Model save
Browse files- .gitattributes +1 -0
- README.md +189 -0
- adapter_config.json +32 -0
- adapter_model.safetensors +3 -0
- runs/Mar10_23-08-48_1412920010036/events.out.tfevents.1741662535.1412920010036.5471.0 +3 -0
- special_tokens_map.json +23 -0
- spiece.model +3 -0
- tokenizer.json +3 -0
- tokenizer_config.json +840 -0
- training_args.bin +3 -0
.gitattributes
CHANGED
@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
|
33 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
34 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
|
|
|
33 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
34 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
36 |
+
tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
README.md
ADDED
@@ -0,0 +1,189 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
library_name: peft
|
3 |
+
license: apache-2.0
|
4 |
+
base_model: google/mt5-small
|
5 |
+
tags:
|
6 |
+
- generated_from_trainer
|
7 |
+
metrics:
|
8 |
+
- rouge
|
9 |
+
model-index:
|
10 |
+
- name: my-lora-sum
|
11 |
+
results: []
|
12 |
+
---
|
13 |
+
|
14 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
15 |
+
should probably proofread and complete it, then remove this comment. -->
|
16 |
+
|
17 |
+
# my-lora-sum
|
18 |
+
|
19 |
+
This model is a fine-tuned version of [google/mt5-small](https://huggingface.co/google/mt5-small) on an unknown dataset.
|
20 |
+
It achieves the following results on the evaluation set:
|
21 |
+
- Loss: 5.3452
|
22 |
+
- Rouge1: 2.9750
|
23 |
+
- Rouge2: 0.0640
|
24 |
+
- Rougel: 2.8027
|
25 |
+
- Rougelsum: 2.8035
|
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: 0.0001
|
45 |
+
- train_batch_size: 4
|
46 |
+
- eval_batch_size: 4
|
47 |
+
- seed: 42
|
48 |
+
- optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
|
49 |
+
- lr_scheduler_type: linear
|
50 |
+
- num_epochs: 2
|
51 |
+
|
52 |
+
### Training results
|
53 |
+
|
54 |
+
| Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum |
|
55 |
+
|:-------------:|:------:|:----:|:---------------:|:------:|:------:|:------:|:---------:|
|
56 |
+
| 23.6472 | 0.0160 | 5 | 11.7512 | 0.4881 | 0.0353 | 0.4380 | 0.4362 |
|
57 |
+
| 21.3789 | 0.0319 | 10 | 11.7109 | 0.4912 | 0.0353 | 0.4526 | 0.4486 |
|
58 |
+
| 19.719 | 0.0479 | 15 | 11.6279 | 0.5005 | 0.0432 | 0.4531 | 0.4477 |
|
59 |
+
| 22.2901 | 0.0639 | 20 | 11.6000 | 0.4946 | 0.0319 | 0.4410 | 0.4381 |
|
60 |
+
| 19.6455 | 0.0799 | 25 | 11.5404 | 0.5263 | 0.0530 | 0.4856 | 0.4833 |
|
61 |
+
| 19.892 | 0.0958 | 30 | 11.5011 | 0.5202 | 0.0396 | 0.4798 | 0.4716 |
|
62 |
+
| 19.8908 | 0.1118 | 35 | 11.4428 | 0.5431 | 0.0429 | 0.5013 | 0.4933 |
|
63 |
+
| 21.5179 | 0.1278 | 40 | 11.4066 | 0.5156 | 0.0405 | 0.4717 | 0.4682 |
|
64 |
+
| 21.7581 | 0.1438 | 45 | 11.3629 | 0.5416 | 0.0325 | 0.4834 | 0.4787 |
|
65 |
+
| 20.9988 | 0.1597 | 50 | 11.2869 | 0.5288 | 0.0270 | 0.4752 | 0.4743 |
|
66 |
+
| 21.3311 | 0.1757 | 55 | 11.2290 | 0.5260 | 0.0223 | 0.4642 | 0.4629 |
|
67 |
+
| 23.6669 | 0.1917 | 60 | 11.1785 | 0.4932 | 0.0188 | 0.4345 | 0.4307 |
|
68 |
+
| 18.2309 | 0.2077 | 65 | 11.1129 | 0.4645 | 0.0193 | 0.4156 | 0.4170 |
|
69 |
+
| 20.9785 | 0.2236 | 70 | 11.0331 | 0.5031 | 0.0238 | 0.4532 | 0.4530 |
