End of training
Browse files- README.md +134 -0
- config.json +29 -0
- merges.txt +0 -0
- model.safetensors +3 -0
- runs/Jan08_12-14-13_32df0236926e/events.out.tfevents.1736338457.32df0236926e.17827.0 +3 -0
- special_tokens_map.json +51 -0
- tokenizer.json +0 -0
- tokenizer_config.json +58 -0
- training_args.bin +3 -0
- vocab.json +0 -0
README.md
ADDED
@@ -0,0 +1,134 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
library_name: transformers
|
3 |
+
license: mit
|
4 |
+
base_model: w11wo/sundanese-roberta-base
|
5 |
+
tags:
|
6 |
+
- generated_from_trainer
|
7 |
+
model-index:
|
8 |
+
- name: RoBERTa-Base-SE2025T11A-sun-v20250108121357
|
9 |
+
results: []
|
10 |
+
---
|
11 |
+
|
12 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
13 |
+
should probably proofread and complete it, then remove this comment. -->
|
14 |
+
|
15 |
+
# RoBERTa-Base-SE2025T11A-sun-v20250108121357
|
16 |
+
|
17 |
+
This model is a fine-tuned version of [w11wo/sundanese-roberta-base](https://huggingface.co/w11wo/sundanese-roberta-base) on an unknown dataset.
|
18 |
+
It achieves the following results on the evaluation set:
|
19 |
+
- Loss: 0.5533
|
20 |
+
- F1 Macro: 0.5973
|
21 |
+
- F1 Micro: 0.6045
|
22 |
+
- F1 Weighted: 0.6046
|
23 |
+
- F1 Samples: 0.6245
|
24 |
+
- F1 Label Marah: 0.625
|
25 |
+
- F1 Label Jijik: 0.5636
|
26 |
+
- F1 Label Takut: 0.5753
|
27 |
+
- F1 Label Senang: 0.7619
|
28 |
+
- F1 Label Sedih: 0.5926
|
29 |
+
- F1 Label Terkejut: 0.55
|
30 |
+
- F1 Label Biasa: 0.5128
|
31 |
+
|
32 |
+
## Model description
|
33 |
+
|
34 |
+
More information needed
|
35 |
+
|
36 |
+
## Intended uses & limitations
|
37 |
+
|
38 |
+
More information needed
|
39 |
+
|
40 |
+
## Training and evaluation data
|
41 |
+
|
42 |
+
More information needed
|
43 |
+
|
44 |
+
## Training procedure
|
45 |
+
|
46 |
+
### Training hyperparameters
|
47 |
+
|
48 |
+
The following hyperparameters were used during training:
|
49 |
+
- learning_rate: 2e-05
|
50 |
+
- train_batch_size: 2
|
51 |
+
- eval_batch_size: 2
|
52 |
+
- seed: 42
|
53 |
+
- optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
|
54 |
+
- lr_scheduler_type: linear
|
55 |
+
- num_epochs: 12
|
56 |
+
|
57 |
+
### Training results
|
58 |
+
|
59 |
+
| Training Loss | Epoch | Step | Validation Loss | F1 Macro | F1 Micro | F1 Weighted | F1 Samples | F1 Label Marah | F1 Label Jijik | F1 Label Takut | F1 Label Senang | F1 Label Sedih | F1 Label Terkejut | F1 Label Biasa |
