syafiqfaray
commited on
Commit
•
7fa54de
1
Parent(s):
e1494f2
End of training
Browse files- README.md +162 -0
- config.json +33 -0
- generation_config.json +6 -0
- pytorch_model.bin +3 -0
- special_tokens_map.json +150 -0
- tokenizer_config.json +157 -0
- training_args.bin +3 -0
README.md
ADDED
@@ -0,0 +1,162 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
license: apache-2.0
|
3 |
+
base_model: google/byt5-small
|
4 |
+
tags:
|
5 |
+
- generated_from_trainer
|
6 |
+
metrics:
|
7 |
+
- wer
|
8 |
+
model-index:
|
9 |
+
- name: byt5-finetuned-indocollex-informal-to-formal
|
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 |
+
# byt5-finetuned-indocollex-informal-to-formal
|
17 |
+
|
18 |
+
This model is a fine-tuned version of [google/byt5-small](https://huggingface.co/google/byt5-small) on an unknown dataset.
|
19 |
+
It achieves the following results on the evaluation set:
|
20 |
+
- Loss: 0.2186
|
21 |
+
- Cer: 0.2292
|
22 |
+
- Wer: 0.6667
|
23 |
+
- Word Acc: 0.3333
|
24 |
+
- Gen Len: 7.4857
|
25 |
+
|
26 |
+
## Model description
|
27 |
+
|
28 |
+
More information needed
|
29 |
+
|
30 |
+
## Intended uses & limitations
|
31 |
+
|
32 |
+
More information needed
|
33 |
+
|
34 |
+
## Training and evaluation data
|
35 |
+
|
36 |
+
More information needed
|
37 |
+
|
38 |
+
## Training procedure
|
39 |
+
|
40 |
+
### Training hyperparameters
|
41 |
+
|
42 |
+
The following hyperparameters were used during training:
|
43 |
+
- learning_rate: 2e-05
|
44 |
+
- train_batch_size: 32
|
45 |
+
- eval_batch_size: 32
|
46 |
+
- seed: 42
|
47 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
48 |
+
- lr_scheduler_type: linear
|
49 |
+
- num_epochs: 100
|
50 |
+
|
51 |
+
### Training results
|
52 |
+
|
53 |
+
| Training Loss | Epoch | Step | Validation Loss | Cer | Wer | Word Acc | Gen Len |
|
54 |
+
|:-------------:|:-----:|:----:|:---------------:|:------:|:------:|:--------:|:-------:|
|
55 |
+
| No log | 1.0 | 47 | 45.4518 | 2.1817 | 2.0286 | -1.0286 | 19.0 |
|
56 |
+
| No log | 2.0 | 94 | 34.7405 | 2.2267 | 2.5619 | -1.5619 | 19.0 |
|
57 |
+
| No log | 3.0 | 141 | 26.0483 | 2.2895 | 4.5857 | -3.5857 | 19.0 |
|
58 |
+
| No log | 4.0 | 188 | 17.2640 | 2.399 | 1.3667 | -0.3667 | 19.0 |
|
59 |
+
| No log | 5.0 | 235 | 7.8648 | 2.4949 | 1.0 | 0.0 | 19.0 |
|
60 |
+
| No log | 6.0 | 282 | 5.4635 | 2.4143 | 1.0 | 0.0 | 19.0 |
|
61 |
+
| No log | 7.0 | 329 | 4.8432 | 1.253 | 1.0 | 0.0 | 8.8743 |
|
62 |
+
