{ "best_global_step": null, "best_metric": null, "best_model_checkpoint": null, "epoch": 10.0, "eval_steps": 500, "global_step": 70, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 1.4285714285714286, "grad_norm": 1.4685486555099487, "learning_rate": 9.242424242424244e-06, "loss": 0.2565, "step": 10 }, { "epoch": 2.857142857142857, "grad_norm": 2.9761343002319336, "learning_rate": 7.727272727272727e-06, "loss": 0.282, "step": 20 }, { "epoch": 4.285714285714286, "grad_norm": 2.0076684951782227, "learning_rate": 6.212121212121213e-06, "loss": 0.2094, "step": 30 }, { "epoch": 5.714285714285714, "grad_norm": 2.965219259262085, "learning_rate": 4.696969696969698e-06, "loss": 0.2262, "step": 40 }, { "epoch": 7.142857142857143, "grad_norm": 0.9869125485420227, "learning_rate": 3.181818181818182e-06, "loss": 0.2018, "step": 50 }, { "epoch": 8.571428571428571, "grad_norm": 2.1355133056640625, "learning_rate": 1.6666666666666667e-06, "loss": 0.1887, "step": 60 }, { "epoch": 10.0, "grad_norm": 0.18442638218402863, "learning_rate": 1.5151515151515152e-07, "loss": 0.155, "step": 70 }, { "epoch": 10.0, "step": 70, "total_flos": 32797848526848.0, "train_loss": 0.21707289997639756, "train_runtime": 15.5227, "train_samples_per_second": 64.422, "train_steps_per_second": 4.51 } ], "logging_steps": 10, "max_steps": 70, "num_input_tokens_seen": 0, "num_train_epochs": 10, "save_steps": 100, "stateful_callbacks": { "TrainerControl": { "args": { "should_epoch_stop": false, "should_evaluate": false, "should_log": false, "should_save": true, "should_training_stop": true }, "attributes": {} } }, "total_flos": 32797848526848.0, "train_batch_size": 16, "trial_name": null, "trial_params": null }