{ "best_metric": 11.5, "best_model_checkpoint": "miner_id_24/checkpoint-10", "epoch": 0.0011228385358185494, "eval_steps": 5, "global_step": 10, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.00011228385358185493, "eval_loss": 11.5, "eval_runtime": 39.7254, "eval_samples_per_second": 94.398, "eval_steps_per_second": 47.199, "step": 1 }, { "epoch": 0.00033685156074556477, "grad_norm": 1.8837872630683705e-05, "learning_rate": 6e-05, "loss": 46.0, "step": 3 }, { "epoch": 0.0005614192679092747, "eval_loss": 11.5, "eval_runtime": 39.8791, "eval_samples_per_second": 94.034, "eval_steps_per_second": 47.017, "step": 5 }, { "epoch": 0.0006737031214911295, "grad_norm": 1.4430891496886034e-05, "learning_rate": 0.00012, "loss": 46.0, "step": 6 }, { "epoch": 0.0010105546822366943, "grad_norm": 1.8416452803649008e-05, "learning_rate": 0.00018, "loss": 46.0, "step": 9 }, { "epoch": 0.0011228385358185494, "eval_loss": 11.5, "eval_runtime": 40.1466, "eval_samples_per_second": 93.408, "eval_steps_per_second": 46.704, "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": 408934907904.0, "train_batch_size": 2, "trial_name": null, "trial_params": null }