| No log | 8.0 | 376 | 4.1049 | 1.0 | 1.0 | 0.0 | 0.0 |
|
63 |
+
| No log | 9.0 | 423 | 3.1453 | 0.848 | 1.0 | 0.0 | 7.3371 |
|
64 |
+
| No log | 10.0 | 470 | 2.6065 | 0.8778 | 0.9905 | 0.0095 | 7.3486 |
|
65 |
+
| 19.2068 | 11.0 | 517 | 1.6326 | 0.9677 | 1.0 | 0.0 | 9.5143 |
|
66 |
+
| 19.2068 | 12.0 | 564 | 0.9833 | 0.7538 | 0.9905 | 0.0095 | 8.4571 |
|
67 |
+
| 19.2068 | 13.0 | 611 | 0.6980 | 0.6562 | 0.981 | 0.019 | 7.5543 |
|
68 |
+
| 19.2068 | 14.0 | 658 | 0.5709 | 0.5679 | 0.9857 | 0.0143 | 6.9714 |
|
69 |
+
| 19.2068 | 15.0 | 705 | 0.4965 | 0.4567 | 0.9571 | 0.0429 | 6.7886 |
|
70 |
+
| 19.2068 | 16.0 | 752 | 0.4470 | 0.3413 | 0.9381 | 0.0619 | 6.84 |
|
71 |
+
| 19.2068 | 17.0 | 799 | 0.4211 | 0.3175 | 0.9238 | 0.0762 | 6.8514 |
|
72 |
+
| 19.2068 | 18.0 | 846 | 0.4036 | 0.3124 | 0.9 | 0.1 | 6.6914 |
|
73 |
+
| 19.2068 | 19.0 | 893 | 0.3738 | 0.3031 | 0.9048 | 0.0952 | 6.9429 |
|
74 |
+
| 19.2068 | 20.0 | 940 | 0.3604 | 0.309 | 0.8857 | 0.1143 | 6.9086 |
|
75 |
+
| 19.2068 | 21.0 | 987 | 0.3489 | 0.3022 | 0.881 | 0.119 | 7.0171 |
|
76 |
+
| 0.8827 | 22.0 | 1034 | 0.3320 | 0.2869 | 0.8333 | 0.1667 | 6.9771 |
|
77 |
+
| 0.8827 | 23.0 | 1081 | 0.3238 | 0.2861 | 0.8238 | 0.1762 | 6.9257 |
|
78 |
+
| 0.8827 | 24.0 | 1128 | 0.3163 | 0.2666 | 0.8143 | 0.1857 | 7.2686 |
|
79 |
+
| 0.8827 | 25.0 | 1175 | 0.3139 | 0.2733 | 0.8095 | 0.1905 | 7.2914 |
|
80 |
+
| 0.8827 | 26.0 | 1222 | 0.3029 | 0.2716 | 0.8 | 0.2 | 7.36 |
|
81 |
+
| 0.8827 | 27.0 | 1269 | 0.2941 | 0.2666 | 0.7905 | 0.2095 | 7.2971 |
|
82 |
+
| 0.8827 | 28.0 | 1316 | 0.2905 | 0.2666 | 0.7857 | 0.2143 | 7.2914 |
|
83 |
+
| 0.8827 | 29.0 | 1363 | 0.2835 | 0.2615 | 0.7857 | 0.2143 | 7.2686 |
|
84 |
+
| 0.8827 | 30.0 | 1410 | 0.2829 | 0.2733 | 0.781 | 0.219 | 7.44 |
|
85 |
+
| 0.8827 | 31.0 | 1457 | 0.2762 | 0.2598 | 0.7714 | 0.2286 | 7.3714 |
|
86 |
+
| 0.3372 | 32.0 | 1504 | 0.2746 | 0.2725 | 0.7857 | 0.2143 | 7.4571 |
|
87 |
+
| 0.3372 | 33.0 | 1551 | 0.2728 | 0.2666 | 0.7714 | 0.2286 | 7.4457 |
|
88 |
+
| 0.3372 | 34.0 | 1598 | 0.2650 | 0.2572 | 0.7619 | 0.2381 | 7.3886 |
|
89 |
+
| 0.3372 | 35.0 | 1645 | 0.2618 | 0.2708 | 0.7762 | 0.2238 | 7.44 |
|
90 |
+
| 0.3372 | 36.0 | 1692 | 0.2579 | 0.2572 | 0.7619 | 0.2381 | 7.3771 |
|
91 |
+
| 0.3372 | 37.0 | 1739 | 0.2563 | 0.2496 | 0.7524 | 0.2476 | 7.3371 |
|
92 |
+
| 0.3372 | 38.0 | 1786 | 0.2530 | 0.247 | 0.7571 | 0.2429 | 7.3543 |
|
93 |
+
| 0.3372 | 39.0 | 1833 | 0.2531 | 0.2504 | 0.7667 | 0.2333 | 7.3657 |
|
94 |
+