|
70 |
+
| 16.4643 | 0.2396 | 75 | 10.9403 | 0.4414 | 0.0177 | 0.3945 | 0.3899 |
|
71 |
+
| 16.8242 | 0.2556 | 80 | 10.8374 | 0.4631 | 0.0177 | 0.4165 | 0.4110 |
|
72 |
+
| 23.1133 | 0.2716 | 85 | 10.7508 | 0.5054 | 0.0253 | 0.4434 | 0.4380 |
|
73 |
+
| 21.1076 | 0.2875 | 90 | 10.6718 | 0.4766 | 0.0178 | 0.4129 | 0.4101 |
|
74 |
+
| 17.6879 | 0.3035 | 95 | 10.5684 | 0.5166 | 0.0212 | 0.4634 | 0.4573 |
|
75 |
+
| 19.3182 | 0.3195 | 100 | 10.4315 | 0.5774 | 0.0217 | 0.5121 | 0.5070 |
|
76 |
+
| 18.6413 | 0.3355 | 105 | 10.2988 | 0.5325 | 0.0257 | 0.4803 | 0.4803 |
|
77 |
+
| 19.9276 | 0.3514 | 110 | 10.1745 | 0.5529 | 0.0348 | 0.4877 | 0.4841 |
|
78 |
+
| 17.9226 | 0.3674 | 115 | 10.0297 | 0.5852 | 0.0432 | 0.5075 | 0.5039 |
|
79 |
+
| 15.9707 | 0.3834 | 120 | 9.8977 | 0.5779 | 0.0403 | 0.5015 | 0.4992 |
|
80 |
+
| 16.5054 | 0.3994 | 125 | 9.7266 | 0.5685 | 0.0416 | 0.5011 | 0.4963 |
|
81 |
+
| 14.6994 | 0.4153 | 130 | 9.5595 | 0.6368 | 0.0506 | 0.5492 | 0.5447 |
|
82 |
+
| 15.9555 | 0.4313 | 135 | 9.3894 | 0.6401 | 0.0438 | 0.5520 | 0.5465 |
|
83 |
+
| 14.876 | 0.4473 | 140 | 9.2403 | 0.6910 | 0.0467 | 0.5961 | 0.5929 |
|
84 |
+
| 17.3615 | 0.4633 | 145 | 9.0976 | 0.7497 | 0.0499 | 0.6499 | 0.6448 |
|
85 |
+
| 15.8582 | 0.4792 | 150 | 8.9385 | 0.7409 | 0.0383 | 0.6427 | 0.6398 |
|
86 |
+
| 14.4111 | 0.4952 | 155 | 8.7924 | 0.7075 | 0.0457 | 0.6404 | 0.6366 |
|
87 |
+
| 13.9827 | 0.5112 | 160 | 8.6373 | 0.6750 | 0.0446 | 0.6211 | 0.6173 |
|
88 |
+
| 17.1081 | 0.5272 | 165 | 8.5070 | 0.7013 | 0.0547 | 0.6479 | 0.6420 |
|
89 |
+
| 14.2012 | 0.5431 | 170 | 8.3725 | 0.7220 | 0.0544 | 0.6553 | 0.6525 |
|
90 |
+
| 13.5024 | 0.5591 | 175 | 8.2316 | 0.7125 | 0.0324 | 0.6540 | 0.6495 |
|
91 |
+
| 13.2137 | 0.5751 | 180 | 8.1178 | 0.7591 | 0.0626 | 0.6776 | 0.6720 |
|
92 |
+
| 12.6791 | 0.5911 | 185 | 8.0139 | 0.7564 | 0.0302 | 0.6845 | 0.6840 |
|
93 |
+
| 13.4419 | 0.6070 | 190 | 7.9119 | 0.7047 | 0.0277 | 0.6559 | 0.6484 |
|
94 |
+
| 13.469 | 0.6230 | 195 | 7.8019 | 0.7849 | 0.0268 | 0.7215 | 0.7189 |
|
95 |
+
| 12.8491 | 0.6390 | 200 | 7.6875 | 0.8839 | 0.0264 | 0.8145 | 0.8153 |
|
96 |
+
| 12.8009 | 0.6550 | 205 | 7.5978 | 0.9797 | 0.0375 | 0.8922 | 0.8930 |
|
97 |
+
| 13.0495 | 0.6709 | 210 | 7.5245 | 1.0712 | 0.0504 | 0.9587 | 0.9579 |
|
98 |
+
| 12.3307 | 0.6869 | 215 | 7.4464 | 1.0918 | 0.0523 | 1.0047 | 0.9994 |
|
99 |
+
| 11.1893 | 0.7029 | 220 | 7.3770 | 1.1632 | 0.0695 | 1.0571 | 1.0527 |
|
100 |
+
| 12.0019 | 0.7188 | 225 | 7.3174 | 1.1872 | 0.0522 | 1.0827 | 1.0821 |
|
101 |
+
| 10.5739 | 0.7348 | 230 | 7.2509 | 1.1771 | 0.0665 | 1.0618 | 1.0630 |
|
102 |
+
| 10.7484 | 0.7508 | 235 | 7.1847 | 1.3403 | 0.0782 | 1.1967 | 1.1933 |
|
103 |
+
| 11.0539 | 0.7668 | 240 | 7.1230 | 1.4099 | 0.1009 | 1.2615 | 1.2612 |
|
104 |
+
| 10.6808 | 0.7827 | 245 | 7.0601 | 1.5268 | 0.0882 | 1.3528 | 1.3506 |
|
105 |
+
| 10.0456 | 0.7987 | 250 | 7.0148 | 1.4664 | 0.0789 | 1.3207 | 1.3142 |
|
106 |
+
| 9.7895 | 0.8147 | 255 | 6.9850 | 1.6529 | 0.0969 | 1.4578 | 1.4445 |
|
107 |
+
| 9.3146 | 0.8307 | 260 | 6.9547 | 1.7461 | 0.0943 | 1.5750 | 1.5566 |
|
108 |
+
| 9.8935 | 0.8466 | 265 | 6.9348 | 1.9384 | 0.1090 | 1.7219 | 1.7093 |
|
109 |
+