|
60 |
+
|:-------------:|:-------:|:----:|:---------------:|:--------:|:--------:|:-----------:|:----------:|:--------------:|:--------------:|:--------------:|:---------------:|:--------------:|:-----------------:|:--------------:|
|
61 |
+
| 0.5025 | 0.1805 | 100 | 0.4545 | 0.0381 | 0.0539 | 0.0497 | 0.0345 | 0.1613 | 0.1053 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 |
|
62 |
+
| 0.4936 | 0.3610 | 200 | 0.4324 | 0.0207 | 0.0210 | 0.0201 | 0.0120 | 0.0 | 0.0 | 0.0541 | 0.0909 | 0.0 | 0.0 | 0.0 |
|
63 |
+
| 0.4201 | 0.5415 | 300 | 0.4170 | 0.1105 | 0.2048 | 0.1136 | 0.1276 | 0.0 | 0.04 | 0.0 | 0.7333 | 0.0 | 0.0 | 0.0 |
|
64 |
+
| 0.4332 | 0.7220 | 400 | 0.3889 | 0.2001 | 0.2926 | 0.2146 | 0.1715 | 0.0357 | 0.2769 | 0.0 | 0.7273 | 0.0 | 0.3611 | 0.0 |
|
65 |
+
| 0.4339 | 0.9025 | 500 | 0.3828 | 0.2424 | 0.3369 | 0.2488 | 0.2523 | 0.1356 | 0.1818 | 0.5312 | 0.7527 | 0.0952 | 0.0 | 0.0 |
|
66 |
+
| 0.3827 | 1.0830 | 600 | 0.3518 | 0.3665 | 0.4320 | 0.3965 | 0.3431 | 0.4578 | 0.3333 | 0.4348 | 0.7209 | 0.4444 | 0.1739 | 0.0 |
|
67 |
+
| 0.3451 | 1.2635 | 700 | 0.3681 | 0.4524 | 0.5236 | 0.4956 | 0.4568 | 0.6 | 0.5225 | 0.5714 | 0.6933 | 0.2979 | 0.4819 | 0.0 |
|
68 |
+
| 0.3225 | 1.4440 | 800 | 0.3451 | 0.4035 | 0.4682 | 0.4333 | 0.3971 | 0.3188 | 0.4752 | 0.3256 | 0.7470 | 0.6032 | 0.3548 | 0.0 |
|
69 |
+
| 0.3338 | 1.6245 | 900 | 0.3223 | 0.5735 | 0.5784 | 0.5640 | 0.5288 | 0.6061 | 0.4103 | 0.6857 | 0.7838 | 0.5747 | 0.3333 | 0.6207 |
|
70 |
+
| 0.331 | 1.8051 | 1000 | 0.3235 | 0.5282 | 0.5470 | 0.5286 | 0.4635 | 0.5238 | 0.2951 | 0.6780 | 0.7381 | 0.5455 | 0.5169 | 0.4 |
|
71 |
+
| 0.3125 | 1.9856 | 1100 | 0.3162 | 0.4996 | 0.5791 | 0.5455 | 0.5502 | 0.6429 | 0.5474 | 0.5882 | 0.8043 | 0.4528 | 0.4615 | 0.0 |
|
72 |
+
| 0.2239 | 2.1661 | 1200 | 0.3253 | 0.5667 | 0.5782 | 0.5781 | 0.5554 | 0.5495 | 0.5660 | 0.6667 | 0.7429 | 0.5574 | 0.5 | 0.3846 |
|
73 |
+
| 0.2407 | 2.3466 | 1300 | 0.3070 | 0.5676 | 0.5909 | 0.5772 | 0.5566 | 0.6122 | 0.4286 | 0.6667 | 0.7692 | 0.5538 | 0.5429 | 0.4 |
|
74 |
+
| 0.2148 | 2.5271 | 1400 | 0.3458 | 0.5629 | 0.5832 | 0.5736 | 0.5659 | 0.5227 | 0.5806 | 0.5660 | 0.7529 | 0.6176 | 0.5 | 0.4 |
|
75 |
+
| 0.2109 | 2.7076 | 1500 | 0.3254 | 0.5491 | 0.5927 | 0.5748 | 0.5659 | 0.6796 | 0.4935 | 0.6441 | 0.7660 | 0.5 | 0.5 | 0.2609 |
|
76 |
+