| 0.3372 | 40.0 | 1880 | 0.2521 | 0.2453 | 0.7476 | 0.2524 | 7.3143 |
|
95 |
+
| 0.3372 | 41.0 | 1927 | 0.2496 | 0.2419 | 0.7333 | 0.2667 | 7.2914 |
|
96 |
+
| 0.3372 | 42.0 | 1974 | 0.2483 | 0.2411 | 0.7381 | 0.2619 | 7.3143 |
|
97 |
+
| 0.2747 | 43.0 | 2021 | 0.2446 | 0.2402 | 0.7381 | 0.2619 | 7.3429 |
|
98 |
+
| 0.2747 | 44.0 | 2068 | 0.2443 | 0.2402 | 0.7381 | 0.2619 | 7.32 |
|
99 |
+
| 0.2747 | 45.0 | 2115 | 0.2425 | 0.2377 | 0.7381 | 0.2619 | 7.3714 |
|
100 |
+
| 0.2747 | 46.0 | 2162 | 0.2406 | 0.2351 | 0.7429 | 0.2571 | 7.3714 |
|
101 |
+
| 0.2747 | 47.0 | 2209 | 0.2399 | 0.2402 | 0.7429 | 0.2571 | 7.32 |
|
102 |
+
| 0.2747 | 48.0 | 2256 | 0.2383 | 0.2402 | 0.7381 | 0.2619 | 7.3657 |
|
103 |
+
| 0.2747 | 49.0 | 2303 | 0.2363 | 0.2377 | 0.7429 | 0.2571 | 7.3257 |
|
104 |
+
| 0.2747 | 50.0 | 2350 | 0.2340 | 0.2301 | 0.7143 | 0.2857 | 7.3714 |
|
105 |
+
| 0.2747 | 51.0 | 2397 | 0.2347 | 0.2275 | 0.7143 | 0.2857 | 7.3543 |
|
106 |
+
| 0.2747 | 52.0 | 2444 | 0.2332 | 0.2275 | 0.7143 | 0.2857 | 7.3714 |
|
107 |
+
| 0.2747 | 53.0 | 2491 | 0.2309 | 0.2258 | 0.7095 | 0.2905 | 7.3657 |
|
108 |
+
| 0.2411 | 54.0 | 2538 | 0.2309 | 0.225 | 0.7048 | 0.2952 | 7.3714 |
|
109 |
+
| 0.2411 | 55.0 | 2585 | 0.2299 | 0.2267 | 0.7048 | 0.2952 | 7.3829 |
|
110 |
+
| 0.2411 | 56.0 | 2632 | 0.2280 | 0.2258 | 0.7048 | 0.2952 | 7.4171 |
|
111 |
+
| 0.2411 | 57.0 | 2679 | 0.2301 | 0.2233 | 0.6952 | 0.3048 | 7.44 |
|
112 |
+
| 0.2411 | 58.0 | 2726 | 0.2287 | 0.2207 | 0.6905 | 0.3095 | 7.44 |
|
113 |
+
| 0.2411 | 59.0 | 2773 | 0.2295 | 0.2216 | 0.7 | 0.3 | 7.4171 |
|
114 |
+
| 0.2411 | 60.0 | 2820 | 0.2277 | 0.2199 | 0.6952 | 0.3048 | 7.4229 |
|
115 |
+
| 0.2411 | 61.0 | 2867 | 0.2267 | 0.2233 | 0.6952 | 0.3048 | 7.4286 |
|
116 |
+
| 0.2411 | 62.0 | 2914 | 0.2260 | 0.2233 | 0.7048 | 0.2952 | 7.4343 |
|
117 |
+
| 0.2411 | 63.0 | 2961 | 0.2263 | 0.2224 | 0.7048 | 0.2952 | 7.4343 |
|
118 |
+
| 0.2193 | 64.0 | 3008 | 0.2262 | 0.2216 | 0.6952 | 0.3048 | 7.4286 |
|
119 |
+
| 0.2193 | 65.0 | 3055 | 0.2268 | 0.225 | 0.6952 | 0.3048 | 7.4 |
|
120 |
+
| 0.2193 | 66.0 | 3102 | 0.2241 | 0.2207 | 0.6952 | 0.3048 | 7.4114 |
|
121 |
+
| 0.2193 | 67.0 | 3149 | 0.2237 | 0.2233 | 0.7 | 0.3 | 7.4286 |
|
122 |
+
| 0.2193 | 68.0 | 3196 | 0.2230 | 0.2224 | 0.7 | 0.3 | 7.4229 |
|
123 |
+
| 0.2193 | 69.0 | 3243 | 0.2229 | 0.2216 | 0.681 | 0.319 | 7.4286 |
|
124 |
+
| 0.2193 | 70.0 | 3290 | 0.2225 | 0.2241 | 0.7 | 0.3 | 7.4286 |
|
125 |
+
| 0.2193 | 71.0 | 3337 | 0.2220 | 0.2241 | 0.6905 | 0.3095 | 7.44 |
