{ "best_metric": 11.5, "best_model_checkpoint": "miner_id_24/checkpoint-10", "epoch": 0.0008443271767810027, "eval_steps": 5, "global_step": 10, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 8.443271767810026e-05, "eval_loss": 11.5, "eval_runtime": 74.6685, "eval_samples_per_second": 66.789, "eval_steps_per_second": 33.401, "step": 1 }, { "epoch": 0.0002532981530343008, "grad_norm": 7.59916947572492e-05, "learning_rate": 0.00012, "loss": 46.0, "step": 3 }, { "epoch": 0.00042216358839050134, "eval_loss": 11.5, "eval_runtime": 75.3477, "eval_samples_per_second": 66.186, "eval_steps_per_second": 33.1, "step": 5 }, { "epoch": 0.0005065963060686016, "grad_norm": 8.391179289901629e-05, "learning_rate": 0.0001992114701314478, "loss": 46.0, "step": 6 }, { "epoch": 0.0007598944591029024, "grad_norm": 5.544255327549763e-05, "learning_rate": 0.00018763066800438636, "loss": 46.0, "step": 9 }, { "epoch": 0.0008443271767810027, "eval_loss": 11.5, "eval_runtime": 74.9361, "eval_samples_per_second": 66.55, "eval_steps_per_second": 33.282, "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": 678233505792.0, "train_batch_size": 2, "trial_name": null, "trial_params": null }