| 0.2071 | 2.8881 | 1600 | 0.3216 | 0.5920 | 0.6199 | 0.6100 | 0.6095 | 0.7018 | 0.5783 | 0.6984 | 0.7529 | 0.5246 | 0.4878 | 0.4 |
|
77 |
+
| 0.1929 | 3.0686 | 1700 | 0.3337 | 0.6376 | 0.6290 | 0.6314 | 0.6197 | 0.6154 | 0.5714 | 0.6786 | 0.7368 | 0.6197 | 0.5745 | 0.6667 |
|
78 |
+
| 0.1376 | 3.2491 | 1800 | 0.3510 | 0.5930 | 0.5951 | 0.5870 | 0.5896 | 0.6111 | 0.4533 | 0.5946 | 0.7640 | 0.6027 | 0.5 | 0.625 |
|
79 |
+
| 0.1473 | 3.4296 | 1900 | 0.3474 | 0.6150 | 0.6141 | 0.6127 | 0.6006 | 0.6598 | 0.5347 | 0.6545 | 0.7532 | 0.5714 | 0.5 | 0.6316 |
|
80 |
+
| 0.1306 | 3.6101 | 2000 | 0.3705 | 0.6231 | 0.6198 | 0.6188 | 0.6081 | 0.5833 | 0.5263 | 0.675 | 0.7848 | 0.5946 | 0.5918 | 0.6061 |
|
81 |
+
| 0.117 | 3.7906 | 2100 | 0.3618 | 0.6215 | 0.6286 | 0.6228 | 0.6269 | 0.6731 | 0.5393 | 0.7105 | 0.7470 | 0.5397 | 0.5526 | 0.5882 |
|
82 |
+
| 0.1415 | 3.9711 | 2200 | 0.3886 | 0.5939 | 0.5989 | 0.5969 | 0.6149 | 0.6379 | 0.5586 | 0.6102 | 0.7470 | 0.5610 | 0.4789 | 0.5641 |
|
83 |
+
| 0.1264 | 4.1516 | 2300 | 0.3849 | 0.5957 | 0.5989 | 0.5971 | 0.5946 | 0.6195 | 0.5053 | 0.5970 | 0.7529 | 0.6027 | 0.5366 | 0.5556 |
|
84 |
+
| 0.078 | 4.3321 | 2400 | 0.3873 | 0.6163 | 0.6209 | 0.6171 | 0.6173 | 0.6726 | 0.5376 | 0.6133 | 0.7765 | 0.5897 | 0.5135 | 0.6111 |
|
85 |
+
| 0.0778 | 4.5126 | 2500 | 0.4128 | 0.6039 | 0.6071 | 0.6081 | 0.5968 | 0.6286 | 0.5393 | 0.65 | 0.7397 | 0.6377 | 0.5060 | 0.5263 |
|
86 |
+
| 0.104 | 4.6931 | 2600 | 0.4260 | 0.6165 | 0.6209 | 0.6213 | 0.6213 | 0.6471 | 0.5536 | 0.6774 | 0.7640 | 0.6197 | 0.5205 | 0.5333 |
|
87 |
+
| 0.0742 | 4.8736 | 2700 | 0.4473 | 0.5867 | 0.5933 | 0.5910 | 0.5965 | 0.6186 | 0.5273 | 0.6071 | 0.7778 | 0.5758 | 0.4789 | 0.5217 |
|
88 |
+
| 0.0881 | 5.0542 | 2800 | 0.4265 | 0.5941 | 0.6026 | 0.6002 | 0.5946 | 0.6667 | 0.5376 | 0.5882 | 0.7561 | 0.5634 | 0.5063 | 0.5405 |
|
89 |
+
| 0.0615 | 5.2347 | 2900 | 0.4332 | 0.6011 | 0.6100 | 0.6068 | 0.6099 | 0.6667 | 0.5227 | 0.6111 | 0.7529 | 0.5974 | 0.5205 | 0.5366 |
|
90 |
+
| 0.0584 | 5.4152 | 3000 | 0.4341 | 0.6010 | 0.6109 | 0.6097 | 0.6047 | 0.6476 | 0.5684 | 0.5714 | 0.7765 | 0.6 | 0.5316 | 0.5116 |
|
91 |
+
| 0.0566 | 5.5957 | 3100 | 0.4429 | 0.6121 | 0.6157 | 0.6162 | 0.6066 | 0.6667 | 0.5192 | 0.5714 | 0.7765 | 0.6567 | 0.5301 | 0.5641 |
|
92 |
+
| 0.059 | 5.7762 | 3200 | 0.4577 | 0.5922 | 0.5945 | 0.5944 | 0.5884 | 0.6471 | 0.5208 | 0.5455 | 0.7654 | 0.6 | 0.4878 | 0.5789 |
|
93 |
+
