Initial Commit
Browse files- README.md +175 -0
- config.json +153 -0
- pytorch_model.bin +3 -0
- training_args.bin +3 -0
README.md
ADDED
@@ -0,0 +1,175 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
license: mit
|
3 |
+
base_model: xlm-roberta-base
|
4 |
+
tags:
|
5 |
+
- generated_from_trainer
|
6 |
+
datasets:
|
7 |
+
- massive
|
8 |
+
metrics:
|
9 |
+
- accuracy
|
10 |
+
- f1
|
11 |
+
model-index:
|
12 |
+
- name: scenario-NON-KD-PR-COPY-D2_data-AmazonScience_massive_all_1_1_betta-jason
|
13 |
+
results: []
|
14 |
+
---
|
15 |
+
|
16 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
17 |
+
should probably proofread and complete it, then remove this comment. -->
|
18 |
+
|
19 |
+
# scenario-NON-KD-PR-COPY-D2_data-AmazonScience_massive_all_1_1_betta-jason
|
20 |
+
|
21 |
+
This model is a fine-tuned version of [xlm-roberta-base](https://huggingface.co/xlm-roberta-base) on the massive dataset.
|
22 |
+
It achieves the following results on the evaluation set:
|
23 |
+
- Loss: 1.4867
|
24 |
+
- Accuracy: 0.8342
|
25 |
+
- F1: 0.8095
|
26 |
+
|
27 |
+
## Model description
|
28 |
+
|
29 |
+
More information needed
|
30 |
+
|
31 |
+
## Intended uses & limitations
|
32 |
+
|
33 |
+
More information needed
|
34 |
+
|
35 |
+
## Training and evaluation data
|
36 |
+
|
37 |
+
More information needed
|
38 |
+
|
39 |
+
## Training procedure
|
40 |
+
|
41 |
+
### Training hyperparameters
|
42 |
+
|
43 |
+
The following hyperparameters were used during training:
|
44 |
+
- learning_rate: 5e-05
|
45 |
+
- train_batch_size: 32
|
46 |
+
- eval_batch_size: 32
|
47 |
+
- seed: 222
|
48 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
49 |
+
- lr_scheduler_type: linear
|
50 |
+
- num_epochs: 30
|
51 |
+
|
52 |
+
### Training results
|
53 |
+
|
54 |
+
| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 |
|
55 |
+
|:-------------:|:-----:|:------:|:---------------:|:--------:|:------:|
|
56 |
+
| 1.6555 | 0.27 | 5000 | 1.5175 | 0.5778 | 0.4204 |
|
57 |
+
| 1.1914 | 0.53 | 10000 | 1.1206 | 0.6936 | 0.5745 |
|
58 |
+
| 0.9781 | 0.8 | 15000 | 0.9691 | 0.7383 | 0.6438 |
|
59 |
+
| 0.7905 | 1.07 | 20000 | 0.8906 | 0.7631 | 0.6846 |
|
60 |
+
| 0.7201 | 1.34 | 25000 | 0.8162 | 0.7809 | 0.7151 |
|
61 |
+
| 0.6624 | 1.6 | 30000 | 0.7933 | 0.7914 | 0.7310 |
|
62 |
+
