Commit
•
aab2dff
1
Parent(s):
7061ea6
bert-squad
Browse files- README.md +208 -0
- config.json +25 -0
- pytorch_model.bin +3 -0
- special_tokens_map.json +7 -0
- tokenizer.json +0 -0
- tokenizer_config.json +57 -0
- training_args.bin +3 -0
- vocab.txt +0 -0
README.md
ADDED
|
@@ -0,0 +1,208 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: mit
|
| 3 |
+
base_model: microsoft/BiomedNLP-PubMedBERT-base-uncased-abstract-fulltext
|
| 4 |
+
tags:
|
| 5 |
+
- generated_from_trainer
|
| 6 |
+
datasets:
|
| 7 |
+
- squad
|
| 8 |
+
model-index:
|
| 9 |
+
- name: bert-squadv2
|
| 10 |
+
results: []
|
| 11 |
+
---
|
| 12 |
+
|
| 13 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 14 |
+
should probably proofread and complete it, then remove this comment. -->
|
| 15 |
+
|
| 16 |
+
# bert-squadv2
|
| 17 |
+
|
| 18 |
+
This model is a fine-tuned version of [microsoft/BiomedNLP-PubMedBERT-base-uncased-abstract-fulltext](https://huggingface.co/microsoft/BiomedNLP-PubMedBERT-base-uncased-abstract-fulltext) on the squad dataset.
|
| 19 |
+
It achieves the following results on the evaluation set:
|
| 20 |
+
- Loss: 1.1930
|
| 21 |
+
|
| 22 |
+
## Model description
|
| 23 |
+
|
| 24 |
+
More information needed
|
| 25 |
+
|
| 26 |
+
## Intended uses & limitations
|
| 27 |
+
|
| 28 |
+
More information needed
|
| 29 |
+
|
| 30 |
+
## Training and evaluation data
|
| 31 |
+
|
| 32 |
+
More information needed
|
| 33 |
+
|
| 34 |
+
## Training procedure
|
| 35 |
+
|
| 36 |
+
### Training hyperparameters
|
| 37 |
+
|
| 38 |
+
The following hyperparameters were used during training:
|
| 39 |
+
- learning_rate: 3e-05
|
| 40 |
+
- train_batch_size: 16
|
| 41 |
+
- eval_batch_size: 16
|
| 42 |
+
- seed: 42
|
| 43 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 44 |
+
- lr_scheduler_type: linear
|
| 45 |
+
- num_epochs: 3
|
| 46 |
+
|
| 47 |
+
### Training results
|
| 48 |
+
|
| 49 |
+
| Training Loss | Epoch | Step | Validation Loss |
|
| 50 |
+
|:-------------:|:-----:|:----:|:---------------:|
|
| 51 |
+
| 5.9623 | 0.02 | 5 | 5.8084 |
|
| 52 |
+
| 5.6934 | 0.04 | 10 | 5.4377 |
|
| 53 |
+
| 5.2457 | 0.06 | 15 | 4.8548 |
|
| 54 |
+
| 4.5796 | 0.08 | 20 | 4.2851 |
|
| 55 |
+
| 4.1507 | 0.1 | 25 | 3.9911 |
|
| 56 |
+
| 4.1134 | 0.12 | 30 | 3.7444 |
|
| 57 |
+
| 3.8076 | 0.14 | 35 | 3.5019 |
|
| 58 |
+
| 3.8445 | 0.16 | 40 | 3.0715 |
|
| 59 |
+
| 3.0969 | 0.18 | 45 | 2.6475 |
|
| 60 |
+
| 2.8899 | 0.2 | 50 | 2.5662 |