|
126 |
+
| 0.2193 | 72.0 | 3384 | 0.2221 | 0.2241 | 0.6905 | 0.3095 | 7.4286 |
|
127 |
+
| 0.2193 | 73.0 | 3431 | 0.2214 | 0.2241 | 0.6905 | 0.3095 | 7.4171 |
|
128 |
+
| 0.2193 | 74.0 | 3478 | 0.2215 | 0.2233 | 0.6905 | 0.3095 | 7.4229 |
|
129 |
+
| 0.2056 | 75.0 | 3525 | 0.2209 | 0.2267 | 0.6905 | 0.3095 | 7.4457 |
|
130 |
+
| 0.2056 | 76.0 | 3572 | 0.2208 | 0.2258 | 0.6905 | 0.3095 | 7.44 |
|
131 |
+
| 0.2056 | 77.0 | 3619 | 0.2201 | 0.225 | 0.6905 | 0.3095 | 7.4343 |
|
132 |
+
| 0.2056 | 78.0 | 3666 | 0.2205 | 0.2258 | 0.6905 | 0.3095 | 7.4229 |
|
133 |
+
| 0.2056 | 79.0 | 3713 | 0.2209 | 0.225 | 0.6905 | 0.3095 | 7.4171 |
|
134 |
+
| 0.2056 | 80.0 | 3760 | 0.2203 | 0.2275 | 0.6857 | 0.3143 | 7.4571 |
|
135 |
+
| 0.2056 | 81.0 | 3807 | 0.2201 | 0.2275 | 0.6857 | 0.3143 | 7.4571 |
|
136 |
+
| 0.2056 | 82.0 | 3854 | 0.2204 | 0.2275 | 0.6857 | 0.3143 | 7.4571 |
|
137 |
+
| 0.2056 | 83.0 | 3901 | 0.2203 | 0.2267 | 0.6762 | 0.3238 | 7.4629 |
|
138 |
+
| 0.2056 | 84.0 | 3948 | 0.2199 | 0.2267 | 0.6667 | 0.3333 | 7.4743 |
|
139 |
+
| 0.2056 | 85.0 | 3995 | 0.2194 | 0.2267 | 0.6667 | 0.3333 | 7.48 |
|
140 |
+
| 0.196 | 86.0 | 4042 | 0.2193 | 0.2275 | 0.6667 | 0.3333 | 7.4743 |
|
141 |
+
| 0.196 | 87.0 | 4089 | 0.2189 | 0.2284 | 0.6667 | 0.3333 | 7.48 |
|
142 |
+
| 0.196 | 88.0 | 4136 | 0.2185 | 0.2275 | 0.6619 | 0.3381 | 7.4971 |
|
143 |
+
| 0.196 | 89.0 | 4183 | 0.2188 | 0.225 | 0.6619 | 0.3381 | 7.4914 |
|
144 |
+
| 0.196 | 90.0 | 4230 | 0.2185 | 0.2292 | 0.6667 | 0.3333 | 7.4857 |
|
145 |
+
| 0.196 | 91.0 | 4277 | 0.2188 | 0.2292 | 0.6667 | 0.3333 | 7.4857 |
|
146 |
+
| 0.196 | 92.0 | 4324 | 0.2189 | 0.2284 | 0.6667 | 0.3333 | 7.48 |
|
147 |
+
| 0.196 | 93.0 | 4371 | 0.2191 | 0.2258 | 0.6667 | 0.3333 | 7.4743 |
|
148 |
+
| 0.196 | 94.0 | 4418 | 0.2190 | 0.2258 | 0.6667 | 0.3333 | 7.4743 |
|
149 |
+
| 0.196 | 95.0 | 4465 | 0.2187 | 0.2258 | 0.6667 | 0.3333 | 7.4743 |
|
150 |
+
| 0.1901 | 96.0 | 4512 | 0.2186 | 0.2267 | 0.6667 | 0.3333 | 7.48 |
|
151 |
+
| 0.1901 | 97.0 | 4559 | 0.2187 | 0.2267 | 0.6667 | 0.3333 | 7.48 |
|
152 |
+
| 0.1901 | 98.0 | 4606 | 0.2187 | 0.2267 | 0.6667 | 0.3333 | 7.48 |
|
153 |
+
| 0.1901 | 99.0 | 4653 | 0.2186 | 0.2292 | 0.6667 | 0.3333 | 7.4857 |
|
154 |
+
| 0.1901 | 100.0 | 4700 | 0.2186 | 0.2292 | 0.6667 | 0.3333 | 7.4857 |
|
155 |
+
|
156 |
+
|
157 |
+
### Framework versions
|
158 |
+
|
159 |
+
- Transformers 4.33.0
|
160 |
+
- Pytorch 2.0.0
|
161 |
+
- Datasets 2.1.0
|
162 |
+
- Tokenizers 0.13.3
