Initial Commit
Browse files- README.md +176 -0
- config.json +159 -0
- model.safetensors +3 -0
- training_args.bin +3 -0
README.md
ADDED
@@ -0,0 +1,176 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
library_name: transformers
|
3 |
+
license: mit
|
4 |
+
base_model: haryoaw/scenario-MDBT-TCR_data-AmazonScience_massive_all_1_1
|
5 |
+
tags:
|
6 |
+
- generated_from_trainer
|
7 |
+
datasets:
|
8 |
+
- massive
|
9 |
+
metrics:
|
10 |
+
- accuracy
|
11 |
+
- f1
|
12 |
+
model-index:
|
13 |
+
- name: scenario-NON-KD-PO-COPY-D2_data-AmazonScience_massive_all_1_155
|
14 |
+
results: []
|
15 |
+
---
|
16 |
+
|
17 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
18 |
+
should probably proofread and complete it, then remove this comment. -->
|
19 |
+
|
20 |
+
# scenario-NON-KD-PO-COPY-D2_data-AmazonScience_massive_all_1_155
|
21 |
+
|
22 |
+
This model is a fine-tuned version of [haryoaw/scenario-MDBT-TCR_data-AmazonScience_massive_all_1_1](https://huggingface.co/haryoaw/scenario-MDBT-TCR_data-AmazonScience_massive_all_1_1) on the massive dataset.
|
23 |
+
It achieves the following results on the evaluation set:
|
24 |
+
- Loss: 2.1172
|
25 |
+
- Accuracy: 0.8547
|
26 |
+
- F1: 0.8307
|
27 |
+
|
28 |
+
## Model description
|
29 |
+
|
30 |
+
More information needed
|
31 |
+
|
32 |
+
## Intended uses & limitations
|
33 |
+
|
34 |
+
More information needed
|
35 |
+
|
36 |
+
## Training and evaluation data
|
37 |
+
|
38 |
+
More information needed
|
39 |
+
|
40 |
+
## Training procedure
|
41 |
+
|
42 |
+
### Training hyperparameters
|
43 |
+
|
44 |
+
The following hyperparameters were used during training:
|
45 |
+
- learning_rate: 5e-05
|
46 |
+
- train_batch_size: 32
|
47 |
+
- eval_batch_size: 32
|
48 |
+
- seed: 55
|
49 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
50 |
+
- lr_scheduler_type: linear
|
51 |
+
- num_epochs: 30
|
52 |
+
|
53 |
+
### Training results
|
54 |
+
|
55 |
+
| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 |
|
56 |
+
|:-------------:|:-------:|:------:|:---------------:|:--------:|:------:|
|
57 |
+
| 0.5096 | 0.2672 | 5000 | 0.6672 | 0.8301 | 0.7901 |
|
58 |
+
| 0.4124 | 0.5344 | 10000 | 0.6564 | 0.8398 | 0.8058 |
|
59 |
+
| 0.3501 | 0.8017 | 15000 | 0.6697 | 0.8466 | 0.8172 |
|
60 |
+
| 0.232 | 1.0689 | 20000 | 0.7193 | 0.8480 | 0.8171 |
|
61 |
+
| 0.2262 | 1.3361 | 25000 | 0.7387 | 0.8489 | 0.8243 |
|
62 |