| 0.0478 | 5.9567 | 3300 | 0.4585 | 0.6026 | 0.6018 | 0.6038 | 0.6044 | 0.6364 | 0.5234 | 0.5556 | 0.7273 | 0.6234 | 0.5641 | 0.5882 |
|
94 |
+
| 0.0413 | 6.1372 | 3400 | 0.4692 | 0.5928 | 0.5939 | 0.5947 | 0.5983 | 0.6239 | 0.5273 | 0.5479 | 0.7407 | 0.6053 | 0.5333 | 0.5714 |
|
95 |
+
| 0.037 | 6.3177 | 3500 | 0.4739 | 0.6233 | 0.6322 | 0.6315 | 0.6273 | 0.6857 | 0.5688 | 0.6154 | 0.7857 | 0.5758 | 0.5909 | 0.5405 |
|
96 |
+
| 0.0391 | 6.4982 | 3600 | 0.4548 | 0.6074 | 0.6114 | 0.6120 | 0.6077 | 0.6538 | 0.5053 | 0.6269 | 0.7654 | 0.6216 | 0.5455 | 0.5333 |
|
97 |
+
| 0.0501 | 6.6787 | 3700 | 0.4723 | 0.6143 | 0.6263 | 0.6248 | 0.6279 | 0.6606 | 0.5859 | 0.6471 | 0.7727 | 0.6076 | 0.5385 | 0.4878 |
|
98 |
+
| 0.0374 | 6.8592 | 3800 | 0.4791 | 0.6165 | 0.6243 | 0.6236 | 0.6302 | 0.6604 | 0.56 | 0.6154 | 0.7816 | 0.6197 | 0.5479 | 0.5306 |
|
99 |
+
| 0.0326 | 7.0397 | 3900 | 0.5033 | 0.6041 | 0.6048 | 0.6056 | 0.6113 | 0.6038 | 0.5487 | 0.64 | 0.7381 | 0.5747 | 0.5679 | 0.5556 |
|
100 |
+
| 0.0288 | 7.2202 | 4000 | 0.5040 | 0.6223 | 0.6263 | 0.6277 | 0.6378 | 0.6504 | 0.5739 | 0.6667 | 0.7407 | 0.6341 | 0.55 | 0.5405 |
|
101 |
+
| 0.0303 | 7.4007 | 4100 | 0.5166 | 0.6145 | 0.6146 | 0.6158 | 0.6254 | 0.6154 | 0.5739 | 0.5915 | 0.75 | 0.6 | 0.5823 | 0.5882 |
|
102 |
+
| 0.0305 | 7.5812 | 4200 | 0.5064 | 0.6134 | 0.6195 | 0.6204 | 0.6270 | 0.6429 | 0.5421 | 0.6087 | 0.7619 | 0.6575 | 0.5679 | 0.5128 |
|
103 |
+
| 0.0298 | 7.7617 | 4300 | 0.5288 | 0.6126 | 0.6248 | 0.6226 | 0.6311 | 0.6337 | 0.5983 | 0.5660 | 0.7816 | 0.6410 | 0.5679 | 0.5 |
|
104 |
+
| 0.024 | 7.9422 | 4400 | 0.5131 | 0.6093 | 0.6159 | 0.6160 | 0.6288 | 0.6296 | 0.5333 | 0.5833 | 0.7907 | 0.6301 | 0.5854 | 0.5128 |
|
105 |
+
| 0.0207 | 8.1227 | 4500 | 0.5077 | 0.6228 | 0.6288 | 0.6263 | 0.6359 | 0.6408 | 0.5161 | 0.6585 | 0.7765 | 0.6420 | 0.5854 | 0.5405 |
|
106 |
+
| 0.0177 | 8.3032 | 4600 | 0.5217 | 0.6135 | 0.6186 | 0.6166 | 0.6282 | 0.6218 | 0.5417 | 0.5846 | 0.7907 | 0.6420 | 0.5581 | 0.5556 |
|
107 |
+
| 0.0223 | 8.4838 | 4700 | 0.5260 | 0.5978 | 0.6066 | 0.6060 | 0.6152 | 0.6296 | 0.5766 | 0.5538 | 0.7619 | 0.6067 | 0.5432 | 0.5128 |
|
108 |
+
| 0.0199 | 8.6643 | 4800 | 0.5204 | 0.6028 | 0.6103 | 0.6102 | 0.6195 | 0.6239 | 0.5490 | 0.6579 | 0.7765 | 0.5882 | 0.5366 | 0.4878 |
|
109 |
+
| 0.021 | 8.8448 | 4900 | 0.5245 | 0.6143 | 0.6213 | 0.6214 | 0.6335 | 0.6387 | 0.5739 | 0.6452 | 0.7619 | 0.6410 | 0.5278 | 0.5116 |
|
110 |
+