|
config.json
ADDED
@@ -0,0 +1,33 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "google/byt5-small",
|
3 |
+
"architectures": [
|
4 |
+
"T5ForConditionalGeneration"
|
5 |
+
],
|
6 |
+
"classifier_dropout": 0.0,
|
7 |
+
"d_ff": 3584,
|
8 |
+
"d_kv": 64,
|
9 |
+
"d_model": 1472,
|
10 |
+
"decoder_start_token_id": 0,
|
11 |
+
"dense_act_fn": "gelu_new",
|
12 |
+
"dropout_rate": 0.1,
|
13 |
+
"eos_token_id": 1,
|
14 |
+
"feed_forward_proj": "gated-gelu",
|
15 |
+
"gradient_checkpointing": false,
|
16 |
+
"initializer_factor": 1.0,
|
17 |
+
"is_encoder_decoder": true,
|
18 |
+
"is_gated_act": true,
|
19 |
+
"layer_norm_epsilon": 1e-06,
|
20 |
+
"model_type": "t5",
|
21 |
+
"num_decoder_layers": 4,
|
22 |
+
"num_heads": 6,
|
23 |
+
"num_layers": 12,
|
24 |
+
"pad_token_id": 0,
|
25 |
+
"relative_attention_max_distance": 128,
|
26 |
+
"relative_attention_num_buckets": 32,
|
27 |
+
"tie_word_embeddings": false,
|
28 |
+
"tokenizer_class": "ByT5Tokenizer",
|
29 |
+
"torch_dtype": "float32",
|
30 |
+
"transformers_version": "4.33.0",
|
31 |
+
"use_cache": true,
|
32 |
+
"vocab_size": 384
|
33 |
+
}
|
generation_config.json
ADDED
@@ -0,0 +1,6 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"decoder_start_token_id": 0,
|
3 |
+
"eos_token_id": 1,
|
4 |
+
"pad_token_id": 0,
|
5 |
+
"transformers_version": "4.33.0"
|
6 |
+
}
|
pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:2854ef95ec6b5121fcde7a0db27dcda826431c278e1512a5423e250ac7687674
|
3 |
+
size 1198609653
|
special_tokens_map.json
ADDED
@@ -0,0 +1,150 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"additional_special_tokens": [
|
3 |
+
"<extra_id_0>",
|
4 |
+
"<extra_id_1>",
|
5 |
+
"<extra_id_2>",
|
6 |
+
"<extra_id_3>",
|
7 |
+
"<extra_id_4>",
|
8 |
+
"<extra_id_5>",
|
9 |
+
"<extra_id_6>",
|
10 |
+
"<extra_id_7>",
|
11 |
+
"<extra_id_8>",
|
12 |
+
"<extra_id_9>",
|
13 |
+
"<extra_id_10>",
|
14 |
+
"<extra_id_11>",
|
15 |
+
"<extra_id_12>",
|
16 |
+
"<extra_id_13>",
|
17 |
+
"<extra_id_14>",
|
18 |
+
"<extra_id_15>",
|
19 |
+
"<extra_id_16>",
|
20 |
+
"<extra_id_17>",
|
21 |
+
"<extra_id_18>",
|
22 |
+
"<extra_id_19>",
|
23 |
+
"<extra_id_20>",
|
24 |
+
"<extra_id_21>",
|
25 |
+
"<extra_id_22>",
|
26 |
+
"<extra_id_23>",
|
27 |
+
"<extra_id_24>",
|
28 |
+
"<extra_id_25>",
|
29 |
+
"<extra_id_26>",
|
30 |
+
"<extra_id_27>",
|
31 |
+
"<extra_id_28>",
|
32 |
+
"<extra_id_29>",
|
33 |
+
"<extra_id_30>",
|
34 |
+
"<extra_id_31>",
|
35 |
+
"<extra_id_32>",
|
36 |