+
| 0.2146 | 1.6033 | 30000 | 0.7377 | 0.8480 | 0.8243 |
|
63 |
+
| 0.2007 | 1.8706 | 35000 | 0.7711 | 0.8463 | 0.8186 |
|
64 |
+
| 0.1472 | 2.1378 | 40000 | 0.8809 | 0.8492 | 0.8218 |
|
65 |
+
| 0.1509 | 2.4050 | 45000 | 0.8559 | 0.8495 | 0.8242 |
|
66 |
+
| 0.1513 | 2.6722 | 50000 | 0.8919 | 0.8481 | 0.8226 |
|
67 |
+
| 0.1428 | 2.9394 | 55000 | 0.8636 | 0.8503 | 0.8272 |
|
68 |
+
| 0.1154 | 3.2067 | 60000 | 0.9868 | 0.8512 | 0.8312 |
|
69 |
+
| 0.1148 | 3.4739 | 65000 | 0.9541 | 0.8502 | 0.8253 |
|
70 |
+
| 0.1152 | 3.7411 | 70000 | 0.9729 | 0.8503 | 0.8305 |
|
71 |
+
| 0.1031 | 4.0083 | 75000 | 1.0581 | 0.8459 | 0.8260 |
|
72 |
+
| 0.0942 | 4.2756 | 80000 | 1.0732 | 0.8487 | 0.8248 |
|
73 |
+
| 0.0961 | 4.5428 | 85000 | 1.0528 | 0.8509 | 0.8284 |
|
74 |
+
| 0.099 | 4.8100 | 90000 | 1.0421 | 0.8486 | 0.8250 |
|
75 |
+
| 0.0761 | 5.0772 | 95000 | 1.1302 | 0.8480 | 0.8221 |
|
76 |
+
| 0.0822 | 5.3444 | 100000 | 1.1138 | 0.8492 | 0.8261 |
|
77 |
+
| 0.0833 | 5.6117 | 105000 | 1.1368 | 0.8478 | 0.8243 |
|
78 |
+
| 0.0768 | 5.8789 | 110000 | 1.1240 | 0.8503 | 0.8256 |
|
79 |
+
| 0.0593 | 6.1461 | 115000 | 1.2497 | 0.8491 | 0.8277 |
|
80 |
+
| 0.0687 | 6.4133 | 120000 | 1.2261 | 0.8484 | 0.8252 |
|
81 |
+
| 0.0738 | 6.6806 | 125000 | 1.1406 | 0.8482 | 0.8257 |
|
82 |
+
| 0.0651 | 6.9478 | 130000 | 1.2154 | 0.8488 | 0.8232 |
|
83 |
+
| 0.0604 | 7.2150 | 135000 | 1.3001 | 0.8459 | 0.8245 |
|
84 |
+
| 0.0646 | 7.4822 | 140000 | 1.2426 | 0.8488 | 0.8223 |
|
85 |
+
| 0.0653 | 7.7495 | 145000 | 1.2843 | 0.8499 | 0.8283 |
|
86 |
+
| 0.0433 | 8.0167 | 150000 | 1.3361 | 0.8500 | 0.8261 |
|
87 |
+
| 0.0497 | 8.2839 | 155000 | 1.2612 | 0.8492 | 0.8241 |
|
88 |
+
| 0.0517 | 8.5511 | 160000 | 1.3544 | 0.8474 | 0.8270 |
|
89 |
+
| 0.0624 | 8.8183 | 165000 | 1.2964 | 0.8489 | 0.8275 |
|
90 |
+
| 0.0381 | 9.0856 | 170000 | 1.3753 | 0.8486 | 0.8242 |
|
91 |
+
| 0.0405 | 9.3528 | 175000 | 1.4366 | 0.8484 | 0.8219 |
|
92 |
+
| 0.0488 | 9.6200 | 180000 | 1.4429 | 0.8458 | 0.8235 |
|
93 |
+
| 0.0495 | 9.8872 | 185000 | 1.3962 | 0.8496 | 0.8273 |
|
94 |
+
| 0.0363 | 10.1545 | 190000 | 1.5269 | 0.8483 | 0.8247 |
|
95 |
+
| 0.0423 | 10.4217 | 195000 | 1.4415 | 0.8489 | 0.8236 |
|
96 |
+
| 0.0448 | 10.6889 | 200000 | 1.3974 | 0.8482 | 0.8218 |
|
97 |
+
| 0.0373 | 10.9561 | 205000 | 1.4432 | 0.8465 | 0.8245 |
|
98 |
+
| 0.0294 | 11.2233 | 210000 | 1.5381 | 0.8493 | 0.8234 |
|
