{ "best_metric": 1.2941644191741943, "best_model_checkpoint": "miner_id_24/checkpoint-10", "epoch": 0.0034057045551298426, "eval_steps": 5, "global_step": 10, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.00034057045551298427, "eval_loss": 1.4796533584594727, "eval_runtime": 164.2532, "eval_samples_per_second": 7.531, "eval_steps_per_second": 3.769, "step": 1 }, { "epoch": 0.0010217113665389529, "grad_norm": 0.384747713804245, "learning_rate": 6e-05, "loss": 1.3415, "step": 3 }, { "epoch": 0.0017028522775649213, "eval_loss": 1.4507091045379639, "eval_runtime": 165.8491, "eval_samples_per_second": 7.459, "eval_steps_per_second": 3.732, "step": 5 }, { "epoch": 0.0020434227330779057, "grad_norm": 0.5841999053955078, "learning_rate": 0.00012, "loss": 1.2883, "step": 6 }, { "epoch": 0.0030651340996168583, "grad_norm": 0.470478892326355, "learning_rate": 0.00018, "loss": 1.2974, "step": 9 }, { "epoch": 0.0034057045551298426, "eval_loss": 1.2941644191741943, "eval_runtime": 165.8717, "eval_samples_per_second": 7.458, "eval_steps_per_second": 3.732, "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": 3718654407475200.0, "train_batch_size": 2, "trial_name": null, "trial_params": null }