+
"<extra_id_33>",
|
37 |
+
"<extra_id_34>",
|
38 |
+
"<extra_id_35>",
|
39 |
+
"<extra_id_36>",
|
40 |
+
"<extra_id_37>",
|
41 |
+
"<extra_id_38>",
|
42 |
+
"<extra_id_39>",
|
43 |
+
"<extra_id_40>",
|
44 |
+
"<extra_id_41>",
|
45 |
+
"<extra_id_42>",
|
46 |
+
"<extra_id_43>",
|
47 |
+
"<extra_id_44>",
|
48 |
+
"<extra_id_45>",
|
49 |
+
"<extra_id_46>",
|
50 |
+
"<extra_id_47>",
|
51 |
+
"<extra_id_48>",
|
52 |
+
"<extra_id_49>",
|
53 |
+
"<extra_id_50>",
|
54 |
+
"<extra_id_51>",
|
55 |
+
"<extra_id_52>",
|
56 |
+
"<extra_id_53>",
|
57 |
+
"<extra_id_54>",
|
58 |
+
"<extra_id_55>",
|
59 |
+
"<extra_id_56>",
|
60 |
+
"<extra_id_57>",
|
61 |
+
"<extra_id_58>",
|
62 |
+
"<extra_id_59>",
|
63 |
+
"<extra_id_60>",
|
64 |
+
"<extra_id_61>",
|
65 |
+
"<extra_id_62>",
|
66 |
+
"<extra_id_63>",
|
67 |
+
"<extra_id_64>",
|
68 |
+
"<extra_id_65>",
|
69 |
+
"<extra_id_66>",
|
70 |
+
"<extra_id_67>",
|
71 |
+
"<extra_id_68>",
|
72 |
+
"<extra_id_69>",
|
73 |
+
"<extra_id_70>",
|
74 |
+
"<extra_id_71>",
|
75 |
+
"<extra_id_72>",
|
76 |
+
"<extra_id_73>",
|
77 |
+
"<extra_id_74>",
|
78 |
+
"<extra_id_75>",
|
79 |
+
"<extra_id_76>",
|
80 |
+
"<extra_id_77>",
|
81 |
+
"<extra_id_78>",
|
82 |
+
"<extra_id_79>",
|
83 |
+
"<extra_id_80>",
|
84 |
+
"<extra_id_81>",
|
85 |
+
"<extra_id_82>",
|
86 |
+
"<extra_id_83>",
|
87 |
+
"<extra_id_84>",
|
88 |
+
"<extra_id_85>",
|
89 |
+
"<extra_id_86>",
|
90 |
+
"<extra_id_87>",
|
91 |
+
"<extra_id_88>",
|
92 |
+
"<extra_id_89>",
|
93 |
+
"<extra_id_90>",
|
94 |
+
"<extra_id_91>",
|
95 |
+
"<extra_id_92>",
|
96 |
+
"<extra_id_93>",
|
97 |
+
"<extra_id_94>",
|
98 |
+
"<extra_id_95>",
|
99 |
+
"<extra_id_96>",
|
100 |
+
"<extra_id_97>",
|
101 |
+
"<extra_id_98>",
|
102 |
+
"<extra_id_99>",
|
103 |
+
"<extra_id_100>",
|
104 |
+
"<extra_id_101>",
|
105 |
+
"<extra_id_102>",
|
106 |
+
"<extra_id_103>",
|
107 |
+
"<extra_id_104>",
|
108 |
+
"<extra_id_105>",
|
109 |
+
"<extra_id_106>",
|
110 |
+
"<extra_id_107>",
|
111 |
+
"<extra_id_108>",
|
112 |
+
"<extra_id_109>",
|
113 |
+
"<extra_id_110>",
|
114 |
+
"<extra_id_111>",
|
115 |
+
"<extra_id_112>",
|
116 |
+
"<extra_id_113>",
|
117 |
+
"<extra_id_114>",
|
118 |
+
"<extra_id_115>",
|
119 |
+
"<extra_id_116>",
|
120 |
+
"<extra_id_117>",
|
121 |
+
"<extra_id_118>",
|
122 |
+
"<extra_id_119>",
|
123 |
+
"<extra_id_120>",
|
124 |
+
"<extra_id_121>",
|
125 |
+
"<extra_id_122>",
|
126 |
+
"<extra_id_123>",
|
127 |
+
"<extra_id_124>"
|
128 |
+
],
|
129 |
+
"eos_token": {
