, "train_batch_size": 2, "trial_name": null, "trial_params": null }