|
| 61 |
+
| 2.8354 | 0.22 | 55 | 2.3382 |
|
| 62 |
+
| 3.1775 | 0.24 | 60 | 2.2028 |
|
| 63 |
+
| 2.3935 | 0.26 | 65 | 2.2038 |
|
| 64 |
+
| 2.3994 | 0.28 | 70 | 1.9708 |
|
| 65 |
+
| 2.2664 | 0.3 | 75 | 1.9092 |
|
| 66 |
+
| 1.8134 | 0.32 | 80 | 1.9546 |
|
| 67 |
+
| 2.1905 | 0.34 | 85 | 1.8623 |
|
| 68 |
+
| 2.3941 | 0.36 | 90 | 1.7622 |
|
| 69 |
+
| 1.8807 | 0.38 | 95 | 1.7976 |
|
| 70 |
+
| 2.3562 | 0.4 | 100 | 1.7311 |
|
| 71 |
+
| 2.1116 | 0.42 | 105 | 1.6848 |
|
| 72 |
+
| 1.8022 | 0.44 | 110 | 1.6636 |
|
| 73 |
+
| 2.0378 | 0.46 | 115 | 1.6401 |
|
| 74 |
+
| 1.7313 | 0.48 | 120 | 1.6013 |
|
| 75 |
+
| 1.9304 | 0.5 | 125 | 1.5312 |
|
| 76 |
+
| 1.7668 | 0.52 | 130 | 1.4995 |
|
| 77 |
+
| 1.908 | 0.54 | 135 | 1.5222 |
|
| 78 |
+
| 1.9348 | 0.56 | 140 | 1.5180 |
|
| 79 |
+
| 1.7307 | 0.58 | 145 | 1.4694 |
|
| 80 |
+
| 1.9088 | 0.6 | 150 | 1.4597 |
|
| 81 |
+
| 1.3283 | 0.62 | 155 | 1.4631 |
|
| 82 |
+
| 1.6898 | 0.64 | 160 | 1.4715 |
|
| 83 |
+
| 1.7079 | 0.66 | 165 | 1.4565 |
|
| 84 |
+
| 1.6261 | 0.68 | 170 | 1.4246 |
|
| 85 |
+
| 1.5628 | 0.7 | 175 | 1.4248 |
|
| 86 |
+
| 1.7642 | 0.72 | 180 | 1.4261 |
|
| 87 |
+
| 1.5168 | 0.74 | 185 | 1.4088 |
|
| 88 |
+
| 1.5967 | 0.76 | 190 | 1.4028 |
|
| 89 |
+
| 1.275 | 0.78 | 195 | 1.4294 |
|
| 90 |
+
| 1.596 | 0.8 | 200 | 1.4128 |
|
| 91 |
+
| 1.5765 | 0.82 | 205 | 1.4032 |
|
| 92 |
+
| 1.6554 | 0.84 | 210 | 1.3599 |
|
| 93 |
+
| 1.785 | 0.86 | 215 | 1.3221 |
|
| 94 |
+
| 1.4147 | 0.88 | 220 | 1.3299 |
|
| 95 |
+
| 1.4364 | 0.9 | 225 | 1.3510 |
|
| 96 |
+
| 1.6059 | 0.92 | 230 | 1.2959 |
|
| 97 |
+
| 1.305 | 0.94 | 235 | 1.2871 |
|
| 98 |
+
| 1.4614 | 0.96 | 240 | 1.2986 |
|
| 99 |
+
| 1.3531 | 0.98 | 245 | 1.3891 |
|
| 100 |
+
| 1.3192 | 1.0 | 250 | 1.3526 |
|
| 101 |
+
| 1.0726 | 1.02 | 255 | 1.3378 |
|
| 102 |
+
| 1.1724 | 1.04 | 260 | 1.3207 |
|
| 103 |
+
| 1.2818 | 1.06 | 265 | 1.3034 |
|
| 104 |
+
| 1.1 | 1.08 | 270 | 1.2991 |
|
| 105 |
+
| 1.0719 | 1.1 | 275 | 1.2799 |
|
| 106 |
+
| 1.231 | 1.12 | 280 | 1.2880 |
|
| 107 |
+
| 1.3378 | 1.14 | 285 | 1.3066 |
|
| 108 |
+
| 1.0818 | 1.16 | 290 | 1.2954 |
|
| 109 |
+
| 1.0873 | 1.18 | 295 | 1.2754 |
|
| 110 |
+
| 1.1567 | 1.2 | 300 | 1.2741 |
|
| 111 |
+
| 1.1031 | 1.22 | 305 | 1.2502 |
|
| 112 |
+
| 1.1391 | 1.24 | 310 | 1.2674 |
|
| 113 |
+
| 1.2142 | 1.26 | 315 | 1.2849 |
|
| 114 |
+
| 0.9893 | 1.28 | 320 | 1.2841 |
|
| 115 |
+
| 1.0846 | 1.3 | 325 | 1.2748 |
|
| 116 |