| 0.6399 | 1.87 | 35000 | 0.7562 | 0.8000 | 0.7518 |
|
63 |
+
| 0.5163 | 2.14 | 40000 | 0.7660 | 0.8057 | 0.7589 |
|
64 |
+
| 0.503 | 2.41 | 45000 | 0.7659 | 0.8060 | 0.7609 |
|
65 |
+
| 0.4855 | 2.67 | 50000 | 0.7446 | 0.8110 | 0.7707 |
|
66 |
+
| 0.4744 | 2.94 | 55000 | 0.7199 | 0.8160 | 0.7793 |
|
67 |
+
| 0.3807 | 3.21 | 60000 | 0.7582 | 0.8165 | 0.7787 |
|
68 |
+
| 0.3902 | 3.47 | 65000 | 0.7526 | 0.8177 | 0.7773 |
|
69 |
+
| 0.3757 | 3.74 | 70000 | 0.7647 | 0.8158 | 0.7771 |
|
70 |
+
| 0.3496 | 4.01 | 75000 | 0.7529 | 0.8234 | 0.7867 |
|
71 |
+
| 0.2917 | 4.28 | 80000 | 0.7961 | 0.8181 | 0.7830 |
|
72 |
+
| 0.3042 | 4.54 | 85000 | 0.7907 | 0.8190 | 0.7837 |
|
73 |
+
| 0.3098 | 4.81 | 90000 | 0.7699 | 0.8237 | 0.7878 |
|
74 |
+
| 0.2381 | 5.08 | 95000 | 0.8027 | 0.8224 | 0.7842 |
|
75 |
+
| 0.244 | 5.34 | 100000 | 0.8074 | 0.8242 | 0.7898 |
|
76 |
+
| 0.2509 | 5.61 | 105000 | 0.8052 | 0.8260 | 0.7924 |
|
77 |
+
| 0.2709 | 5.88 | 110000 | 0.8002 | 0.8258 | 0.7925 |
|
78 |
+
| 0.2001 | 6.15 | 115000 | 0.8449 | 0.8242 | 0.7909 |
|
79 |
+
| 0.2175 | 6.41 | 120000 | 0.8669 | 0.8236 | 0.7892 |
|
80 |
+
| 0.214 | 6.68 | 125000 | 0.8765 | 0.8252 | 0.7987 |
|
81 |
+
| 0.222 | 6.95 | 130000 | 0.8332 | 0.8288 | 0.8003 |
|
82 |
+
| 0.1713 | 7.22 | 135000 | 0.9019 | 0.8262 | 0.7951 |
|
83 |
+
| 0.1751 | 7.48 | 140000 | 0.8958 | 0.8255 | 0.7957 |
|
84 |
+
| 0.1794 | 7.75 | 145000 | 0.9065 | 0.8260 | 0.7982 |
|
85 |
+
| 0.1544 | 8.02 | 150000 | 0.9200 | 0.8263 | 0.8020 |
|
86 |
+
| 0.1445 | 8.28 | 155000 | 0.9510 | 0.8240 | 0.7975 |
|
87 |
+
| 0.155 | 8.55 | 160000 | 0.9418 | 0.8294 | 0.7999 |
|
88 |
+
| 0.157 | 8.82 | 165000 | 0.9463 | 0.8295 | 0.8055 |
|
89 |
+
| 0.1182 | 9.09 | 170000 | 0.9762 | 0.8273 | 0.8020 |
|
90 |
+
| 0.1303 | 9.35 | 175000 | 0.9829 | 0.8271 | 0.8032 |
|
91 |
+
| 0.131 | 9.62 | 180000 | 1.0006 | 0.8292 | 0.8019 |
|
92 |
+
| 0.127 | 9.89 | 185000 | 0.9976 | 0.8251 | 0.8009 |
|
93 |
+
| 0.092 | 10.15 | 190000 | 1.0280 | 0.8278 | 0.8002 |
|
94 |
+
| 0.1131 | 10.42 | 195000 | 1.0338 | 0.8271 | 0.8018 |
|
95 |
+
| 0.1135 | 10.69 | 200000 | 1.0388 | 0.8277 | 0.8009 |
|
96 |
+
| 0.115 | 10.96 | 205000 | 1.0341 | 0.8278 | 0.8010 |
|
97 |
+
| 0.0871 | 11.22 | 210000 | 1.0720 | 0.8282 | 0.8022 |
|
98 |
+
| 0.0992 | 11.49 | 215000 | 1.0691 | 0.8292 | 0.8040 |
