{ "best_metric": 10.376873970031738, "best_model_checkpoint": "miner_id_24/checkpoint-10", "epoch": 0.01137009664582149, "eval_steps": 5, "global_step": 10, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.0011370096645821489, "eval_loss": 10.37795639038086, "eval_runtime": 4.5144, "eval_samples_per_second": 164.14, "eval_steps_per_second": 41.201, "step": 1 }, { "epoch": 0.0034110289937464467, "grad_norm": 0.022033361718058586, "learning_rate": 0.00012, "loss": 10.3806, "step": 3 }, { "epoch": 0.005685048322910745, "eval_loss": 10.377598762512207, "eval_runtime": 4.4571, "eval_samples_per_second": 166.253, "eval_steps_per_second": 41.731, "step": 5 }, { "epoch": 0.006822057987492893, "grad_norm": 0.02438768371939659, "learning_rate": 0.0001992114701314478, "loss": 10.3789, "step": 6 }, { "epoch": 0.01023308698123934, "grad_norm": 0.037406694144010544, "learning_rate": 0.00018763066800438636, "loss": 10.3787, "step": 9 }, { "epoch": 0.01137009664582149, "eval_loss": 10.376873970031738, "eval_runtime": 4.5982, "eval_samples_per_second": 161.149, "eval_steps_per_second": 40.45, "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": 536100077568.0, "train_batch_size": 4, "trial_name": null, "trial_params": null }