| 9.3272 | 0.8626 | 270 | 6.9348 | 1.8664 | 0.1143 | 1.6837 | 1.6758 |
|
110 |
+
| 9.4551 | 0.8786 | 275 | 6.9497 | 2.1360 | 0.1578 | 1.9404 | 1.9297 |
|
111 |
+
| 8.7474 | 0.8946 | 280 | 6.9095 | 2.1561 | 0.1494 | 1.9453 | 1.9398 |
|
112 |
+
| 8.8361 | 0.9105 | 285 | 6.8680 | 2.1476 | 0.1304 | 1.9360 | 1.9314 |
|
113 |
+
| 10.3327 | 0.9265 | 290 | 6.8129 | 2.2233 | 0.1330 | 1.9752 | 1.9732 |
|
114 |
+
| 9.6949 | 0.9425 | 295 | 6.7423 | 2.2698 | 0.1491 | 2.0114 | 2.0057 |
|
115 |
+
| 9.2422 | 0.9585 | 300 | 6.6728 | 2.2544 | 0.1332 | 2.0282 | 2.0281 |
|
116 |
+
| 9.1457 | 0.9744 | 305 | 6.5924 | 2.1699 | 0.1038 | 1.9641 | 1.9592 |
|
117 |
+
| 8.4371 | 0.9904 | 310 | 6.5061 | 2.2267 | 0.1423 | 2.0247 | 2.0174 |
|
118 |
+
| 8.8187 | 1.0064 | 315 | 6.4224 | 2.3070 | 0.1251 | 2.1206 | 2.1144 |
|
119 |
+
| 8.6228 | 1.0224 | 320 | 6.3316 | 2.3591 | 0.1070 | 2.1583 | 2.1714 |
|
120 |
+
| 7.9446 | 1.0383 | 325 | 6.2488 | 2.3552 | 0.1209 | 2.1538 | 2.1659 |
|
121 |
+
| 7.9126 | 1.0543 | 330 | 6.1856 | 2.3870 | 0.1292 | 2.1680 | 2.1668 |
|
122 |
+
| 8.0568 | 1.0703 | 335 | 6.1166 | 2.5029 | 0.1254 | 2.2559 | 2.2636 |
|
123 |
+
| 7.5392 | 1.0863 | 340 | 6.0326 | 2.4650 | 0.1265 | 2.2809 | 2.2768 |
|
124 |
+
| 8.2361 | 1.1022 | 345 | 5.9569 | 2.4594 | 0.1041 | 2.2155 | 2.2160 |
|
125 |
+
| 7.7452 | 1.1182 | 350 | 5.8964 | 2.4663 | 0.0998 | 2.2324 | 2.2333 |
|
126 |
+
| 7.6389 | 1.1342 | 355 | 5.8526 | 2.4997 | 0.1063 | 2.2902 | 2.2822 |
|
127 |
+
| 7.6098 | 1.1502 | 360 | 5.8106 | 2.6162 | 0.1157 | 2.3610 | 2.3596 |
|
128 |
+
| 7.8916 | 1.1661 | 365 | 5.7841 | 2.5536 | 0.0968 | 2.3276 | 2.3290 |
|
129 |
+
| 7.5782 | 1.1821 | 370 | 5.7585 | 2.5692 | 0.1032 | 2.3456 | 2.3406 |
|
130 |
+
| 7.3974 | 1.1981 | 375 | 5.7402 | 2.5963 | 0.1286 | 2.3806 | 2.3711 |
|
131 |
+
| 7.0614 | 1.2141 | 380 | 5.7159 | 2.6104 | 0.0990 | 2.3693 | 2.3758 |
|
132 |
+
| 7.2043 | 1.2300 | 385 | 5.6968 | 2.6200 | 0.0934 | 2.3816 | 2.3891 |
|
133 |
+
| 6.996 | 1.2460 | 390 | 5.6787 | 2.5952 | 0.0641 | 2.4221 | 2.4286 |
|
134 |
+
| 8.2705 | 1.2620 | 395 | 5.6632 | 2.6169 | 0.0403 | 2.4257 | 2.4329 |
|
135 |
+
| 7.1852 | 1.2780 | 400 | 5.6461 | 2.5815 | 0.0522 | 2.4163 | 2.4257 |
|
136 |
+
| 7.1047 | 1.2939 | 405 | 5.6273 | 2.5892 | 0.0486 | 2.4551 | 2.4584 |
|
137 |
+
| 7.0063 | 1.3099 | 410 | 5.6064 | 2.5683 | 0.0327 | 2.4328 | 2.4334 |
|
138 |
+
| 6.8297 | 1.3259 | 415 | 5.5840 | 2.5684 | 0.0425 | 2.4205 | 2.4136 |
|
139 |
+
| 6.7474 | 1.3419 | 420 | 5.5610 | 2.5945 | 0.0279 | 2.4552 | 2.4478 |
|
140 |
+
| 7.0426 | 1.3578 | 425 | 5.5415 | 2.5908 | 0.0120 | 2.4275 | 2.4241 |
|
141 |
+
| 6.6945 | 1.3738 | 430 | 5.5259 | 2.5609 | 0.0086 | 2.4019 | 2.4040 |
|
142 |
+
| 6.8208 | 1.3898 | 435 | 5.5160 | 2.6132 | 0.0086 | 2.4673 | 2.4634 |
|
143 |
+
| 6.6174 | 1.4058 | 440 | 5.5070 | 2.6443 | 0.0187 | 2.4737 | 2.4660 |
|
144 |
+
| 6.7205 | 1.4217 | 445 | 5.4988 | 2.6701 | 0.0236 | 2.5099 | 2.4985 |
|
145 |
+
| 6.6941 | 1.4377 | 450 | 5.4915 | 2.6858 | 0.0236 | 2.5133 | 2.5047 |
|
146 |
+
| 6.5988 | 1.4537 | 455 | 5.4851 | 2.6766 | 0.0349 | 2.5185 | 2.5128 |
|
147 |
+
| 6.4683 | 1.4696 | 460 | 5.4767 | 2.6661 | 0.0347 | 2.4922 | 2.4918 |
|
148 |
+
| 6.7409 | 1.4856 | 465 | 5.4675 | 2.6519 | 0.0347 | 2.5065 | 2.5077 |
|
149 |
