{ "best_metric": 1.8087369203567505, "best_model_checkpoint": "miner_id_24/checkpoint-50", "epoch": 0.014210601108426887, "eval_steps": 50, "global_step": 50, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.0002842120221685377, "eval_loss": 2.4652628898620605, "eval_runtime": 82.1891, "eval_samples_per_second": 9.016, "eval_steps_per_second": 2.263, "step": 1 }, { "epoch": 0.002842120221685377, "grad_norm": 2.0982413291931152, "learning_rate": 4.12e-05, "loss": 1.8261, "step": 10 }, { "epoch": 0.005684240443370754, "grad_norm": 4.10166597366333, "learning_rate": 8.24e-05, "loss": 1.4635, "step": 20 }, { "epoch": 0.008526360665056132, "grad_norm": 1.6615333557128906, "learning_rate": 0.0001236, "loss": 1.667, "step": 30 }, { "epoch": 0.011368480886741509, "grad_norm": 1.931045651435852, "learning_rate": 0.0001648, "loss": 1.5695, "step": 40 }, { "epoch": 0.014210601108426887, "grad_norm": 1.6880329847335815, "learning_rate": 0.000206, "loss": 1.8497, "step": 50 }, { "epoch": 0.014210601108426887, "eval_loss": 1.8087369203567505, "eval_runtime": 81.6706, "eval_samples_per_second": 9.073, "eval_steps_per_second": 2.277, "step": 50 } ], "logging_steps": 10, "max_steps": 500, "num_input_tokens_seen": 0, "num_train_epochs": 1, "save_steps": 50, "stateful_callbacks": { "EarlyStoppingCallback": { "args": { "early_stopping_patience": 3, "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": 9325282703966208.0, "train_batch_size": 2, "trial_name": null, "trial_params": null }