{ "best_metric": null, "best_model_checkpoint": null, "epoch": 0.0061823802163833074, "eval_steps": 3, "global_step": 10, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.0006182380216383308, "grad_norm": NaN, "learning_rate": 2e-05, "loss": 0.0, "step": 1 }, { "epoch": 0.0006182380216383308, "eval_loss": NaN, "eval_runtime": 21.4658, "eval_samples_per_second": 31.725, "eval_steps_per_second": 15.886, "step": 1 }, { "epoch": 0.0012364760432766616, "grad_norm": NaN, "learning_rate": 4e-05, "loss": 0.0, "step": 2 }, { "epoch": 0.0018547140649149924, "grad_norm": NaN, "learning_rate": 6e-05, "loss": 0.0, "step": 3 }, { "epoch": 0.0018547140649149924, "eval_loss": NaN, "eval_runtime": 20.374, "eval_samples_per_second": 33.425, "eval_steps_per_second": 16.737, "step": 3 }, { "epoch": 0.002472952086553323, "grad_norm": NaN, "learning_rate": 8e-05, "loss": 0.0, "step": 4 }, { "epoch": 0.0030911901081916537, "grad_norm": NaN, "learning_rate": 0.0001, "loss": 0.0, "step": 5 }, { "epoch": 0.0037094281298299847, "grad_norm": NaN, "learning_rate": 0.00012, "loss": 0.0, "step": 6 }, { "epoch": 0.0037094281298299847, "eval_loss": NaN, "eval_runtime": 20.1849, "eval_samples_per_second": 33.738, "eval_steps_per_second": 16.894, "step": 6 }, { "epoch": 0.004327666151468315, "grad_norm": NaN, "learning_rate": 0.00014, "loss": 0.0, "step": 7 }, { "epoch": 0.004945904173106646, "grad_norm": NaN, "learning_rate": 0.00016, "loss": 0.0, "step": 8 }, { "epoch": 0.0055641421947449764, "grad_norm": NaN, "learning_rate": 0.00018, "loss": 0.0, "step": 9 }, { "epoch": 0.0055641421947449764, "eval_loss": NaN, "eval_runtime": 20.1058, "eval_samples_per_second": 33.871, "eval_steps_per_second": 16.96, "step": 9 }, { "epoch": 0.0061823802163833074, "grad_norm": NaN, "learning_rate": 0.0002, "loss": 0.0, "step": 10 } ], "logging_steps": 1, "max_steps": 10, "num_input_tokens_seen": 0, "num_train_epochs": 1, "save_steps": 3, "stateful_callbacks": { "TrainerControl": { "args": { "should_epoch_stop": false, "should_evaluate": false, "should_log": false, "should_save": true, "should_training_stop": true }, "attributes": {} } }, "total_flos": 89038163804160.0, "train_batch_size": 2, "trial_name": null, "trial_params": null }