+
| 6.9734 | 1.5016 | 470 | 5.4599 | 2.6663 | 0.0431 | 2.5285 | 2.5313 |
|
150 |
+
| 6.7049 | 1.5176 | 475 | 5.4536 | 2.6913 | 0.0428 | 2.5617 | 2.5574 |
|
151 |
+
| 7.1744 | 1.5335 | 480 | 5.4483 | 2.7426 | 0.0469 | 2.5896 | 2.5873 |
|
152 |
+
| 6.6163 | 1.5495 | 485 | 5.4434 | 2.7223 | 0.0428 | 2.5761 | 2.5782 |
|
153 |
+
| 6.6025 | 1.5655 | 490 | 5.4381 | 2.6981 | 0.0379 | 2.5405 | 2.5406 |
|
154 |
+
| 6.4328 | 1.5815 | 495 | 5.4326 | 2.6555 | 0.0321 | 2.5019 | 2.4957 |
|
155 |
+
| 6.5182 | 1.5974 | 500 | 5.4278 | 2.7413 | 0.0445 | 2.5816 | 2.5765 |
|
156 |
+
| 6.6248 | 1.6134 | 505 | 5.4226 | 2.7559 | 0.0384 | 2.5907 | 2.5833 |
|
157 |
+
| 6.4422 | 1.6294 | 510 | 5.4180 | 2.8097 | 0.0384 | 2.6591 | 2.6516 |
|
158 |
+
| 6.3315 | 1.6454 | 515 | 5.4139 | 2.8195 | 0.0345 | 2.6772 | 2.6692 |
|
159 |
+
| 6.3602 | 1.6613 | 520 | 5.4077 | 2.8024 | 0.0435 | 2.6610 | 2.6544 |
|
160 |
+
| 6.3096 | 1.6773 | 525 | 5.4016 | 2.8611 | 0.0558 | 2.7244 | 2.7161 |
|
161 |
+
| 6.4627 | 1.6933 | 530 | 5.3956 | 2.8914 | 0.0558 | 2.7576 | 2.7547 |
|
162 |
+
| 7.0027 | 1.7093 | 535 | 5.3912 | 2.9207 | 0.0601 | 2.7619 | 2.7592 |
|
163 |
+
| 6.6364 | 1.7252 | 540 | 5.3880 | 2.9260 | 0.0601 | 2.7612 | 2.7558 |
|
164 |
+
| 6.3329 | 1.7412 | 545 | 5.3835 | 2.9258 | 0.0631 | 2.7616 | 2.7580 |
|
165 |
+
| 6.3528 | 1.7572 | 550 | 5.3783 | 2.9378 | 0.0631 | 2.7630 | 2.7573 |
|
166 |
+
| 6.3083 | 1.7732 | 555 | 5.3731 | 2.9500 | 0.0631 | 2.7680 | 2.7632 |
|
167 |
+
| 6.3824 | 1.7891 | 560 | 5.3686 | 2.9599 | 0.0681 | 2.7896 | 2.7882 |
|
168 |
+
| 6.2145 | 1.8051 | 565 | 5.3646 | 2.9371 | 0.0644 | 2.7612 | 2.7619 |
|
169 |
+
| 6.5271 | 1.8211 | 570 | 5.3605 | 2.9350 | 0.0647 | 2.7695 | 2.7717 |
|
170 |
+
| 6.5508 | 1.8371 | 575 | 5.3568 | 2.9277 | 0.0524 | 2.7676 | 2.7682 |
|
171 |
+
| 6.4093 | 1.8530 | 580 | 5.3551 | 2.9401 | 0.0524 | 2.7711 | 2.7727 |
|
172 |
+
| 6.5111 | 1.8690 | 585 | 5.3532 | 2.9682 | 0.0641 | 2.7947 | 2.7934 |
|
173 |
+
| 6.459 | 1.8850 | 590 | 5.3513 | 2.9682 | 0.0641 | 2.7946 | 2.7933 |
|
174 |
+
| 6.3278 | 1.9010 | 595 | 5.3497 | 2.9685 | 0.0641 | 2.7994 | 2.7970 |
|
175 |
+
| 6.7423 | 1.9169 | 600 | 5.3486 | 2.9733 | 0.0641 | 2.7993 | 2.7969 |
|
176 |
+
| 6.5692 | 1.9329 | 605 | 5.3476 | 2.9732 | 0.0641 | 2.8092 | 2.8055 |
|
177 |
+
| 6.3758 | 1.9489 | 610 | 5.3467 | 2.9784 | 0.0640 | 2.8074 | 2.8060 |
|
178 |
+
| 6.4735 | 1.9649 | 615 | 5.3460 | 2.9749 | 0.0640 | 2.8028 | 2.8034 |
|
179 |
+
| 6.2938 | 1.9808 | 620 | 5.3455 | 2.9749 | 0.0640 | 2.8027 | 2.8033 |
|
180 |
+
| 6.2542 | 1.9968 | 625 | 5.3452 | 2.9750 | 0.0640 | 2.8027 | 2.8035 |
|
181 |
+
|
182 |
+
|
183 |
+
### Framework versions
|
184 |
+
|
185 |
+
- PEFT 0.14.0
|
186 |
+
- Transformers 4.49.0
|
187 |
+
- Pytorch 2.6.0+cu124
|
188 |
+
- Datasets 3.3.2
|
189 |
+
- Tokenizers 0.21.0
|
adapter_config.json
ADDED
@@ -0,0 +1,32 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"alpha_pattern": {},
|
3 |
+
"auto_mapping": null,
|
4 |
+
"base_model_name_or_path": "google/mt5-small",
|
5 |
+
"bias": "none",
|
6 |
+
"eva_config": null,
|
7 |
+
"exclude_modules": null,
|
8 |
+
"fan_in_fan_out": false,
|
9 |
+
"inference_mode": true,
|
10 |
+
"init_lora_weights": true,
|
11 |
+
"layer_replication": null,