|
130 |
+
"content": "</s>",
|
131 |
+
"lstrip": false,
|
132 |
+
"normalized": true,
|
133 |
+
"rstrip": false,
|
134 |
+
"single_word": false
|
135 |
+
},
|
136 |
+
"pad_token": {
|
137 |
+
"content": "<pad>",
|
138 |
+
"lstrip": false,
|
139 |
+
"normalized": true,
|
140 |
+
"rstrip": false,
|
141 |
+
"single_word": false
|
142 |
+
},
|
143 |
+
"unk_token": {
|
144 |
+
"content": "<unk>",
|
145 |
+
"lstrip": false,
|
146 |
+
"normalized": true,
|
147 |
+
"rstrip": false,
|
148 |
+
"single_word": false
|
149 |
+
}
|
150 |
+
}
|
tokenizer_config.json
ADDED
@@ -0,0 +1,157 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"additional_special_tokens": [
|
3 |
+
"<extra_id_0>",
|
4 |
+
"<extra_id_1>",
|
5 |
+
"<extra_id_2>",
|
6 |
+
"<extra_id_3>",
|
7 |
+
"<extra_id_4>",
|
8 |
+
"<extra_id_5>",
|
9 |
+
"<extra_id_6>",
|
10 |
+
"<extra_id_7>",
|
11 |
+
"<extra_id_8>",
|
12 |
+
"<extra_id_9>",
|
13 |
+
"<extra_id_10>",
|
14 |
+
"<extra_id_11>",
|
15 |
+
"<extra_id_12>",
|
16 |
+
"<extra_id_13>",
|
17 |
+
"<extra_id_14>",
|
18 |
+
"<extra_id_15>",
|
19 |
+
"<extra_id_16>",
|
20 |
+
"<extra_id_17>",
|
21 |
+
"<extra_id_18>",
|
22 |
+
"<extra_id_19>",
|
23 |
+
"<extra_id_20>",
|
24 |
+
"<extra_id_21>",
|
25 |
+
"<extra_id_22>",
|
26 |
+
"<extra_id_23>",
|
27 |
+
"<extra_id_24>",
|
28 |
+
"<extra_id_25>",
|
29 |
+
"<extra_id_26>",
|
30 |
+
"<extra_id_27>",
|
31 |
+
"<extra_id_28>",
|
32 |
+
"<extra_id_29>",
|
33 |
+
"<extra_id_30>",
|
34 |
+
"<extra_id_31>",
|
35 |
+
"<extra_id_32>",
|
36 |
+
"<extra_id_33>",
|
37 |
+
"<extra_id_34>",
|
38 |
+
"<extra_id_35>",
|
39 |
+
"<extra_id_36>",
|
40 |
+
"<extra_id_37>",
|
41 |
+
"<extra_id_38>",
|
42 |
+
"<extra_id_39>",
|
43 |
+
"<extra_id_40>",
|
44 |
+
"<extra_id_41>",
|
45 |
+
"<extra_id_42>",
|
46 |
+
"<extra_id_43>",
|
47 |
+
"<extra_id_44>",
|
48 |
+
"<extra_id_45>",
|
49 |
+
"<extra_id_46>",
|
50 |
+
"<extra_id_47>",
|
51 |
+
"<extra_id_48>",
|
52 |
+
"<extra_id_49>",
|
53 |
+
"<extra_id_50>",
|
54 |
+
"<extra_id_51>",
|
55 |
+
"<extra_id_52>",
|
56 |
+
"<extra_id_53>",
|
57 |
+
"<extra_id_54>",
|
58 |
+
"<extra_id_55>",
|
59 |
+
"<extra_id_56>",
|
60 |
+
"<extra_id_57>",
|
61 |
+
"<extra_id_58>",
|
62 |
+
"<extra_id_59>",
|
63 |
+
"<extra_id_60>",
|
64 |
+
"<extra_id_61>",
|
65 |
+
"<extra_id_62>",
|
66 |
+
"<extra_id_63>",
|
67 |
+
"<extra_id_64>",
|
68 |
+
"<extra_id_65>",
|
69 |
+
"<extra_id_66>",
|
70 |
+
"<extra_id_67>",
|
71 |
+
"<extra_id_68>",
|
72 |
+
"<extra_id_69>",
|
73 |
