--- license: apache-2.0 base_model: bert-base-uncased tags: - generated_from_trainer metrics: - accuracy model-index: - name: best_model-sst-2-16-13 results: [] --- # best_model-sst-2-16-13 This model is a fine-tuned version of [bert-base-uncased](https://huggingface.co./bert-base-uncased) on an unknown dataset. It achieves the following results on the evaluation set: - Loss: 0.6847 - Accuracy: 0.625 ## 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: 1e-05 - train_batch_size: 32 - eval_batch_size: 32 - seed: 42 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - lr_scheduler_warmup_steps: 500 - num_epochs: 150 ### Training results | Training Loss | Epoch | Step | Validation Loss | Accuracy | |:-------------:|:-----:|:----:|:---------------:|:--------:| | No log | 1.0 | 1 | 0.6990 | 0.5 | | No log | 2.0 | 2 | 0.6990 | 0.5 | | No log | 3.0 | 3 | 0.6990 | 0.5 | | No log | 4.0 | 4 | 0.6989 | 0.5 | | No log | 5.0 | 5 | 0.6989 | 0.5 | | No log | 6.0 | 6 | 0.6988 | 0.5 | | No log | 7.0 | 7 | 0.6987 | 0.5 | | No log | 8.0 | 8 | 0.6986 | 0.5 | | No log | 9.0 | 9 | 0.6985 | 0.5 | | 0.6966 | 10.0 | 10 | 0.6984 | 0.5 | | 0.6966 | 11.0 | 11 | 0.6982 | 0.5 | | 0.6966 | 12.0 | 12 | 0.6980 | 0.5 | | 0.6966 | 13.0 | 13 | 0.6979 | 0.5 | | 0.6966 | 14.0 | 14 | 0.6977 | 0.5 | | 0.6966 | 15.0 | 15 | 0.6974 | 0.5 | | 0.6966 | 16.0 | 16 | 0.6972 | 0.5 | | 0.6966 | 17.0 | 17 | 0.6969 | 0.5 | | 0.6966 | 18.0 | 18 | 0.6967 | 0.5 | | 0.6966 | 19.0 | 19 | 0.6964 | 0.5 | | 0.6896 | 20.0 | 20 | 0.6961 | 0.5 | | 0.6896 | 21.0 | 21 | 0.6958 | 0.5 | | 0.6896 | 22.0 | 22 | 0.6955 | 0.5 | | 0.6896 | 23.0 | 23 | 0.6951 | 0.5 | | 0.6896 | 24.0 | 24 | 0.6947 | 0.5 | | 0.6896 | 25.0 | 25 | 0.6944 | 0.5 | | 0.6896 | 26.0 | 26 | 0.6940 | 0.5 | | 0.6896 | 27.0 | 27 | 0.6936 | 0.5 | | 0.6896 | 28.0 | 28 | 0.6932 | 0.5 | | 0.6896 | 29.0 | 29 | 0.6928 | 0.5 | | 0.6844 | 30.0 | 30 | 0.6924 | 0.5 | | 0.6844 | 31.0 | 31 | 0.6920 | 0.5 | | 0.6844 | 32.0 | 32 | 0.6916 | 0.5 | | 0.6844 | 33.0 | 33 | 0.6912 | 0.5 | | 0.6844 | 34.0 | 34 | 0.6908 | 0.5 | | 0.6844 | 35.0 | 35 | 0.6904 | 0.5 | | 0.6844 | 36.0 | 36 | 0.6900 | 0.5 | | 0.6844 | 37.0 | 37 | 0.6896 | 0.5 | | 0.6844 | 38.0 | 38 | 0.6892 | 0.5 | | 0.6844 | 39.0 | 39 | 0.6887 | 0.5 | | 0.6747 | 40.0 | 40 | 0.6883 | 0.5 | | 0.6747 | 41.0 | 41 | 0.6879 | 0.5 | | 0.6747 | 42.0 | 42 | 0.6875 | 0.5 | | 0.6747 | 43.0 | 43 | 0.6871 | 0.5 | | 0.6747 | 44.0 | 44 | 0.6867 | 0.5 | | 0.6747 | 45.0 | 45 | 0.6864 | 0.5 | | 0.6747 | 46.0 | 46 | 0.6860 | 0.5 | | 0.6747 | 47.0 | 47 | 0.6856 | 0.5312 | | 0.6747 | 48.0 | 48 | 0.6852 | 0.5625 | | 0.6747 | 49.0 | 49 | 0.6849 | 0.5625 | | 0.6545 | 50.0 | 50 | 0.6845 | 0.5625 | | 0.6545 | 51.0 | 51 | 0.6841 | 0.5625 | | 0.6545 | 52.0 | 52 | 0.6838 | 0.5625 | | 0.6545 | 53.0 | 53 | 0.6834 | 0.5625 | | 0.6545 | 54.0 | 54 | 0.6830 | 0.5625 | | 0.6545 | 55.0 | 55 | 0.6826 | 0.5938 | | 0.6545 | 56.0 | 56 | 0.6823 | 0.5938 | | 0.6545 | 57.0 | 57 | 0.6819 | 0.625 | | 0.6545 | 58.0 | 58 | 0.6815 | 0.6562 | | 0.6545 | 59.0 | 59 | 0.6811 | 0.6562 | | 0.6293 | 60.0 | 60 | 0.6808 | 0.6875 | | 0.6293 | 61.0 | 61 | 0.6806 | 0.7188 | | 0.6293 | 62.0 | 62 | 0.6806 | 0.7188 | | 0.6293 | 63.0 | 63 | 0.6805 | 0.75 | | 0.6293 | 64.0 | 64 | 0.6805 | 0.75 | | 0.6293 | 65.0 | 65 | 0.6804 | 0.75 | | 0.6293 | 66.0 | 66 | 0.6802 | 0.7188 | | 0.6293 | 67.0 | 67 | 0.6799 | 0.7188 | | 0.6293 | 68.0 | 68 | 0.6796 | 0.6875 | | 0.6293 | 69.0 | 69 | 0.6792 | 0.7188 | | 0.5938 | 70.0 | 70 | 0.6789 | 0.6875 | | 0.5938 | 71.0 | 71 | 0.6787 | 0.6875 | | 0.5938 | 72.0 | 72 | 0.6789 | 0.6562 | | 0.5938 | 73.0 | 73 | 0.6797 | 0.6875 | | 0.5938 | 74.0 | 74 | 0.6809 | 0.6875 | | 0.5938 | 75.0 | 75 | 0.6818 | 0.6875 | | 0.5938 | 76.0 | 76 | 0.6819 | 0.6875 | | 0.5938 | 77.0 | 77 | 0.6811 | 0.6875 | | 0.5938 | 78.0 | 78 | 0.6800 | 0.6875 | | 0.5938 | 79.0 | 79 | 0.6790 | 0.6875 | | 0.5521 | 80.0 | 80 | 0.6786 | 0.6875 | | 0.5521 | 81.0 | 81 | 0.6785 | 0.6875 | | 0.5521 | 82.0 | 82 | 0.6783 | 0.6562 | | 0.5521 | 83.0 | 83 | 0.6781 | 0.6562 | | 0.5521 | 84.0 | 84 | 0.6780 | 0.625 | | 0.5521 | 85.0 | 85 | 0.6780 | 0.625 | | 0.5521 | 86.0 | 86 | 0.6781 | 0.625 | | 0.5521 | 87.0 | 87 | 0.6783 | 0.625 | | 0.5521 | 88.0 | 88 | 0.6788 | 0.625 | | 0.5521 | 89.0 | 89 | 0.6793 | 0.625 | | 0.4936 | 90.0 | 90 | 0.6800 | 0.625 | | 0.4936 | 91.0 | 91 | 0.6804 | 0.625 | | 0.4936 | 92.0 | 92 | 0.6797 | 0.625 | | 0.4936 | 93.0 | 93 | 0.6779 | 0.625 | | 0.4936 | 94.0 | 94 | 0.6759 | 0.625 | | 0.4936 | 95.0 | 95 | 0.6745 | 0.625 | | 0.4936 | 96.0 | 96 | 0.6734 | 0.625 | | 0.4936 | 97.0 | 97 | 0.6721 | 0.625 | | 0.4936 | 98.0 | 98 | 0.6711 | 0.625 | | 0.4936 | 99.0 | 99 | 0.6704 | 0.5938 | | 0.4373 | 100.0 | 100 | 0.6697 | 0.5938 | | 0.4373 | 101.0 | 101 | 0.6693 | 0.5625 | | 0.4373 | 102.0 | 102 | 0.6694 | 0.5625 | | 0.4373 | 103.0 | 103 | 0.6701 | 0.5625 | | 0.4373 | 104.0 | 104 | 0.6707 | 0.5625 | | 0.4373 | 105.0 | 105 | 0.6711 | 0.5625 | | 0.4373 | 106.0 | 106 | 0.6716 | 0.5625 | | 0.4373 | 107.0 | 107 | 0.6720 | 0.5625 | | 0.4373 | 108.0 | 108 | 0.6725 | 0.5938 | | 0.4373 | 109.0 | 109 | 0.6731 | 0.5938 | | 0.3728 | 110.0 | 110 | 0.6742 | 0.5938 | | 0.3728 | 111.0 | 111 | 0.6755 | 0.5938 | | 0.3728 | 112.0 | 112 | 0.6773 | 0.5938 | | 0.3728 | 113.0 | 113 | 0.6789 | 0.5938 | | 0.3728 | 114.0 | 114 | 0.6801 | 0.5938 | | 0.3728 | 115.0 | 115 | 0.6809 | 0.5938 | | 0.3728 | 116.0 | 116 | 0.6815 | 0.5938 | | 0.3728 | 117.0 | 117 | 0.6815 | 0.5938 | | 0.3728 | 118.0 | 118 | 0.6811 | 0.5938 | | 0.3728 | 119.0 | 119 | 0.6800 | 0.5938 | | 0.3198 | 120.0 | 120 | 0.6787 | 0.5938 | | 0.3198 | 121.0 | 121 | 0.6775 | 0.625 | | 0.3198 | 122.0 | 122 | 0.6765 | 0.625 | | 0.3198 | 123.0 | 123 | 0.6760 | 0.625 | | 0.3198 | 124.0 | 124 | 0.6758 | 0.625 | | 0.3198 | 125.0 | 125 | 0.6756 | 0.625 | | 0.3198 | 126.0 | 126 | 0.6754 | 0.625 | | 0.3198 | 127.0 | 127 | 0.6754 | 0.625 | | 0.3198 | 128.0 | 128 | 0.6753 | 0.625 | | 0.3198 | 129.0 | 129 | 0.6751 | 0.625 | | 0.2713 | 130.0 | 130 | 0.6750 | 0.625 | | 0.2713 | 131.0 | 131 | 0.6748 | 0.625 | | 0.2713 | 132.0 | 132 | 0.6747 | 0.625 | | 0.2713 | 133.0 | 133 | 0.6747 | 0.625 | | 0.2713 | 134.0 | 134 | 0.6745 | 0.625 | | 0.2713 | 135.0 | 135 | 0.6738 | 0.625 | | 0.2713 | 136.0 | 136 | 0.6731 | 0.625 | | 0.2713 | 137.0 | 137 | 0.6723 | 0.625 | | 0.2713 | 138.0 | 138 | 0.6719 | 0.625 | | 0.2713 | 139.0 | 139 | 0.6717 | 0.625 | | 0.2331 | 140.0 | 140 | 0.6717 | 0.6562 | | 0.2331 | 141.0 | 141 | 0.6719 | 0.6562 | | 0.2331 | 142.0 | 142 | 0.6722 | 0.6562 | | 0.2331 | 143.0 | 143 | 0.6725 | 0.6562 | | 0.2331 | 144.0 | 144 | 0.6732 | 0.6562 | | 0.2331 | 145.0 | 145 | 0.6744 | 0.6562 | | 0.2331 | 146.0 | 146 | 0.6764 | 0.625 | | 0.2331 | 147.0 | 147 | 0.6793 | 0.625 | | 0.2331 | 148.0 | 148 | 0.6816 | 0.625 | | 0.2331 | 149.0 | 149 | 0.6833 | 0.625 | | 0.2017 | 150.0 | 150 | 0.6847 | 0.625 | ### Framework versions - Transformers 4.32.0.dev0 - Pytorch 2.0.1+cu118 - Datasets 2.4.0 - Tokenizers 0.13.3