|
12 |
+
"layers_pattern": null,
|
13 |
+
"layers_to_transform": null,
|
14 |
+
"loftq_config": {},
|
15 |
+
"lora_alpha": 16,
|
16 |
+
"lora_bias": false,
|
17 |
+
"lora_dropout": 0.2,
|
18 |
+
"megatron_config": null,
|
19 |
+
"megatron_core": "megatron.core",
|
20 |
+
"modules_to_save": null,
|
21 |
+
"peft_type": "LORA",
|
22 |
+
"r": 1,
|
23 |
+
"rank_pattern": {},
|
24 |
+
"revision": null,
|
25 |
+
"target_modules": [
|
26 |
+
"v",
|
27 |
+
"q"
|
28 |
+
],
|
29 |
+
"task_type": "SEQ_2_SEQ_LM",
|
30 |
+
"use_dora": false,
|
31 |
+
"use_rslora": false
|
32 |
+
}
|
adapter_model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c2da1bfb038733ec642cca80a304a8efb2efe57f3a7da2e3936903f686f3767a
|
3 |
+
size 185072
|
runs/Mar10_23-08-48_1412920010036/events.out.tfevents.1741662535.1412920010036.5471.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d86bf84720e7f90ac974efa75515570b134c9d405e77c7b946753da0a78708c9
|
3 |
+
size 91015
|
special_tokens_map.json
ADDED
@@ -0,0 +1,23 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"eos_token": {
|
3 |
+
"content": "</s>",
|
4 |
+
"lstrip": false,
|
5 |
+
"normalized": false,
|
6 |
+
"rstrip": false,
|
7 |
+
"single_word": false
|
8 |
+
},
|
9 |
+
"pad_token": {
|
10 |
+
"content": "<pad>",
|
11 |
+
"lstrip": false,
|
12 |
+
"normalized": false,
|
13 |
+
"rstrip": false,
|
14 |
+
"single_word": false
|
15 |
+
},
|
16 |
+
"unk_token": {
|
17 |
+
"content": "<unk>",
|
18 |
+
"lstrip": false,
|
19 |
+
"normalized": false,
|
20 |
+
"rstrip": false,
|
21 |
+
"single_word": false
|
22 |
+
}
|
23 |
+
}
|
spiece.model
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ef78f86560d809067d12bac6c09f19a462cb3af3f54d2b8acbba26e1433125d6
|
3 |
+
size 4309802
|
tokenizer.json
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:90ed658667887a6a72b5f071e2e34bd3d9c562683f9c71a2f9c7c1c414e6c5bc
|
3 |
+
size 16350026
|
tokenizer_config.json
ADDED
@@ -0,0 +1,840 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"add_prefix_space": null,
|
3 |
+
"added_tokens_decoder": {
|
4 |
+
"0": {
|
5 |
+
"content": "<pad>",
|
6 |
+
"lstrip": false,
|
7 |
+
"normalized": false,
|
8 |
+
"rstrip": false,
|
9 |
+
"single_word": false,
|
10 |
+
"special": true
|
11 |
+
},
|
12 |
+
"1": {
|
13 |
+
"content": "</s>",
|
14 |
+
"lstrip": false,
|
15 |
+
"normalized": false,
|
16 |
+
"rstrip": false,
|
17 |
+
"single_word": false,
|
18 |
+
"special": true
|
19 |
+
},
|
20 |
+
"2": {
|
21 |
+
"content": "<unk>",
|
22 |
+
"lstrip": false,
|
23 |
+
"normalized": false,
|
24 |
+
"rstrip": false,
|
25 |
+
"single_word": false,
|
26 |
+
"special": true
|
27 |
+
},
|
28 |
+
"250000": {
|
29 |
+
"content": "β<extra_id_99>",
|
30 |
+
"lstrip": false,
|
31 |
+
"normalized": false,
|
32 |
+
"rstrip": false,
|
33 |
+
"single_word": false,
|
34 |
+
"special": false
|
35 |
+
},
|
36 |
+
"250001": {
|
37 |
+
"content": "β<extra_id_98>",
|
38 |
+
"lstrip": false,
|
39 |
+
"normalized": false,
|
40 |
+
"rstrip": false,
|
41 |
+
"single_word": false,
|
42 |
+
"special": false
|
43 |
+
},
|
44 |
+
"250002": {
|
45 |
+
"content": "β<extra_id_97>",
|
46 |
+
"lstrip": false,
|
47 |
+
"normalized": false,
|
48 |
+
"rstrip": false,
|
49 |
+
