--- license: cc-by-4.0 base_model: distilbert-base-cased language: - vi tags: - generated_from_trainer model-index: - name: distilbert-base-vietnamese-case results: [] widget: - text: Đà Nẵng là một thành [MASK] example_title: Example 1 - text: 'Chí Phèo là một nhân [MASK] hư cấu ' example_title: Example 2 --- # distilbert-base-vietnamese-case This model is a fine-tuned version of [distilbert-base-cased](https://huggingface.co/distilbert-base-cased) on an unknown dataset. It achieves the following results on the evaluation set: - Loss: 3.9239 ## 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: 2e-05 - train_batch_size: 64 - eval_batch_size: 64 - seed: 42 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - num_epochs: 100 ### Training results | Training Loss | Epoch | Step | Validation Loss | |:-------------:|:-----:|:----:|:---------------:| | 6.1273 | 1.0 | 79 | 6.0333 | | 5.9095 | 2.0 | 158 | 5.9172 | | 5.8407 | 3.0 | 237 | 5.7789 | | 5.7761 | 4.0 | 316 | 5.6779 | | 5.6909 | 5.0 | 395 | 5.6731 | | 5.6318 | 6.0 | 474 | 5.5712 | | 5.5787 | 7.0 | 553 | 5.4994 | | 5.4948 | 8.0 | 632 | 5.4146 | | 5.4399 | 9.0 | 711 | 5.3760 | | 5.3676 | 10.0 | 790 | 5.3624 | | 5.3691 | 11.0 | 869 | 5.2900 | | 5.2904 | 12.0 | 948 | 5.3213 | | 5.228 | 13.0 | 1027 | 5.2162 | | 5.2384 | 14.0 | 1106 | 5.2232 | | 5.1101 | 15.0 | 1185 | 5.1858 | | 5.1316 | 16.0 | 1264 | 4.9780 | | 5.0517 | 17.0 | 1343 | 5.0227 | | 5.0014 | 18.0 | 1422 | 4.9703 | | 5.0012 | 19.0 | 1501 | 4.9751 | | 4.9574 | 20.0 | 1580 | 4.9152 | | 4.8492 | 21.0 | 1659 | 4.8699 | | 4.8717 | 22.0 | 1738 | 4.8291 | | 4.8014 | 23.0 | 1817 | 4.8247 | | 4.7941 | 24.0 | 1896 | 4.7314 | | 4.7218 | 25.0 | 1975 | 4.8128 | | 4.6991 | 26.0 | 2054 | 4.7312 | | 4.695 | 27.0 | 2133 | 4.6820 | | 4.6339 | 28.0 | 2212 | 4.6659 | | 4.5968 | 29.0 | 2291 | 4.6682 | | 4.581 | 30.0 | 2370 | 4.5671 | | 4.5606 | 31.0 | 2449 | 4.5874 | | 4.4842 | 32.0 | 2528 | 4.4972 | | 4.5101 | 33.0 | 2607 | 4.5457 | | 4.4482 | 34.0 | 2686 | 4.4926 | | 4.4563 | 35.0 | 2765 | 4.4372 | | 4.4161 | 36.0 | 2844 | 4.3623 | | 4.3537 | 37.0 | 2923 | 4.4122 | | 4.3775 | 38.0 | 3002 | 4.3519 | | 4.3519 | 39.0 | 3081 | 4.3866 | | 4.3392 | 40.0 | 3160 | 4.3779 | | 4.3011 | 41.0 | 3239 | 4.3855 | | 4.2702 | 42.0 | 3318 | 4.2953 | | 4.2614 | 43.0 | 3397 | 4.3726 | | 4.2464 | 44.0 | 3476 | 4.3147 | | 4.1984 | 45.0 | 3555 | 4.2556 | | 4.2463 | 46.0 | 3634 | 4.2224 | | 4.1559 | 47.0 | 3713 | 4.1839 | | 4.1859 | 48.0 | 3792 | 4.2830 | | 4.1063 | 49.0 | 3871 | 4.1803 | | 4.1222 | 50.0 | 3950 | 4.1545 | | 4.1423 | 51.0 | 4029 | 4.2308 | | 4.0657 | 52.0 | 4108 | 4.1227 | | 4.1018 | 53.0 | 4187 | 4.1687 | | 4.0689 | 54.0 | 4266 | 4.1626 | | 4.0676 | 55.0 | 4345 | 4.1790 | | 4.0127 | 56.0 | 4424 | 4.0618 | | 4.066 | 57.0 | 4503 | 4.0780 | | 3.9994 | 58.0 | 4582 | 4.1382 | | 4.0002 | 59.0 | 4661 | 4.0318 | | 4.0064 | 60.0 | 4740 | 4.0891 | | 3.9681 | 61.0 | 4819 | 4.0633 | | 3.9608 | 62.0 | 4898 | 4.0223 | | 3.9544 | 63.0 | 4977 | 4.0722 | | 3.97 | 64.0 | 5056 | 4.0127 | | 3.913 | 65.0 | 5135 | 3.9915 | | 3.9177 | 66.0 | 5214 | 4.0256 | | 3.9388 | 67.0 | 5293 | 3.9830 | | 3.9429 | 68.0 | 5372 | 4.0162 | | 3.9036 | 69.0 | 5451 | 4.0515 | | 3.8851 | 70.0 | 5530 | 3.9716 | | 3.8894 | 71.0 | 5609 | 3.9939 | | 3.896 | 72.0 | 5688 | 3.9699 | | 3.8893 | 73.0 | 5767 | 3.9772 | | 3.8648 | 74.0 | 5846 | 4.0543 | | 3.8511 | 75.0 | 5925 | 3.9879 | | 3.8286 | 76.0 | 6004 | 3.9393 | | 3.851 | 77.0 | 6083 | 4.0088 | | 3.8407 | 78.0 | 6162 | 3.9580 | | 3.8391 | 79.0 | 6241 | 3.9453 | | 3.8537 | 80.0 | 6320 | 3.9377 | | 3.823 | 81.0 | 6399 | 3.9423 | | 3.8395 | 82.0 | 6478 | 3.9240 | | 3.7859 | 83.0 | 6557 | 3.8921 | | 3.8177 | 84.0 | 6636 | 3.9167 | | 3.7862 | 85.0 | 6715 | 3.9479 | | 3.7978 | 86.0 | 6794 | 3.9230 | | 3.7939 | 87.0 | 6873 | 3.9401 | | 3.8006 | 88.0 | 6952 | 3.9525 | | 3.7697 | 89.0 | 7031 | 3.9304 | | 3.7914 | 90.0 | 7110 | 3.8875 | | 3.7799 | 91.0 | 7189 | 3.8851 | | 3.812 | 92.0 | 7268 | 3.9349 | | 3.7942 | 93.0 | 7347 | 3.8931 | | 3.7671 | 94.0 | 7426 | 3.8653 | | 3.7654 | 95.0 | 7505 | 3.8282 | | 3.7648 | 96.0 | 7584 | 3.8408 | | 3.8011 | 97.0 | 7663 | 3.8898 | | 3.7781 | 98.0 | 7742 | 3.9560 | | 3.8056 | 99.0 | 7821 | 3.8882 | | 3.7749 | 100.0 | 7900 | 3.9239 | ### Framework versions - Transformers 4.33.2 - Pytorch 2.0.1+cu118 - Datasets 2.14.5 - Tokenizers 0.13.3