|
99 |
+
| 0.1007 | 11.76 | 220000 | 1.0821 | 0.8279 | 0.8017 |
|
100 |
+
| 0.0776 | 12.03 | 225000 | 1.1169 | 0.8260 | 0.7960 |
|
101 |
+
| 0.0833 | 12.29 | 230000 | 1.1196 | 0.8283 | 0.8031 |
|
102 |
+
| 0.0843 | 12.56 | 235000 | 1.1386 | 0.8286 | 0.8035 |
|
103 |
+
| 0.0884 | 12.83 | 240000 | 1.1368 | 0.8281 | 0.8006 |
|
104 |
+
| 0.0637 | 13.09 | 245000 | 1.1611 | 0.8265 | 0.8032 |
|
105 |
+
| 0.0721 | 13.36 | 250000 | 1.1857 | 0.8248 | 0.7988 |
|
106 |
+
| 0.0731 | 13.63 | 255000 | 1.1788 | 0.8294 | 0.8028 |
|
107 |
+
| 0.0754 | 13.9 | 260000 | 1.1879 | 0.8266 | 0.8027 |
|
108 |
+
| 0.0615 | 14.16 | 265000 | 1.2059 | 0.8308 | 0.8049 |
|
109 |
+
| 0.0741 | 14.43 | 270000 | 1.2121 | 0.8280 | 0.8019 |
|
110 |
+
| 0.0677 | 14.7 | 275000 | 1.2192 | 0.8296 | 0.8033 |
|
111 |
+
| 0.0736 | 14.96 | 280000 | 1.2419 | 0.8266 | 0.7993 |
|
112 |
+
| 0.0561 | 15.23 | 285000 | 1.2439 | 0.8288 | 0.8006 |
|
113 |
+
| 0.0554 | 15.5 | 290000 | 1.2603 | 0.8282 | 0.7990 |
|
114 |
+
| 0.0634 | 15.77 | 295000 | 1.2692 | 0.8279 | 0.8009 |
|
115 |
+
| 0.0445 | 16.03 | 300000 | 1.2826 | 0.8284 | 0.8010 |
|
116 |
+
| 0.052 | 16.3 | 305000 | 1.2949 | 0.8287 | 0.8048 |
|
117 |
+
| 0.0568 | 16.57 | 310000 | 1.3029 | 0.8284 | 0.8031 |
|
118 |
+
| 0.0484 | 16.84 | 315000 | 1.2977 | 0.8298 | 0.8043 |
|
119 |
+
| 0.0446 | 17.1 | 320000 | 1.3212 | 0.8280 | 0.8031 |
|
120 |
+
| 0.0462 | 17.37 | 325000 | 1.3350 | 0.8277 | 0.8013 |
|
121 |
+
| 0.047 | 17.64 | 330000 | 1.3301 | 0.8297 | 0.8042 |
|
122 |
+
| 0.048 | 17.9 | 335000 | 1.3293 | 0.8297 | 0.8041 |
|
123 |
+
| 0.0421 | 18.17 | 340000 | 1.3249 | 0.8286 | 0.8023 |
|
124 |
+
| 0.0405 | 18.44 | 345000 | 1.3471 | 0.8277 | 0.8025 |
|
125 |
+
| 0.0458 | 18.71 | 350000 | 1.3654 | 0.8302 | 0.8037 |
|
126 |
+
| 0.0463 | 18.97 | 355000 | 1.3435 | 0.8311 | 0.8043 |
|
127 |
+
| 0.0392 | 19.24 | 360000 | 1.3816 | 0.8294 | 0.8051 |
|
128 |
+
| 0.0379 | 19.51 | 365000 | 1.3748 | 0.8315 | 0.8077 |
|
129 |
+
| 0.0358 | 19.77 | 370000 | 1.3599 | 0.8322 | 0.8064 |
|
130 |
+
| 0.0276 | 20.04 | 375000 | 1.3637 | 0.8318 | 0.8080 |
|
131 |
+
| 0.0359 | 20.31 | 380000 | 1.3649 | 0.8322 | 0.8068 |
|
132 |
+
| 0.0322 | 20.58 | 385000 | 1.3857 | 0.8305 | 0.8040 |
|
133 |
+
| 0.0404 | 20.84 | 390000 | 1.3926 | 0.8302 | 0.8048 |
|
134 |
+