99 |
+
| 0.0336 | 11.4906 | 215000 | 1.5496 | 0.8490 | 0.8218 |
|
100 |
+
| 0.041 | 11.7578 | 220000 | 1.4867 | 0.8468 | 0.8240 |
|
101 |
+
| 0.028 | 12.0250 | 225000 | 1.5215 | 0.8498 | 0.8270 |
|
102 |
+
| 0.0287 | 12.2922 | 230000 | 1.5916 | 0.8495 | 0.8256 |
|
103 |
+
| 0.0314 | 12.5595 | 235000 | 1.6239 | 0.8500 | 0.8291 |
|
104 |
+
| 0.0347 | 12.8267 | 240000 | 1.5390 | 0.8464 | 0.8243 |
|
105 |
+
| 0.0247 | 13.0939 | 245000 | 1.5492 | 0.8502 | 0.8271 |
|
106 |
+
| 0.0281 | 13.3611 | 250000 | 1.5729 | 0.8465 | 0.8262 |
|
107 |
+
| 0.025 | 13.6283 | 255000 | 1.6933 | 0.8470 | 0.8249 |
|
108 |
+
| 0.0325 | 13.8956 | 260000 | 1.5823 | 0.8511 | 0.8289 |
|
109 |
+
| 0.0268 | 14.1628 | 265000 | 1.6099 | 0.8476 | 0.8213 |
|
110 |
+
| 0.0339 | 14.4300 | 270000 | 1.6234 | 0.8514 | 0.8306 |
|
111 |
+
| 0.0285 | 14.6972 | 275000 | 1.5725 | 0.8524 | 0.8288 |
|
112 |
+
| 0.0309 | 14.9645 | 280000 | 1.6213 | 0.8498 | 0.8251 |
|
113 |
+
| 0.0274 | 15.2317 | 285000 | 1.6650 | 0.8481 | 0.8235 |
|
114 |
+
| 0.02 | 15.4989 | 290000 | 1.7295 | 0.8488 | 0.8261 |
|
115 |
+
| 0.0299 | 15.7661 | 295000 | 1.6868 | 0.8513 | 0.8277 |
|
116 |
+
| 0.0196 | 16.0333 | 300000 | 1.7188 | 0.8492 | 0.8234 |
|
117 |
+
| 0.0221 | 16.3006 | 305000 | 1.7492 | 0.8511 | 0.8265 |
|
118 |
+
| 0.0273 | 16.5678 | 310000 | 1.6775 | 0.8505 | 0.8267 |
|
119 |
+
| 0.0212 | 16.8350 | 315000 | 1.7104 | 0.8492 | 0.8253 |
|
120 |
+
| 0.0188 | 17.1022 | 320000 | 1.6627 | 0.8502 | 0.8271 |
|
121 |
+
| 0.0225 | 17.3695 | 325000 | 1.7774 | 0.8504 | 0.8256 |
|
122 |
+
| 0.0204 | 17.6367 | 330000 | 1.7537 | 0.8489 | 0.8240 |
|
123 |
+
| 0.0261 | 17.9039 | 335000 | 1.6829 | 0.8516 | 0.8273 |
|
124 |
+
| 0.0153 | 18.1711 | 340000 | 1.8292 | 0.8532 | 0.8295 |
|
125 |
+
| 0.0226 | 18.4384 | 345000 | 1.7632 | 0.8511 | 0.8273 |
|
126 |
+
| 0.0213 | 18.7056 | 350000 | 1.7662 | 0.8515 | 0.8252 |
|
127 |
+
| 0.0162 | 18.9728 | 355000 | 1.7639 | 0.8519 | 0.8280 |
|
128 |
+
| 0.0155 | 19.2400 | 360000 | 1.8033 | 0.8521 | 0.8262 |
|
129 |
+
| 0.0151 | 19.5072 | 365000 | 1.8838 | 0.8505 | 0.8241 |
|
130 |
+
| 0.0151 | 19.7745 | 370000 | 1.8777 | 0.8532 | 0.8268 |
|
131 |
+
| 0.0138 | 20.0417 | 375000 | 1.8770 | 0.8522 | 0.8284 |
|
132 |
+
| 0.0152 | 20.3089 | 380000 | 1.8785 | 0.8525 | 0.8275 |
|
133 |
+
| 0.0136 | 20.5761 | 385000 | 1.8761 | 0.8530 | 0.8310 |
|
134 |
+
| 0.0181 | 20.8434 | 390000 | 1.8843 | 0.8526 | 0.8288 |
