{ "best_metric": 11.076813697814941, "best_model_checkpoint": "miner_id_24/checkpoint-5", "epoch": 1.1578947368421053, "eval_steps": 5, "global_step": 5, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.21052631578947367, "grad_norm": 3.557851791381836, "learning_rate": 1e-05, "loss": 44.3379, "step": 1 }, { "epoch": 0.21052631578947367, "eval_loss": 11.085034370422363, "eval_runtime": 0.6434, "eval_samples_per_second": 3.109, "eval_steps_per_second": 1.554, "step": 1 }, { "epoch": 0.42105263157894735, "grad_norm": 3.559921979904175, "learning_rate": 2e-05, "loss": 44.3408, "step": 2 }, { "epoch": 0.631578947368421, "grad_norm": 3.5422604084014893, "learning_rate": 3e-05, "loss": 44.3175, "step": 3 }, { "epoch": 0.8421052631578947, "grad_norm": 3.5251545906066895, "learning_rate": 4e-05, "loss": 44.3401, "step": 4 }, { "epoch": 1.1578947368421053, "grad_norm": 3.601130485534668, "learning_rate": 5e-05, "loss": 44.3186, "step": 5 }, { "epoch": 1.1578947368421053, "eval_loss": 11.076813697814941, "eval_runtime": 0.025, "eval_samples_per_second": 79.879, "eval_steps_per_second": 39.939, "step": 5 } ], "logging_steps": 1, "max_steps": 5, "num_input_tokens_seen": 0, "num_train_epochs": 2, "save_steps": 10, "stateful_callbacks": { "EarlyStoppingCallback": { "args": { "early_stopping_patience": 2, "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": true }, "attributes": {} } }, "total_flos": 96448020480.0, "train_batch_size": 2, "trial_name": null, "trial_params": null }