| 0.0338 | 21.11 | 395000 | 1.3937 | 0.8311 | 0.8048 |
|
135 |
+
| 0.0307 | 21.38 | 400000 | 1.4248 | 0.8294 | 0.8043 |
|
136 |
+
| 0.0301 | 21.65 | 405000 | 1.4184 | 0.8296 | 0.8050 |
|
137 |
+
| 0.0289 | 21.91 | 410000 | 1.4154 | 0.8307 | 0.8053 |
|
138 |
+
| 0.0266 | 22.18 | 415000 | 1.4249 | 0.8304 | 0.8057 |
|
139 |
+
| 0.0282 | 22.45 | 420000 | 1.4311 | 0.8319 | 0.8085 |
|
140 |
+
| 0.0306 | 22.71 | 425000 | 1.4417 | 0.8306 | 0.8055 |
|
141 |
+
| 0.0272 | 22.98 | 430000 | 1.4490 | 0.8302 | 0.8036 |
|
142 |
+
| 0.0264 | 23.25 | 435000 | 1.4372 | 0.8321 | 0.8061 |
|
143 |
+
| 0.0232 | 23.52 | 440000 | 1.4548 | 0.8304 | 0.8057 |
|
144 |
+
| 0.0264 | 23.78 | 445000 | 1.4496 | 0.8317 | 0.8065 |
|
145 |
+
| 0.0194 | 24.05 | 450000 | 1.4454 | 0.8320 | 0.8073 |
|
146 |
+
| 0.0228 | 24.32 | 455000 | 1.4532 | 0.8327 | 0.8077 |
|
147 |
+
| 0.0229 | 24.58 | 460000 | 1.4574 | 0.8325 | 0.8068 |
|
148 |
+
| 0.0203 | 24.85 | 465000 | 1.4709 | 0.8310 | 0.8066 |
|
149 |
+
| 0.0183 | 25.12 | 470000 | 1.4707 | 0.8327 | 0.8090 |
|
150 |
+
| 0.0157 | 25.39 | 475000 | 1.4689 | 0.8334 | 0.8089 |
|
151 |
+
| 0.0175 | 25.65 | 480000 | 1.4704 | 0.8324 | 0.8076 |
|
152 |
+
| 0.0211 | 25.92 | 485000 | 1.4806 | 0.8319 | 0.8065 |
|
153 |
+
| 0.0158 | 26.19 | 490000 | 1.4881 | 0.8326 | 0.8067 |
|
154 |
+
| 0.0209 | 26.46 | 495000 | 1.4771 | 0.8335 | 0.8084 |
|
155 |
+
| 0.0193 | 26.72 | 500000 | 1.4882 | 0.8325 | 0.8076 |
|
156 |
+
| 0.0184 | 26.99 | 505000 | 1.4740 | 0.8333 | 0.8088 |
|
157 |
+
| 0.0145 | 27.26 | 510000 | 1.4818 | 0.8339 | 0.8095 |
|
158 |
+
| 0.0141 | 27.52 | 515000 | 1.4909 | 0.8327 | 0.8075 |
|
159 |
+
| 0.0157 | 27.79 | 520000 | 1.4787 | 0.8331 | 0.8086 |
|
160 |
+
| 0.0168 | 28.06 | 525000 | 1.4842 | 0.8336 | 0.8078 |
|
161 |
+
| 0.0179 | 28.33 | 530000 | 1.4847 | 0.8338 | 0.8084 |
|
162 |
+
| 0.014 | 28.59 | 535000 | 1.4846 | 0.8339 | 0.8089 |
|
163 |
+
| 0.0145 | 28.86 | 540000 | 1.4856 | 0.8333 | 0.8087 |
|
164 |
+
| 0.0135 | 29.13 | 545000 | 1.4864 | 0.8336 | 0.8085 |
|
165 |
+
| 0.0127 | 29.39 | 550000 | 1.4852 | 0.8340 | 0.8088 |
|
166 |
+
| 0.0159 | 29.66 | 555000 | 1.4874 | 0.8342 | 0.8093 |
|
167 |
+
| 0.0144 | 29.93 | 560000 | 1.4867 | 0.8342 | 0.8095 |
|
168 |
+
|
169 |
+
|
170 |
+
### Framework versions
|
171 |
+
|
172 |
+
- Transformers 4.33.3
|
173 |