+
"<extra_id_70>",
|
74 |
+
"<extra_id_71>",
|
75 |
+
"<extra_id_72>",
|
76 |
+
"<extra_id_73>",
|
77 |
+
"<extra_id_74>",
|
78 |
+
"<extra_id_75>",
|
79 |
+
"<extra_id_76>",
|
80 |
+
"<extra_id_77>",
|
81 |
+
"<extra_id_78>",
|
82 |
+
"<extra_id_79>",
|
83 |
+
"<extra_id_80>",
|
84 |
+
"<extra_id_81>",
|
85 |
+
"<extra_id_82>",
|
86 |
+
"<extra_id_83>",
|
87 |
+
"<extra_id_84>",
|
88 |
+
"<extra_id_85>",
|
89 |
+
"<extra_id_86>",
|
90 |
+
"<extra_id_87>",
|
91 |
+
"<extra_id_88>",
|
92 |
+
"<extra_id_89>",
|
93 |
+
"<extra_id_90>",
|
94 |
+
"<extra_id_91>",
|
95 |
+
"<extra_id_92>",
|
96 |
+
"<extra_id_93>",
|
97 |
+
"<extra_id_94>",
|
98 |
+
"<extra_id_95>",
|
99 |
+
"<extra_id_96>",
|
100 |
+
"<extra_id_97>",
|
101 |
+
"<extra_id_98>",
|
102 |
+
"<extra_id_99>",
|
103 |
+
"<extra_id_100>",
|
104 |
+
"<extra_id_101>",
|
105 |
+
"<extra_id_102>",
|
106 |
+
"<extra_id_103>",
|
107 |
+
"<extra_id_104>",
|
108 |
+
"<extra_id_105>",
|
109 |
+
"<extra_id_106>",
|
110 |
+
"<extra_id_107>",
|
111 |
+
"<extra_id_108>",
|
112 |
+
"<extra_id_109>",
|
113 |
+
"<extra_id_110>",
|
114 |
+
"<extra_id_111>",
|
115 |
+
"<extra_id_112>",
|
116 |
+
"<extra_id_113>",
|
117 |
+
"<extra_id_114>",
|
118 |
+
"<extra_id_115>",
|
119 |
+
"<extra_id_116>",
|
120 |
+
"<extra_id_117>",
|
121 |
+
"<extra_id_118>",
|
122 |
+
"<extra_id_119>",
|
123 |
+
"<extra_id_120>",
|
124 |
+
"<extra_id_121>",
|
125 |
+
"<extra_id_122>",
|
126 |
+
"<extra_id_123>",
|
127 |
+
"<extra_id_124>"
|
128 |
+
],
|
129 |
+
"clean_up_tokenization_spaces": true,
|
130 |
+
"eos_token": {
|
131 |
+
"__type": "AddedToken",
|
132 |
+
"content": "</s>",
|
133 |
+
"lstrip": false,
|
134 |
+
"normalized": true,
|
135 |
+
"rstrip": false,
|
136 |
+
"single_word": false
|
137 |
+
},
|
138 |
+
"extra_ids": 125,
|
139 |
+
"model_max_length": 1000000000000000019884624838656,
|
140 |
+
"pad_token": {
|
141 |
+
"__type": "AddedToken",
|
142 |
+
"content": "<pad>",
|
143 |
+
"lstrip": false,
|
144 |
+
"normalized": true,
|
145 |
+
"rstrip": false,
|
146 |
+
"single_word": false
|
147 |
+
},
|
148 |
+
"tokenizer_class": "ByT5Tokenizer",
|
149 |
+
"unk_token": {
|
150 |
+
"__type": "AddedToken",
|
151 |
+
"content": "<unk>",
|
152 |
+
"lstrip": false,
|
153 |
+
"normalized": true,
|
154 |
+
"rstrip": false,
|
155 |
+
"single_word": false
|
156 |
+
}
|
157 |
+
}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e025943ac44033e663fdc165bd7a26d9e0fb5eb2243fba5de9c8a5bc83e17bf3
|
3 |
+
size 4219
|