|
135 |
+
| 0.0113 | 21.1106 | 395000 | 1.8946 | 0.8540 | 0.8306 |
|
136 |
+
| 0.0144 | 21.3778 | 400000 | 1.8532 | 0.8530 | 0.8318 |
|
137 |
+
| 0.0149 | 21.6450 | 405000 | 1.9300 | 0.8519 | 0.8296 |
|
138 |
+
| 0.0165 | 21.9122 | 410000 | 1.9072 | 0.8532 | 0.8316 |
|
139 |
+
| 0.0128 | 22.1795 | 415000 | 1.9919 | 0.8516 | 0.8270 |
|
140 |
+
| 0.0071 | 22.4467 | 420000 | 1.9807 | 0.8543 | 0.8313 |
|
141 |
+
| 0.0099 | 22.7139 | 425000 | 1.9709 | 0.8527 | 0.8277 |
|
142 |
+
| 0.011 | 22.9811 | 430000 | 1.9782 | 0.8521 | 0.8279 |
|
143 |
+
| 0.0102 | 23.2484 | 435000 | 2.0483 | 0.8515 | 0.8268 |
|
144 |
+
| 0.013 | 23.5156 | 440000 | 2.0266 | 0.8527 | 0.8290 |
|
145 |
+
| 0.0145 | 23.7828 | 445000 | 1.9633 | 0.8533 | 0.8303 |
|
146 |
+
| 0.0091 | 24.0500 | 450000 | 2.0645 | 0.8514 | 0.8274 |
|
147 |
+
| 0.0128 | 24.3172 | 455000 | 2.0243 | 0.8541 | 0.8314 |
|
148 |
+
| 0.0101 | 24.5845 | 460000 | 2.0680 | 0.8518 | 0.8281 |
|
149 |
+
| 0.0087 | 24.8517 | 465000 | 2.0453 | 0.8526 | 0.8290 |
|
150 |
+
| 0.0087 | 25.1189 | 470000 | 2.0808 | 0.8529 | 0.8294 |
|
151 |
+
| 0.0079 | 25.3861 | 475000 | 2.1050 | 0.8522 | 0.8285 |
|
152 |
+
| 0.0101 | 25.6534 | 480000 | 2.0773 | 0.8518 | 0.8275 |
|
153 |
+
| 0.0094 | 25.9206 | 485000 | 2.0602 | 0.8533 | 0.8305 |
|
154 |
+
| 0.0097 | 26.1878 | 490000 | 2.0994 | 0.8519 | 0.8267 |
|
155 |
+
| 0.01 | 26.4550 | 495000 | 2.0608 | 0.8549 | 0.8309 |
|
156 |
+
| 0.0107 | 26.7222 | 500000 | 2.0748 | 0.8539 | 0.8300 |
|
157 |
+
| 0.0088 | 26.9895 | 505000 | 2.1072 | 0.8539 | 0.8305 |
|
158 |
+
| 0.0057 | 27.2567 | 510000 | 2.1086 | 0.8548 | 0.8318 |
|
159 |
+
| 0.0096 | 27.5239 | 515000 | 2.1032 | 0.8539 | 0.8297 |
|
160 |
+
| 0.0082 | 27.7911 | 520000 | 2.1119 | 0.8538 | 0.8294 |
|
161 |
+
| 0.0081 | 28.0584 | 525000 | 2.1045 | 0.8543 | 0.8296 |
|
162 |
+
| 0.0079 | 28.3256 | 530000 | 2.1268 | 0.8539 | 0.8296 |
|
163 |
+
| 0.0089 | 28.5928 | 535000 | 2.1128 | 0.8547 | 0.8303 |
|
164 |
+
| 0.0079 | 28.8600 | 540000 | 2.1003 | 0.8540 | 0.8294 |
|
165 |
+
| 0.0056 | 29.1273 | 545000 | 2.1130 | 0.8541 | 0.8294 |
|
166 |
+
| 0.0082 | 29.3945 | 550000 | 2.1167 | 0.8544 | 0.8302 |
|
167 |
+
| 0.0056 | 29.6617 | 555000 | 2.1182 | 0.8546 | 0.8306 |
|
168 |
+
| 0.0076 | 29.9289 | 560000 | 2.1172 | 0.8547 | 0.8307 |
|
169 |
+
|
170 |
+
|
171 |
+
### Framework versions
|
172 |
+
|
173 |
+
- Transformers 4.44.2
|
174 |