"single_word": false,
|
50 |
+
"special": false
|
51 |
+
},
|
52 |
+
"250003": {
|
53 |
+
"content": "β<extra_id_96>",
|
54 |
+
"lstrip": false,
|
55 |
+
"normalized": false,
|
56 |
+
"rstrip": false,
|
57 |
+
"single_word": false,
|
58 |
+
"special": false
|
59 |
+
},
|
60 |
+
"250004": {
|
61 |
+
"content": "β<extra_id_95>",
|
62 |
+
"lstrip": false,
|
63 |
+
"normalized": false,
|
64 |
+
"rstrip": false,
|
65 |
+
"single_word": false,
|
66 |
+
"special": false
|
67 |
+
},
|
68 |
+
"250005": {
|
69 |
+
"content": "β<extra_id_94>",
|
70 |
+
"lstrip": false,
|
71 |
+
"normalized": false,
|
72 |
+
"rstrip": false,
|
73 |
+
"single_word": false,
|
74 |
+
"special": false
|
75 |
+
},
|
76 |
+
"250006": {
|
77 |
+
"content": "β<extra_id_93>",
|
78 |
+
"lstrip": false,
|
79 |
+
"normalized": false,
|
80 |
+
"rstrip": false,
|
81 |
+
"single_word": false,
|
82 |
+
"special": false
|
83 |
+
},
|
84 |
+
"250007": {
|
85 |
+
"content": "β<extra_id_92>",
|
86 |
+
"lstrip": false,
|
87 |
+
"normalized": false,
|
88 |
+
"rstrip": false,
|
89 |
+
"single_word": false,
|
90 |
+
"special": false
|
91 |
+
},
|
92 |
+
"250008": {
|
93 |
+
"content": "β<extra_id_91>",
|
94 |
+
"lstrip": false,
|
95 |
+
"normalized": false,
|
96 |
+
"rstrip": false,
|
97 |
+
"single_word": false,
|
98 |
+
"special": false
|
99 |
+
},
|
100 |
+
"250009": {
|
101 |
+
"content": "β<extra_id_90>",
|
102 |
+
"lstrip": false,
|
103 |
+
"normalized": false,
|
104 |
+
"rstrip": false,
|
105 |
+
"single_word": false,
|
106 |
+
"special": false
|
107 |
+
},
|
108 |
+
"250010": {
|
109 |
+
"content": "β<extra_id_89>",
|
110 |
+
"lstrip": false,
|
111 |
+
"normalized": false,
|
112 |
+
"rstrip": false,
|
113 |
+
"single_word": false,
|
114 |
+
"special": false
|
115 |
+
},
|
116 |
+
"250011": {
|
117 |
+
"content": "β<extra_id_88>",
|
118 |
+
"lstrip": false,
|
119 |
+
"normalized": false,
|
120 |
+
"rstrip": false,
|
121 |
+
"single_word": false,
|
122 |
+
"special": false
|
123 |
+
},
|
124 |
+
"250012": {
|
125 |
+
"content": "β<extra_id_87>",
|
126 |
+
"lstrip": false,
|
127 |
+
"normalized": false,
|
128 |
+
"rstrip": false,
|
129 |
+
"single_word": false,
|
130 |
+
"special": false
|
131 |
+
},
|
132 |
+
"250013": {
|
133 |
+
"content": "β<extra_id_86>",
|
134 |
+
"lstrip": false,
|
135 |
+
"normalized": false,
|
136 |
+
"rstrip": false,
|
137 |
+
"single_word": false,
|
138 |
+
"special": false
|
139 |
+
},
|
140 |
+
"250014": {
|
141 |
+
"content": "β<extra_id_85>",
|
142 |
+
"lstrip": false,
|
143 |
+
"normalized": false,
|
144 |
+
"rstrip": false,
|
145 |
+
"single_word": false,
|
146 |
+
"special": false
|
147 |
+
},
|
148 |
+
"250015": {
|
149 |
+
"content": "β<extra_id_84>",
|
150 |
+
"lstrip": false,
|
151 |
+
"normalized": false,
|
152 |
+
"rstrip": false,
|
153 |
+
"single_word": false,
|
154 |
+
"special": false
|
155 |
+
},
|
156 |
+
"250016": {
|
157 |
+
"content": "β<extra_id_83>",
|
158 |
+
"lstrip": false,
|
159 |
+
"normalized": false,
|
160 |
+
"rstrip": false,
|
161 |
+
"single_word": false,
|
162 |
+
"special": false
|
163 |
+
},
|
164 |
+
"250017": {
|
165 |
+
"content": "β<extra_id_82>",
|
166 |
+
"lstrip": false,
|
167 |
+
"normalized": false,
|
168 |
+
"rstrip": false,