+
- Pytorch 2.1.1+cu121
|
174 |
+
- Datasets 2.14.5
|
175 |
+
- Tokenizers 0.13.3
|
config.json
ADDED
@@ -0,0 +1,153 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "xlm-roberta-base",
|
3 |
+
"architectures": [
|
4 |
+
"XLMRobertaForSequenceClassificationKD"
|
5 |
+
],
|
6 |
+
"attention_probs_dropout_prob": 0.1,
|
7 |
+
"bos_token_id": 0,
|
8 |
+
"classifier_dropout": null,
|
9 |
+
"eos_token_id": 2,
|
10 |
+
"hidden_act": "gelu",
|
11 |
+
"hidden_dropout_prob": 0.1,
|
12 |
+
"hidden_size": 384,
|
13 |
+
"id2label": {
|
14 |
+
"0": "LABEL_0",
|
15 |
+
"1": "LABEL_1",
|
16 |
+
"2": "LABEL_2",
|
17 |
+
"3": "LABEL_3",
|
18 |
+
"4": "LABEL_4",
|
19 |
+
"5": "LABEL_5",
|
20 |
+
"6": "LABEL_6",
|
21 |
+
"7": "LABEL_7",
|
22 |
+
"8": "LABEL_8",
|
23 |
+
"9": "LABEL_9",
|
24 |
+
"10": "LABEL_10",
|
25 |
+
"11": "LABEL_11",
|
26 |
+
"12": "LABEL_12",
|
27 |
+
"13": "LABEL_13",
|
28 |
+
"14": "LABEL_14",
|
29 |
+
"15": "LABEL_15",
|
30 |
+
"16": "LABEL_16",
|
31 |
+
"17": "LABEL_17",
|
32 |
+
"18": "LABEL_18",
|
33 |
+
"19": "LABEL_19",
|
34 |
+
"20": "LABEL_20",
|
35 |
+
"21": "LABEL_21",
|
36 |
+
"22": "LABEL_22",
|
37 |
+
"23": "LABEL_23",
|
38 |
+
"24": "LABEL_24",
|
39 |
+
"25": "LABEL_25",
|
40 |
+
"26": "LABEL_26",
|
41 |
+
"27": "LABEL_27",
|
42 |
+
"28": "LABEL_28",
|
43 |
+
"29": "LABEL_29",
|
44 |
+
"30": "LABEL_30",
|
45 |
+
"31": "LABEL_31",
|
46 |
+
"32": "LABEL_32",
|
47 |
+
"33": "LABEL_33",
|
48 |
+
"34": "LABEL_34",
|
49 |
+
"35": "LABEL_35",
|
50 |
+
"36": "LABEL_36",
|
51 |
+
"37": "LABEL_37",
|
52 |
+
"38": "LABEL_38",
|
53 |
+
"39": "LABEL_39",
|
54 |
+
"40": "LABEL_40",
|
55 |
+
"41": "LABEL_41",
|
56 |
+
"42": "LABEL_42",
|
57 |
+
"43": "LABEL_43",
|
58 |
+
"44": "LABEL_44",
|
59 |
+
"45": "LABEL_45",
|
60 |
+
"46": "LABEL_46",
|
61 |
+
"47": "LABEL_47",
|
62 |
+
"48": "LABEL_48",
|
63 |
+
"49": "LABEL_49",
|
64 |
+
"50": "LABEL_50",
|
65 |
+
"51": "LABEL_51",
|
66 |
+
"52": "LABEL_52",
|
67 |
+
"53": "LABEL_53",
|
68 |
+
"54": "LABEL_54",
|
69 |
+
"55": "LABEL_55",
|
70 |
+
"56": "LABEL_56",
|
71 |
+
"57": "LABEL_57",
|
72 |
+
"58": "LABEL_58",
|
73 |
+
"59": "LABEL_59"
|
74 |
+
},
|
75 |
+
"initializer_range": 0.02,
|
76 |
+
"intermediate_size": 1536,
|
77 |
+
"label2id": {
|
78 |
+
"LABEL_0": 0,
|
79 |
+
"LABEL_1": 1,
|
80 |
+