+
| 1.2535 | 1.32 | 330 | 1.2628 |
|
| 117 |
+
| 1.1309 | 1.34 | 335 | 1.2410 |
|
| 118 |
+
| 0.9969 | 1.36 | 340 | 1.2267 |
|
| 119 |
+
| 1.0932 | 1.38 | 345 | 1.2032 |
|
| 120 |
+
| 1.4972 | 1.4 | 350 | 1.1923 |
|
| 121 |
+
| 0.9547 | 1.42 | 355 | 1.1954 |
|
| 122 |
+
| 1.1322 | 1.44 | 360 | 1.2043 |
|
| 123 |
+
| 0.8833 | 1.46 | 365 | 1.2234 |
|
| 124 |
+
| 0.7986 | 1.48 | 370 | 1.2600 |
|
| 125 |
+
| 1.1929 | 1.5 | 375 | 1.2788 |
|
| 126 |
+
| 0.9585 | 1.52 | 380 | 1.2554 |
|
| 127 |
+
| 1.3862 | 1.54 | 385 | 1.2165 |
|
| 128 |
+
| 1.1168 | 1.56 | 390 | 1.2064 |
|
| 129 |
+
| 1.135 | 1.58 | 395 | 1.1976 |
|
| 130 |
+
| 0.8741 | 1.6 | 400 | 1.1933 |
|
| 131 |
+
| 1.3593 | 1.62 | 405 | 1.1857 |
|
| 132 |
+
| 1.0084 | 1.64 | 410 | 1.1851 |
|
| 133 |
+
| 0.9579 | 1.66 | 415 | 1.1728 |
|
| 134 |
+
| 0.9541 | 1.68 | 420 | 1.1721 |
|
| 135 |
+
| 1.2569 | 1.7 | 425 | 1.1773 |
|
| 136 |
+
| 1.0629 | 1.72 | 430 | 1.1717 |
|
| 137 |
+
| 1.1233 | 1.74 | 435 | 1.1671 |
|
| 138 |
+
| 0.8304 | 1.76 | 440 | 1.1742 |
|
| 139 |
+
| 0.8097 | 1.78 | 445 | 1.1861 |
|
| 140 |
+
| 0.9703 | 1.8 | 450 | 1.1822 |
|
| 141 |
+
| 1.1413 | 1.82 | 455 | 1.1909 |
|
| 142 |
+
| 1.0977 | 1.84 | 460 | 1.1938 |
|
| 143 |
+
| 1.0375 | 1.86 | 465 | 1.1839 |
|
| 144 |
+
| 1.0726 | 1.88 | 470 | 1.1871 |
|
| 145 |
+
| 1.1322 | 1.9 | 475 | 1.2020 |
|
| 146 |
+
| 1.0286 | 1.92 | 480 | 1.2004 |
|
| 147 |
+
| 0.9395 | 1.94 | 485 | 1.1981 |
|
| 148 |
+
| 1.059 | 1.96 | 490 | 1.1772 |
|
| 149 |
+
| 1.0722 | 1.98 | 495 | 1.1568 |
|
| 150 |
+
| 0.8618 | 2.0 | 500 | 1.1475 |
|
| 151 |
+
| 0.9305 | 2.02 | 505 | 1.1554 |
|
| 152 |
+
| 0.8525 | 2.04 | 510 | 1.1740 |
|
| 153 |
+
| 1.0687 | 2.06 | 515 | 1.1759 |
|
| 154 |
+
| 0.8899 | 2.08 | 520 | 1.1647 |
|
| 155 |
+
| 0.6881 | 2.1 | 525 | 1.1755 |
|
| 156 |
+
| 0.8582 | 2.12 | 530 | 1.1920 |
|
| 157 |
+
| 0.6645 | 2.14 | 535 | 1.1952 |
|
| 158 |
+
| 0.6028 | 2.16 | 540 | 1.2121 |
|
| 159 |
+
| 0.7364 | 2.18 | 545 | 1.2169 |
|
| 160 |
+
| 0.5562 | 2.2 | 550 | 1.2278 |
|
| 161 |
+
| 0.6175 | 2.22 | 555 | 1.2413 |
|
| 162 |
+
| 0.5392 | 2.24 | 560 | 1.2466 |
|
| 163 |
+
| 0.8727 | 2.26 | 565 | 1.2362 |
|
| 164 |
+
| 0.6778 | 2.28 | 570 | 1.2253 |
|
| 165 |
+
| 0.685 | 2.3 | 575 | 1.2254 |
|
| 166 |
+
| 0.8991 | 2.32 | 580 | 1.2181 |
|
| 167 |
+
| 1.0157 | 2.34 | 585 | 1.2044 |
|
| 168 |
+
| 0.5054 | 2.36 | 590 | 1.1943 |
|
| 169 |
+
| 0.8036 | 2.38 | 595 | 1.1950 |
|
| 170 |
+