| 0.0216 | 9.0253 | 5000 | 0.5416 | 0.6182 | 0.6235 | 0.6233 | 0.6351 | 0.6415 | 0.5812 | 0.5970 | 0.7674 | 0.6234 | 0.5610 | 0.5556 |
|
111 |
+
| 0.0123 | 9.2058 | 5100 | 0.5260 | 0.6091 | 0.6151 | 0.6165 | 0.6303 | 0.6364 | 0.5636 | 0.56 | 0.7805 | 0.6047 | 0.5926 | 0.5263 |
|
112 |
+
| 0.0143 | 9.3863 | 5200 | 0.5354 | 0.6195 | 0.6231 | 0.6226 | 0.6393 | 0.6333 | 0.5714 | 0.6061 | 0.7765 | 0.6098 | 0.5679 | 0.5714 |
|
113 |
+
| 0.0155 | 9.5668 | 5300 | 0.5293 | 0.6071 | 0.6148 | 0.6150 | 0.6308 | 0.6538 | 0.5370 | 0.5797 | 0.7816 | 0.6234 | 0.5610 | 0.5128 |
|
114 |
+
| 0.0126 | 9.7473 | 5400 | 0.5321 | 0.5987 | 0.6064 | 0.6060 | 0.6185 | 0.6346 | 0.5283 | 0.5915 | 0.7816 | 0.6234 | 0.5316 | 0.5 |
|
115 |
+
| 0.014 | 9.9278 | 5500 | 0.5400 | 0.6112 | 0.6175 | 0.6171 | 0.6330 | 0.6355 | 0.5607 | 0.5641 | 0.7816 | 0.6316 | 0.5641 | 0.5405 |
|
116 |
+
| 0.0172 | 10.1083 | 5600 | 0.5339 | 0.6030 | 0.6073 | 0.6068 | 0.6215 | 0.6239 | 0.5347 | 0.6 | 0.7619 | 0.6098 | 0.55 | 0.5405 |
|
117 |
+
| 0.0097 | 10.2888 | 5700 | 0.5372 | 0.6113 | 0.6135 | 0.6123 | 0.6216 | 0.6296 | 0.5155 | 0.6154 | 0.7619 | 0.6173 | 0.5679 | 0.5714 |
|
118 |
+
| 0.01 | 10.4693 | 5800 | 0.5472 | 0.6006 | 0.6079 | 0.6075 | 0.6249 | 0.6168 | 0.5766 | 0.5946 | 0.7674 | 0.5926 | 0.5432 | 0.5128 |
|
119 |
+
| 0.0092 | 10.6498 | 5900 | 0.5489 | 0.6114 | 0.6170 | 0.6163 | 0.6338 | 0.6195 | 0.5688 | 0.5867 | 0.7674 | 0.6329 | 0.5641 | 0.5405 |
|
120 |
+
| 0.0115 | 10.8303 | 6000 | 0.5493 | 0.6018 | 0.6066 | 0.6058 | 0.6231 | 0.6296 | 0.5556 | 0.5753 | 0.7674 | 0.5977 | 0.5316 | 0.5556 |
|
121 |
+
| 0.0104 | 11.0108 | 6100 | 0.5480 | 0.6068 | 0.6105 | 0.6107 | 0.6254 | 0.6346 | 0.5455 | 0.5833 | 0.7674 | 0.6 | 0.5610 | 0.5556 |
|
122 |
+
| 0.0072 | 11.1913 | 6200 | 0.5485 | 0.6076 | 0.6125 | 0.6116 | 0.6290 | 0.6207 | 0.5714 | 0.5714 | 0.7674 | 0.6234 | 0.5432 | 0.5556 |
|
123 |
+
| 0.0074 | 11.3718 | 6300 | 0.5490 | 0.6019 | 0.6055 | 0.6052 | 0.6222 | 0.6195 | 0.5505 | 0.5753 | 0.7765 | 0.5926 | 0.5432 | 0.5556 |
|
124 |
+
| 0.008 | 11.5523 | 6400 | 0.5490 | 0.6025 | 0.6052 | 0.6049 | 0.6206 | 0.6195 | 0.5607 | 0.5753 | 0.7619 | 0.5854 | 0.5432 | 0.5714 |
|
125 |
+
| 0.0105 | 11.7329 | 6500 | 0.5529 | 0.5976 | 0.6045 | 0.6047 | 0.6230 | 0.625 | 0.5586 | 0.5753 | 0.7619 | 0.5926 | 0.5570 | 0.5128 |
|
126 |
+
| 0.0072 | 11.9134 | 6600 | 0.5533 | 0.5973 | 0.6045 | 0.6046 | 0.6245 | 0.625 | 0.5636 | 0.5753 | 0.7619 | 0.5926 | 0.55 | 0.5128 |
|
127 |