"LABEL_10": 10,
|
81 |
+
"LABEL_11": 11,
|
82 |
+
"LABEL_12": 12,
|
83 |
+
"LABEL_13": 13,
|
84 |
+
"LABEL_14": 14,
|
85 |
+
"LABEL_15": 15,
|
86 |
+
"LABEL_16": 16,
|
87 |
+
"LABEL_17": 17,
|
88 |
+
"LABEL_18": 18,
|
89 |
+
"LABEL_19": 19,
|
90 |
+
"LABEL_2": 2,
|
91 |
+
"LABEL_20": 20,
|
92 |
+
"LABEL_21": 21,
|
93 |
+
"LABEL_22": 22,
|
94 |
+
"LABEL_23": 23,
|
95 |
+
"LABEL_24": 24,
|
96 |
+
"LABEL_25": 25,
|
97 |
+
"LABEL_26": 26,
|
98 |
+
"LABEL_27": 27,
|
99 |
+
"LABEL_28": 28,
|
100 |
+
"LABEL_29": 29,
|
101 |
+
"LABEL_3": 3,
|
102 |
+
"LABEL_30": 30,
|
103 |
+
"LABEL_31": 31,
|
104 |
+
"LABEL_32": 32,
|
105 |
+
"LABEL_33": 33,
|
106 |
+
"LABEL_34": 34,
|
107 |
+
"LABEL_35": 35,
|
108 |
+
"LABEL_36": 36,
|
109 |
+
"LABEL_37": 37,
|
110 |
+
"LABEL_38": 38,
|
111 |
+
"LABEL_39": 39,
|
112 |
+
"LABEL_4": 4,
|
113 |
+
"LABEL_40": 40,
|
114 |
+
"LABEL_41": 41,
|
115 |
+
"LABEL_42": 42,
|
116 |
+
"LABEL_43": 43,
|
117 |
+
"LABEL_44": 44,
|
118 |
+
"LABEL_45": 45,
|
119 |
+
"LABEL_46": 46,
|
120 |
+
"LABEL_47": 47,
|
121 |
+
"LABEL_48": 48,
|
122 |
+
"LABEL_49": 49,
|
123 |
+
"LABEL_5": 5,
|
124 |
+
"LABEL_50": 50,
|
125 |
+
"LABEL_51": 51,
|
126 |
+
"LABEL_52": 52,
|
127 |
+
"LABEL_53": 53,
|
128 |
+
"LABEL_54": 54,
|
129 |
+
"LABEL_55": 55,
|
130 |
+
"LABEL_56": 56,
|
131 |
+
"LABEL_57": 57,
|
132 |
+
"LABEL_58": 58,
|
133 |
+
"LABEL_59": 59,
|
134 |
+
"LABEL_6": 6,
|
135 |
+
"LABEL_7": 7,
|
136 |
+
"LABEL_8": 8,
|
137 |
+
"LABEL_9": 9
|
138 |
+
},
|
139 |
+
"layer_norm_eps": 1e-05,
|
140 |
+
"max_position_embeddings": 514,
|
141 |
+
"model_type": "xlm-roberta",
|
142 |
+
"num_attention_heads": 12,
|
143 |
+
"num_hidden_layers": 6,
|
144 |
+
"output_past": true,
|
145 |
+
"pad_token_id": 1,
|
146 |
+
"position_embedding_type": "absolute",
|
147 |
+
"problem_type": "single_label_classification",
|
148 |
+
"torch_dtype": "float32",
|
149 |
+
"transformers_version": "4.33.3",
|
150 |
+
"type_vocab_size": 1,
|
151 |
+
"use_cache": true,
|
152 |
+
"vocab_size": 250002
|
153 |
+
}
|
pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:aad5b0fb7037fa0e741913f6799ad3b99224e1d9cc6b83ed6454ffb0a4e76874
|
3 |
+
size 429287542
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:de05ce42a42de812934baf03c2fa77bf646e89e5f9963b60193ec036865e8981
|
3 |
+
size 4664
|