| 0.6207 | 2.4 | 600 | 1.2025 |
|
| 171 |
+
| 0.6828 | 2.42 | 605 | 1.2178 |
|
| 172 |
+
| 0.8008 | 2.44 | 610 | 1.2312 |
|
| 173 |
+
| 0.739 | 2.46 | 615 | 1.2401 |
|
| 174 |
+
| 0.5479 | 2.48 | 620 | 1.2459 |
|
| 175 |
+
| 0.9443 | 2.5 | 625 | 1.2359 |
|
| 176 |
+
| 0.7468 | 2.52 | 630 | 1.2264 |
|
| 177 |
+
| 0.6803 | 2.54 | 635 | 1.2223 |
|
| 178 |
+
| 0.8997 | 2.56 | 640 | 1.2208 |
|
| 179 |
+
| 0.7044 | 2.58 | 645 | 1.2118 |
|
| 180 |
+
| 0.707 | 2.6 | 650 | 1.2076 |
|
| 181 |
+
| 0.7813 | 2.62 | 655 | 1.2072 |
|
| 182 |
+
| 0.6376 | 2.64 | 660 | 1.2122 |
|
| 183 |
+
| 0.8885 | 2.66 | 665 | 1.2141 |
|
| 184 |
+
| 0.7359 | 2.68 | 670 | 1.2121 |
|
| 185 |
+
| 0.6928 | 2.7 | 675 | 1.2113 |
|
| 186 |
+
| 0.7706 | 2.72 | 680 | 1.2082 |
|
| 187 |
+
| 0.884 | 2.74 | 685 | 1.2033 |
|
| 188 |
+
| 0.6362 | 2.76 | 690 | 1.1991 |
|
| 189 |
+
| 0.8517 | 2.78 | 695 | 1.1959 |
|
| 190 |
+
| 0.7713 | 2.8 | 700 | 1.1954 |
|
| 191 |
+
| 0.8654 | 2.82 | 705 | 1.1945 |
|
| 192 |
+
| 0.6268 | 2.84 | 710 | 1.1923 |
|
| 193 |
+
| 0.8246 | 2.86 | 715 | 1.1919 |
|
| 194 |
+
| 0.646 | 2.88 | 720 | 1.1920 |
|
| 195 |
+
| 0.8648 | 2.9 | 725 | 1.1922 |
|
| 196 |
+
| 0.8398 | 2.92 | 730 | 1.1928 |
|
| 197 |
+
| 0.6281 | 2.94 | 735 | 1.1931 |
|
| 198 |
+
| 0.6319 | 2.96 | 740 | 1.1927 |
|
| 199 |
+
| 0.6304 | 2.98 | 745 | 1.1932 |
|
| 200 |
+
| 0.6554 | 3.0 | 750 | 1.1930 |
|
| 201 |
+
|
| 202 |
+
|
| 203 |
+
### Framework versions
|
| 204 |
+
|
| 205 |
+
- Transformers 4.34.1
|
| 206 |
+
- Pytorch 2.1.0+cu118
|
| 207 |
+
- Datasets 2.14.5
|
| 208 |
+
- Tokenizers 0.14.1
|
config.json
ADDED
|
@@ -0,0 +1,25 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "microsoft/BiomedNLP-PubMedBERT-base-uncased-abstract-fulltext",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"BertForQuestionAnswering"
|
| 5 |
+
],
|
| 6 |
+
"attention_probs_dropout_prob": 0.1,
|
| 7 |
+
"classifier_dropout": null,
|
| 8 |
+
"hidden_act": "gelu",
|
| 9 |
+
"hidden_dropout_prob": 0.1,
|
| 10 |
+
"hidden_size": 768,
|
| 11 |
+
"initializer_range": 0.02,
|
| 12 |
+
"intermediate_size": 3072,
|
| 13 |
+
"layer_norm_eps": 1e-12,
|
| 14 |
+
"max_position_embeddings": 512,
|
| 15 |
+
"model_type": "bert",
|
| 16 |
+
"num_attention_heads": 12,
|
| 17 |
+
"num_hidden_layers": 12,
|
| 18 |
+
"pad_token_id": 0,
|
| 19 |
+
"position_embedding_type": "absolute",
|
| 20 |
+
"torch_dtype": "float32",
|
| 21 |
+
"transformers_version": "4.34.1",
|