+
- Pytorch 2.1.1+cu121
|
175 |
+
- Datasets 2.14.5
|
176 |
+
- Tokenizers 0.19.1
|
config.json
ADDED
@@ -0,0 +1,159 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "haryoaw/scenario-MDBT-TCR_data-AmazonScience_massive_all_1_1",
|
3 |
+
"architectures": [
|
4 |
+
"DebertaForSequenceClassificationKD"
|
5 |
+
],
|
6 |
+
"attention_probs_dropout_prob": 0.1,
|
7 |
+
"hidden_act": "gelu",
|
8 |
+
"hidden_dropout_prob": 0.1,
|
9 |
+
"hidden_size": 768,
|
10 |
+
"id2label": {
|
11 |
+
"0": "LABEL_0",
|
12 |
+
"1": "LABEL_1",
|
13 |
+
"2": "LABEL_2",
|
14 |
+
"3": "LABEL_3",
|
15 |
+
"4": "LABEL_4",
|
16 |
+
"5": "LABEL_5",
|
17 |
+
"6": "LABEL_6",
|
18 |
+
"7": "LABEL_7",
|
19 |
+
"8": "LABEL_8",
|
20 |
+
"9": "LABEL_9",
|
21 |
+
"10": "LABEL_10",
|
22 |
+
"11": "LABEL_11",
|
23 |
+
"12": "LABEL_12",
|
24 |
+
"13": "LABEL_13",
|
25 |
+
"14": "LABEL_14",
|
26 |
+
"15": "LABEL_15",
|
27 |
+
"16": "LABEL_16",
|
28 |
+
"17": "LABEL_17",
|
29 |
+
"18": "LABEL_18",
|
30 |
+
"19": "LABEL_19",
|
31 |
+
"20": "LABEL_20",
|
32 |
+
"21": "LABEL_21",
|
33 |
+
"22": "LABEL_22",
|
34 |
+
"23": "LABEL_23",
|
35 |
+
"24": "LABEL_24",
|
36 |
+
"25": "LABEL_25",
|
37 |
+
"26": "LABEL_26",
|
38 |
+
"27": "LABEL_27",
|
39 |
+
"28": "LABEL_28",
|
40 |
+
"29": "LABEL_29",
|
41 |
+
"30": "LABEL_30",
|
42 |
+
"31": "LABEL_31",
|
43 |
+
"32": "LABEL_32",
|
44 |
+
"33": "LABEL_33",
|
45 |
+
"34": "LABEL_34",
|
46 |
+
"35": "LABEL_35",
|
47 |
+
"36": "LABEL_36",
|
48 |
+
"37": "LABEL_37",
|
49 |
+
"38": "LABEL_38",
|
50 |
+
"39": "LABEL_39",
|
51 |
+
"40": "LABEL_40",
|
52 |
+
"41": "LABEL_41",
|
53 |
+
"42": "LABEL_42",
|
54 |
+
"43": "LABEL_43",
|
55 |
+
"44": "LABEL_44",
|
56 |
+
"45": "LABEL_45",
|
57 |
+
"46": "LABEL_46",
|
58 |
+
"47": "LABEL_47",
|
59 |
+
"48": "LABEL_48",
|
60 |
+
"49": "LABEL_49",
|
61 |
+
"50": "LABEL_50",
|
62 |
+
"51": "LABEL_51",
|
63 |
+
"52": "LABEL_52",
|
64 |
+
"53": "LABEL_53",
|
65 |
+
"54": "LABEL_54",
|
66 |
+
"55": "LABEL_55",
|
67 |
+
"56": "LABEL_56",
|
68 |
+
"57": "LABEL_57",
|
69 |
+
"58": "LABEL_58",
|
70 |
+
"59": "LABEL_59"
|
71 |
+
},
|
72 |
+
"initializer_range": 0.02,
|
73 |
+
"intermediate_size": 3072,
|
74 |
+
"label2id": {
|
75 |
+
"LABEL_0": 0,
|
76 |
+
"LABEL_1": 1,
|
77 |
+
"LABEL_10": 10,
|
78 |
+
"LABEL_11": 11,
|
79 |
+
"LABEL_12": 12,
|
80 |
+
"LABEL_13": 13,
|
81 |
+
"LABEL_14": 14,
|
82 |
+
"LABEL_15": 15,
|
83 |