|
169 |
+
"single_word": false,
|
170 |
+
"special": false
|
171 |
+
},
|
172 |
+
"250018": {
|
173 |
+
"content": "β<extra_id_81>",
|
174 |
+
"lstrip": false,
|
175 |
+
"normalized": false,
|
176 |
+
"rstrip": false,
|
177 |
+
"single_word": false,
|
178 |
+
"special": false
|
179 |
+
},
|
180 |
+
"250019": {
|
181 |
+
"content": "β<extra_id_80>",
|
182 |
+
"lstrip": false,
|
183 |
+
"normalized": false,
|
184 |
+
"rstrip": false,
|
185 |
+
"single_word": false,
|
186 |
+
"special": false
|
187 |
+
},
|
188 |
+
"250020": {
|
189 |
+
"content": "β<extra_id_79>",
|
190 |
+
"lstrip": false,
|
191 |
+
"normalized": false,
|
192 |
+
"rstrip": false,
|
193 |
+
"single_word": false,
|
194 |
+
"special": false
|
195 |
+
},
|
196 |
+
"250021": {
|
197 |
+
"content": "β<extra_id_78>",
|
198 |
+
"lstrip": false,
|
199 |
+
"normalized": false,
|
200 |
+
"rstrip": false,
|
201 |
+
"single_word": false,
|
202 |
+
"special": false
|
203 |
+
},
|
204 |
+
"250022": {
|
205 |
+
"content": "β<extra_id_77>",
|
206 |
+
"lstrip": false,
|
207 |
+
"normalized": false,
|
208 |
+
"rstrip": false,
|
209 |
+
"single_word": false,
|
210 |
+
"special": false
|
211 |
+
},
|
212 |
+
"250023": {
|
213 |
+
"content": "β<extra_id_76>",
|
214 |
+
"lstrip": false,
|
215 |
+
"normalized": false,
|
216 |
+
"rstrip": false,
|
217 |
+
"single_word": false,
|
218 |
+
"special": false
|
219 |
+
},
|
220 |
+
"250024": {
|
221 |
+
"content": "β<extra_id_75>",
|
222 |
+
"lstrip": false,
|
223 |
+
"normalized": false,
|
224 |
+
"rstrip": false,
|
225 |
+
"single_word": false,
|
226 |
+
"special": false
|
227 |
+
},
|
228 |
+
"250025": {
|
229 |
+
"content": "β<extra_id_74>",
|
230 |
+
"lstrip": false,
|
231 |
+
"normalized": false,
|
232 |
+
"rstrip": false,
|
233 |
+
"single_word": false,
|
234 |
+
"special": false
|
235 |
+
},
|
236 |
+
"250026": {
|
237 |
+
"content": "β<extra_id_73>",
|
238 |
+
"lstrip": false,
|
239 |
+
"normalized": false,
|
240 |
+
"rstrip": false,
|
241 |
+
"single_word": false,
|
242 |
+
"special": false
|
243 |
+
},
|
244 |
+
"250027": {
|
245 |
+
"content": "β<extra_id_72>",
|
246 |
+
"lstrip": false,
|
247 |
+
"normalized": false,
|
248 |
+
"rstrip": false,
|
249 |
+
"single_word": false,
|
250 |
+
"special": false
|
251 |
+
},
|
252 |
+
"250028": {
|
253 |
+
"content": "β<extra_id_71>",
|
254 |
+
"lstrip": false,
|
255 |
+
"normalized": false,
|
256 |
+
"rstrip": false,
|
257 |
+
"single_word": false,
|
258 |
+
"special": false
|
259 |
+
},
|
260 |
+
"250029": {
|
261 |
+
"content": "β<extra_id_70>",
|
262 |
+
"lstrip": false,
|
263 |
+
"normalized": false,
|
264 |
+
"rstrip": false,
|
265 |
+
"single_word": false,
|
266 |
+
"special": false
|
267 |
+
},
|
268 |
+
"250030": {
|
269 |
+
"content": "β<extra_id_69>",
|
270 |
+
"lstrip": false,
|
271 |
+
"normalized": false,
|
272 |
+
"rstrip": false,
|
273 |
+
"single_word": false,
|
274 |
+
"special": false
|
275 |
+
},
|
276 |
+
"250031": {
|
277 |
+
"content": "β<extra_id_68>",
|
278 |
+
"lstrip": false,
|
279 |
+
"normalized": false,
|
280 |
+
"rstrip": false,
|
281 |
+
"single_word": false,
|
282 |
+
"special": false
|
283 |
+
},
|
284 |
+
"250032": {
|
285 |
+
"content": "β<extra_id_67>",
|
286 |
+
"lstrip": false,