| 22 |
+
"type_vocab_size": 2,
|
| 23 |
+
"use_cache": true,
|
| 24 |
+
"vocab_size": 30522
|
| 25 |
+
}
|
pytorch_model.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:73b4ff493bf402aa1dc0dce39c0676315521caa4a46127ee4f4bbee80dc63248
|
| 3 |
+
size 435640934
|
special_tokens_map.json
ADDED
|
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"cls_token": "[CLS]",
|
| 3 |
+
"mask_token": "[MASK]",
|
| 4 |
+
"pad_token": "[PAD]",
|
| 5 |
+
"sep_token": "[SEP]",
|
| 6 |
+
"unk_token": "[UNK]"
|
| 7 |
+
}
|
tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,57 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"added_tokens_decoder": {
|
| 3 |
+
"0": {
|
| 4 |
+
"content": "[PAD]",
|
| 5 |
+
"lstrip": false,
|
| 6 |
+
"normalized": false,
|
| 7 |
+
"rstrip": false,
|
| 8 |
+
"single_word": false,
|
| 9 |
+
"special": true
|
| 10 |
+
},
|
| 11 |
+
"1": {
|
| 12 |
+
"content": "[UNK]",
|
| 13 |
+
"lstrip": false,
|
| 14 |
+
"normalized": false,
|
| 15 |
+
"rstrip": false,
|
| 16 |
+
"single_word": false,
|
| 17 |
+
"special": true
|
| 18 |
+
},
|
| 19 |
+
"2": {
|
| 20 |
+
"content": "[CLS]",
|
| 21 |
+
"lstrip": false,
|
| 22 |
+
"normalized": false,
|
| 23 |
+
"rstrip": false,
|
| 24 |
+
"single_word": false,
|
| 25 |
+
"special": true
|
| 26 |
+
},
|
| 27 |
+
"3": {
|
| 28 |
+
"content": "[SEP]",
|
| 29 |
+
"lstrip": false,
|
| 30 |
+
"normalized": false,
|
| 31 |
+
"rstrip": false,
|
| 32 |
+
"single_word": false,
|
| 33 |
+
"special": true
|
| 34 |
+
},
|
| 35 |
+
"4": {
|
| 36 |
+
"content": "[MASK]",
|
| 37 |
+
"lstrip": false,
|
| 38 |
+
"normalized": false,
|
| 39 |
+
"rstrip": false,
|
| 40 |
+
"single_word": false,
|
| 41 |
+
"special": true
|
| 42 |
+
}
|
| 43 |
+
},
|
| 44 |
+
"clean_up_tokenization_spaces": true,
|
| 45 |
+
"cls_token": "[CLS]",
|
| 46 |
+
"do_basic_tokenize": true,
|
| 47 |
+
"do_lower_case": true,
|
| 48 |
+
"mask_token": "[MASK]",
|
| 49 |
+
"model_max_length": 1000000000000000019884624838656,
|
| 50 |
+
"never_split": null,
|
| 51 |
+
"pad_token": "[PAD]",
|
| 52 |
+
"sep_token": "[SEP]",
|
| 53 |
+
"strip_accents": null,
|
| 54 |
+
"tokenize_chinese_chars": true,
|
| 55 |
+
"tokenizer_class": "BertTokenizer",
|
| 56 |
+
"unk_token": "[UNK]"
|
| 57 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:0ac14c51a08af4744d839adcf6df410d7af5cfa1ea11e37d5b5aed558837bff8
|
| 3 |
+
size 4536
|
vocab.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|