+
"LABEL_16": 16,
|
84 |
+
"LABEL_17": 17,
|
85 |
+
"LABEL_18": 18,
|
86 |
+
"LABEL_19": 19,
|
87 |
+
"LABEL_2": 2,
|
88 |
+
"LABEL_20": 20,
|
89 |
+
"LABEL_21": 21,
|
90 |
+
"LABEL_22": 22,
|
91 |
+
"LABEL_23": 23,
|
92 |
+
"LABEL_24": 24,
|
93 |
+
"LABEL_25": 25,
|
94 |
+
"LABEL_26": 26,
|
95 |
+
"LABEL_27": 27,
|
96 |
+
"LABEL_28": 28,
|
97 |
+
"LABEL_29": 29,
|
98 |
+
"LABEL_3": 3,
|
99 |
+
"LABEL_30": 30,
|
100 |
+
"LABEL_31": 31,
|
101 |
+
"LABEL_32": 32,
|
102 |
+
"LABEL_33": 33,
|
103 |
+
"LABEL_34": 34,
|
104 |
+
"LABEL_35": 35,
|
105 |
+
"LABEL_36": 36,
|
106 |
+
"LABEL_37": 37,
|
107 |
+
"LABEL_38": 38,
|
108 |
+
"LABEL_39": 39,
|
109 |
+
"LABEL_4": 4,
|
110 |
+
"LABEL_40": 40,
|
111 |
+
"LABEL_41": 41,
|
112 |
+
"LABEL_42": 42,
|
113 |
+
"LABEL_43": 43,
|
114 |
+
"LABEL_44": 44,
|
115 |
+
"LABEL_45": 45,
|
116 |
+
"LABEL_46": 46,
|
117 |
+
"LABEL_47": 47,
|
118 |
+
"LABEL_48": 48,
|
119 |
+
"LABEL_49": 49,
|
120 |
+
"LABEL_5": 5,
|
121 |
+
"LABEL_50": 50,
|
122 |
+
"LABEL_51": 51,
|
123 |
+
"LABEL_52": 52,
|
124 |
+
"LABEL_53": 53,
|
125 |
+
"LABEL_54": 54,
|
126 |
+
"LABEL_55": 55,
|
127 |
+
"LABEL_56": 56,
|
128 |
+
"LABEL_57": 57,
|
129 |
+
"LABEL_58": 58,
|
130 |
+
"LABEL_59": 59,
|
131 |
+
"LABEL_6": 6,
|
132 |
+
"LABEL_7": 7,
|
133 |
+
"LABEL_8": 8,
|
134 |
+
"LABEL_9": 9
|
135 |
+
},
|
136 |
+
"layer_norm_eps": 1e-07,
|
137 |
+
"max_position_embeddings": 512,
|
138 |
+
"max_relative_positions": -1,
|
139 |
+
"model_type": "deberta-v2",
|
140 |
+
"norm_rel_ebd": "layer_norm",
|
141 |
+
"num_attention_heads": 12,
|
142 |
+
"num_hidden_layers": 6,
|
143 |
+
"pad_token_id": 0,
|
144 |
+
"pooler_dropout": 0,
|
145 |
+
"pooler_hidden_act": "gelu",
|
146 |
+
"pooler_hidden_size": 768,
|
147 |
+
"pos_att_type": [
|
148 |
+
"p2c",
|
149 |
+
"c2p"
|
150 |
+
],
|
151 |
+
"position_biased_input": false,
|
152 |
+
"position_buckets": 256,
|
153 |
+
"relative_attention": true,
|
154 |
+
"share_att_key": true,
|
155 |
+
"torch_dtype": "float32",
|
156 |
+
"transformers_version": "4.44.2",
|
157 |
+
"type_vocab_size": 0,
|
158 |
+
"vocab_size": 251000
|
159 |
+
}
|
model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:7ef2899f1a513215105c4e9ae217d0ad0c74bf25318152cef7a560c755093b17
|
3 |
+
size 946892288
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:fd79e236c3e64da6c0525f2d31069fb0df3c717721b626a38be36841d12118db
|
3 |
+
size 5304
|