{ "best_metric": 11.922587394714355, "best_model_checkpoint": "miner_id_24/checkpoint-50", "epoch": 0.011757789535567314, "eval_steps": 50, "global_step": 50, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.00023515579071134627, "eval_loss": 11.93261432647705, "eval_runtime": 6.8929, "eval_samples_per_second": 259.831, "eval_steps_per_second": 64.994, "step": 1 }, { "epoch": 0.0023515579071134627, "grad_norm": 0.02188640646636486, "learning_rate": 4.36e-05, "loss": 11.9324, "step": 10 }, { "epoch": 0.004703115814226925, "grad_norm": 0.02135710045695305, "learning_rate": 8.72e-05, "loss": 11.9322, "step": 20 }, { "epoch": 0.007054673721340388, "grad_norm": 0.046854469925165176, "learning_rate": 0.0001308, "loss": 11.9319, "step": 30 }, { "epoch": 0.00940623162845385, "grad_norm": 0.07760409265756607, "learning_rate": 0.0001744, "loss": 11.9297, "step": 40 }, { "epoch": 0.011757789535567314, "grad_norm": 0.29217442870140076, "learning_rate": 0.000218, "loss": 11.9241, "step": 50 }, { "epoch": 0.011757789535567314, "eval_loss": 11.922587394714355, "eval_runtime": 7.1316, "eval_samples_per_second": 251.135, "eval_steps_per_second": 62.819, "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": 45797867520.0, "train_batch_size": 4, "trial_name": null, "trial_params": null }