+
|
128 |
+
|
129 |
+
### Framework versions
|
130 |
+
|
131 |
+
- Transformers 4.47.1
|
132 |
+
- Pytorch 2.5.1+cu121
|
133 |
+
- Datasets 3.2.0
|
134 |
+
- Tokenizers 0.21.0
|
config.json
ADDED
@@ -0,0 +1,29 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "w11wo/sundanese-roberta-base",
|
3 |
+
"architectures": [
|
4 |
+
"RobertaForSequenceClassification"
|
5 |
+
],
|
6 |
+
"attention_probs_dropout_prob": 0.1,
|
7 |
+
"bos_token_id": 0,
|
8 |
+
"classifier_dropout": null,
|
9 |
+
"eos_token_id": 2,
|
10 |
+
"gradient_checkpointing": false,
|
11 |
+
"hidden_act": "gelu",
|
12 |
+
"hidden_dropout_prob": 0.1,
|
13 |
+
"hidden_size": 768,
|
14 |
+
"initializer_range": 0.02,
|
15 |
+
"intermediate_size": 3072,
|
16 |
+
"layer_norm_eps": 1e-05,
|
17 |
+
"max_position_embeddings": 514,
|
18 |
+
"model_type": "roberta",
|
19 |
+
"num_attention_heads": 12,
|
20 |
+
"num_hidden_layers": 12,
|
21 |
+
"pad_token_id": 1,
|
22 |
+
"position_embedding_type": "absolute",
|
23 |
+
"problem_type": "multi_label_classification",
|
24 |
+
"torch_dtype": "float32",
|
25 |
+
"transformers_version": "4.47.1",
|
26 |
+
"type_vocab_size": 1,
|
27 |
+
"use_cache": true,
|
28 |
+
"vocab_size": 50265
|
29 |
+
}
|
merges.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|
model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b67052620d62dbd71cf2a6ce2749b73710de52b65680f8c68bf27fc31d711650
|
3 |
+
size 498628204
|
runs/Jan08_12-14-13_32df0236926e/events.out.tfevents.1736338457.32df0236926e.17827.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:dcb6bd5877f87e7d38c365f2d43843423352b243257b575db17462fdf8ef1275
|
3 |
+
size 78525
|
special_tokens_map.json
ADDED
@@ -0,0 +1,51 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"bos_token": {
|
3 |
+
"content": "<s>",
|
4 |
+
"lstrip": false,
|
5 |
+
"normalized": false,
|
6 |
+
"rstrip": false,
|
7 |
+
"single_word": false
|
8 |
+
},
|
9 |
+
"cls_token": {
|
10 |
+
"content": "<s>",
|
11 |
+
"lstrip": false,
|
12 |
+
"normalized": false,
|
13 |
+
"rstrip": false,
|
14 |
+
"single_word": false
|
15 |
+
},
|
16 |
+
"eos_token": {
|
17 |
+
"content": "</s>",
|
18 |
+
"lstrip": false,
|
19 |
+
"normalized": false,
|
20 |
+
"rstrip": false,
|
21 |
+
"single_word": false
|
22 |
+
},
|
23 |
+
"mask_token": {
|
24 |
+
"content": "<mask>",
|
25 |
+
"lstrip": true,
|
26 |
+
"normalized": false,
|
27 |
+
"rstrip": false,
|
28 |
+
"single_word": false
