--- license: mit base_model: openai-community/gpt2 tags: - trl - sft - generated_from_trainer metrics: - accuracy model-index: - name: '47015772_3' results: [] --- # 47015772_3 This model is a fine-tuned version of [openai-community/gpt2](https://huggingface.co/openai-community/gpt2) on an unknown dataset. It achieves the following results on the evaluation set: - Loss: 0.6606 - Accuracy: 0.0000 ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 1.41e-05 - train_batch_size: 32 - eval_batch_size: 4 - seed: 42 - distributed_type: multi-GPU - num_devices: 2 - gradient_accumulation_steps: 4 - total_train_batch_size: 256 - total_eval_batch_size: 8 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - training_steps: 2000 ### Training results | Training Loss | Epoch | Step | Validation Loss | Accuracy | |:-------------:|:-----:|:----:|:---------------:|:--------:| | 1.0942 | 0.0 | 25 | 0.9862 | 0.0001 | | 0.8794 | 0.0 | 50 | 0.8269 | 0.0001 | | 0.8241 | 0.0 | 75 | 0.7812 | 0.0001 | | 0.8085 | 0.0 | 100 | 0.7559 | 0.0001 | | 0.78 | 0.0 | 125 | 0.7417 | 0.0001 | | 0.7656 | 0.0 | 150 | 0.7316 | 0.0000 | | 0.759 | 0.0 | 175 | 0.7247 | 0.0000 | | 0.7558 | 0.0 | 200 | 0.7191 | 0.0000 | | 0.7434 | 0.0 | 225 | 0.7143 | 0.0000 | | 0.7419 | 0.0 | 250 | 0.7114 | 0.0000 | | 0.7383 | 0.0 | 275 | 0.7086 | 0.0000 | | 0.7395 | 0.0 | 300 | 0.7051 | 0.0000 | | 0.7324 | 0.0 | 325 | 0.7031 | 0.0000 | | 0.721 | 0.0 | 350 | 0.7008 | 0.0000 | | 0.7279 | 0.0 | 375 | 0.6982 | 0.0000 | | 0.7303 | 0.01 | 400 | 0.6959 | 0.0000 | | 0.7185 | 0.01 | 425 | 0.6932 | 0.0000 | | 0.7221 | 0.01 | 450 | 0.6914 | 0.0000 | | 0.6984 | 0.01 | 475 | 0.6887 | 0.0000 | | 0.7162 | 0.01 | 500 | 0.6875 | 0.0000 | | 0.712 | 0.01 | 525 | 0.6859 | 0.0000 | | 0.7057 | 0.01 | 550 | 0.6848 | 0.0000 | | 0.7058 | 0.01 | 575 | 0.6831 | 0.0000 | | 0.705 | 0.01 | 600 | 0.6820 | 0.0000 | | 0.6941 | 0.01 | 625 | 0.6810 | 0.0000 | | 0.6973 | 0.01 | 650 | 0.6798 | 0.0000 | | 0.7044 | 0.01 | 675 | 0.6784 | 0.0000 | | 0.6943 | 0.01 | 700 | 0.6775 | 0.0000 | | 0.6993 | 0.01 | 725 | 0.6766 | 0.0000 | | 0.698 | 0.01 | 750 | 0.6755 | 0.0000 | | 0.7054 | 0.01 | 775 | 0.6745 | 0.0000 | | 0.693 | 0.01 | 800 | 0.6743 | 0.0000 | | 0.6957 | 0.01 | 825 | 0.6732 | 0.0000 | | 0.7015 | 0.01 | 850 | 0.6725 | 0.0000 | | 0.6878 | 0.01 | 875 | 0.6719 | 0.0000 | | 0.6965 | 0.01 | 900 | 0.6715 | 0.0000 | | 0.6887 | 0.01 | 925 | 0.6712 | 0.0000 | | 0.6945 | 0.01 | 950 | 0.6704 | 0.0000 | | 0.6885 | 0.01 | 975 | 0.6695 | 0.0000 | | 0.6872 | 0.01 | 1000 | 0.6692 | 0.0000 | | 0.6908 | 0.01 | 1025 | 0.6688 | 0.0000 | | 0.6912 | 0.01 | 1050 | 0.6684 | 0.0000 | | 0.6729 | 0.01 | 1075 | 0.6676 | 0.0000 | | 0.6852 | 0.01 | 1100 | 0.6674 | 0.0000 | | 0.6869 | 0.01 | 1125 | 0.6669 | 0.0000 | | 0.6875 | 0.01 | 1150 | 0.6663 | 0.0000 | | 0.6884 | 0.02 | 1175 | 0.6659 | 0.0000 | | 0.6905 | 0.02 | 1200 | 0.6658 | 0.0000 | | 0.6817 | 0.02 | 1225 | 0.6653 | 0.0000 | | 0.6875 | 0.02 | 1250 | 0.6649 | 0.0000 | | 0.6897 | 0.02 | 1275 | 0.6644 | 0.0000 | | 0.6727 | 0.02 | 1300 | 0.6642 | 0.0000 | | 0.6859 | 0.02 | 1325 | 0.6640 | 0.0000 | | 0.6836 | 0.02 | 1350 | 0.6637 | 0.0000 | | 0.6788 | 0.02 | 1375 | 0.6636 | 0.0000 | | 0.6866 | 0.02 | 1400 | 0.6634 | 0.0000 | | 0.6847 | 0.02 | 1425 | 0.6632 | 0.0000 | | 0.6804 | 0.02 | 1450 | 0.6630 | 0.0000 | | 0.6861 | 0.02 | 1475 | 0.6628 | 0.0000 | | 0.6803 | 0.02 | 1500 | 0.6625 | 0.0000 | | 0.6829 | 0.02 | 1525 | 0.6622 | 0.0000 | | 0.6825 | 0.02 | 1550 | 0.6621 | 0.0000 | | 0.6892 | 0.02 | 1575 | 0.6620 | 0.0000 | | 0.6801 | 0.02 | 1600 | 0.6619 | 0.0000 | | 0.6811 | 0.02 | 1625 | 0.6616 | 0.0000 | | 0.6764 | 0.02 | 1650 | 0.6616 | 0.0000 | | 0.6698 | 0.02 | 1675 | 0.6613 | 0.0000 | | 0.6879 | 0.02 | 1700 | 0.6613 | 0.0000 | | 0.6704 | 0.02 | 1725 | 0.6612 | 0.0000 | | 0.6888 | 0.02 | 1750 | 0.6611 | 0.0000 | | 0.6735 | 0.02 | 1775 | 0.6611 | 0.0000 | | 0.6859 | 0.02 | 1800 | 0.6609 | 0.0000 | | 0.6827 | 0.02 | 1825 | 0.6610 | 0.0000 | | 0.6826 | 0.02 | 1850 | 0.6608 | 0.0000 | | 0.6779 | 0.02 | 1875 | 0.6608 | 0.0000 | | 0.6749 | 0.02 | 1900 | 0.6607 | 0.0000 | | 0.6791 | 0.02 | 1925 | 0.6607 | 0.0000 | | 0.6801 | 0.03 | 1950 | 0.6607 | 0.0000 | | 0.6921 | 0.03 | 1975 | 0.6606 | 0.0000 | | 0.6792 | 0.03 | 2000 | 0.6606 | 0.0000 | ### Framework versions - Transformers 4.37.0 - Pytorch 2.0.0+cu118 - Datasets 2.16.1 - Tokenizers 0.15.1