|
29 |
+
},
|
30 |
+
"pad_token": {
|
31 |
+
"content": "<pad>",
|
32 |
+
"lstrip": false,
|
33 |
+
"normalized": false,
|
34 |
+
"rstrip": false,
|
35 |
+
"single_word": false
|
36 |
+
},
|
37 |
+
"sep_token": {
|
38 |
+
"content": "</s>",
|
39 |
+
"lstrip": false,
|
40 |
+
"normalized": false,
|
41 |
+
"rstrip": false,
|
42 |
+
"single_word": false
|
43 |
+
},
|
44 |
+
"unk_token": {
|
45 |
+
"content": "<unk>",
|
46 |
+
"lstrip": false,
|
47 |
+
"normalized": false,
|
48 |
+
"rstrip": false,
|
49 |
+
"single_word": false
|
50 |
+
}
|
51 |
+
}
|
tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
tokenizer_config.json
ADDED
@@ -0,0 +1,58 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"add_prefix_space": false,
|
3 |
+
"added_tokens_decoder": {
|
4 |
+
"0": {
|
5 |
+
"content": "<s>",
|
6 |
+
"lstrip": false,
|
7 |
+
"normalized": false,
|
8 |
+
"rstrip": false,
|
9 |
+
"single_word": false,
|
10 |
+
"special": true
|
11 |
+
},
|
12 |
+
"1": {
|
13 |
+
"content": "<pad>",
|
14 |
+
"lstrip": false,
|
15 |
+
"normalized": false,
|
16 |
+
"rstrip": false,
|
17 |
+
"single_word": false,
|
18 |
+
"special": true
|
19 |
+
},
|
20 |
+
"2": {
|
21 |
+
"content": "</s>",
|
22 |
+
"lstrip": false,
|
23 |
+
"normalized": false,
|
24 |
+
"rstrip": false,
|
25 |
+
"single_word": false,
|
26 |
+
"special": true
|
27 |
+
},
|
28 |
+
"3": {
|
29 |
+
"content": "<unk>",
|
30 |
+
"lstrip": false,
|
31 |
+
"normalized": false,
|
32 |
+
"rstrip": false,
|
33 |
+
"single_word": false,
|
34 |
+
"special": true
|
35 |
+
},
|
36 |
+
"4": {
|
37 |
+
"content": "<mask>",
|
38 |
+
"lstrip": true,
|
39 |
+
"normalized": false,
|
40 |
+
"rstrip": false,
|
41 |
+
"single_word": false,
|
42 |
+
"special": true
|
43 |
+
}
|
44 |
+
},
|
45 |
+
"bos_token": "<s>",
|
46 |
+
"clean_up_tokenization_spaces": false,
|
47 |
+
"cls_token": "<s>",
|
48 |
+
"eos_token": "</s>",
|
49 |
+
"errors": "replace",
|
50 |
+
"extra_special_tokens": {},
|
51 |
+
"mask_token": "<mask>",
|
52 |
+
"model_max_length": 1000000000000000019884624838656,
|
53 |
+
"pad_token": "<pad>",
|
54 |
+
"sep_token": "</s>",
|
55 |
+
"tokenizer_class": "RobertaTokenizer",
|
56 |
+
"trim_offsets": true,
|
57 |
+
"unk_token": "<unk>"
|
58 |
+
}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:1699d3f6b35c02ba246ebef67b02c6735bf64d227b989c4938b6e39d9bb81752
|
3 |
+
size 5368
|
vocab.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|