|
287 |
+
"normalized": false,
|
288 |
+
"rstrip": false,
|
289 |
+
"single_word": false,
|
290 |
+
"special": false
|
291 |
+
},
|
292 |
+
"250033": {
|
293 |
+
"content": "β<extra_id_66>",
|
294 |
+
"lstrip": false,
|
295 |
+
"normalized": false,
|
296 |
+
"rstrip": false,
|
297 |
+
"single_word": false,
|
298 |
+
"special": false
|
299 |
+
},
|
300 |
+
"250034": {
|
301 |
+
"content": "β<extra_id_65>",
|
302 |
+
"lstrip": false,
|
303 |
+
"normalized": false,
|
304 |
+
"rstrip": false,
|
305 |
+
"single_word": false,
|
306 |
+
"special": false
|
307 |
+
},
|
308 |
+
"250035": {
|
309 |
+
"content": "β<extra_id_64>",
|
310 |
+
"lstrip": false,
|
311 |
+
"normalized": false,
|
312 |
+
"rstrip": false,
|
313 |
+
"single_word": false,
|
314 |
+
"special": false
|
315 |
+
},
|
316 |
+
"250036": {
|
317 |
+
"content": "β<extra_id_63>",
|
318 |
+
"lstrip": false,
|
319 |
+
"normalized": false,
|
320 |
+
"rstrip": false,
|
321 |
+
"single_word": false,
|
322 |
+
"special": false
|
323 |
+
},
|
324 |
+
"250037": {
|
325 |
+
"content": "β<extra_id_62>",
|
326 |
+
"lstrip": false,
|
327 |
+
"normalized": false,
|
328 |
+
"rstrip": false,
|
329 |
+
"single_word": false,
|
330 |
+
"special": false
|
331 |
+
},
|
332 |
+
"250038": {
|
333 |
+
"content": "β<extra_id_61>",
|
334 |
+
"lstrip": false,
|
335 |
+
"normalized": false,
|
336 |
+
"rstrip": false,
|
337 |
+
"single_word": false,
|
338 |
+
"special": false
|
339 |
+
},
|
340 |
+
"250039": {
|
341 |
+
"content": "β<extra_id_60>",
|
342 |
+
"lstrip": false,
|
343 |
+
"normalized": false,
|
344 |
+
"rstrip": false,
|
345 |
+
"single_word": false,
|
346 |
+
"special": false
|
347 |
+
},
|
348 |
+
"250040": {
|
349 |
+
"content": "β<extra_id_59>",
|
350 |
+
"lstrip": false,
|
351 |
+
"normalized": false,
|
352 |
+
"rstrip": false,
|
353 |
+
"single_word": false,
|
354 |
+
"special": false
|
355 |
+
},
|
356 |
+
"250041": {
|
357 |
+
"content": "β<extra_id_58>",
|
358 |
+
"lstrip": false,
|
359 |
+
"normalized": false,
|
360 |
+
"rstrip": false,
|
361 |
+
"single_word": false,
|
362 |
+
"special": false
|
363 |
+
},
|
364 |
+
"250042": {
|
365 |
+
"content": "β<extra_id_57>",
|
366 |
+
"lstrip": false,
|
367 |
+
"normalized": false,
|
368 |
+
"rstrip": false,
|
369 |
+
"single_word": false,
|
370 |
+
"special": false
|
371 |
+
},
|
372 |
+
"250043": {
|
373 |
+
"content": "β<extra_id_56>",
|
374 |
+
"lstrip": false,
|
375 |
+
"normalized": false,
|
376 |
+
"rstrip": false,
|
377 |
+
"single_word": false,
|
378 |
+
"special": false
|
379 |
+
},
|
380 |
+
"250044": {
|
381 |
+
"content": "β<extra_id_55>",
|
382 |
+
"lstrip": false,
|
383 |
+
"normalized": false,
|
384 |
+
"rstrip": false,
|
385 |
+
"single_word": false,
|
386 |
+
"special": false
|
387 |
+
},
|
388 |
+
"250045": {
|
389 |
+
"content": "β<extra_id_54>",
|
390 |
+
"lstrip": false,
|
391 |
+
"normalized": false,
|
392 |
+
"rstrip": false,
|
393 |
+
"single_word": false,
|
394 |
+
"special": false
|
395 |
+
},
|
396 |
+
"250046": {
|
397 |
+
"content": "β<extra_id_53>",
|
398 |
+
"lstrip": false,
|
399 |
+
"normalized": false,
|
400 |
+
"rstrip": false,
|
401 |
+
"single_word": false,
|
402 |
+
"special": false
|
403 |
+
},
|
404 |
+
"250047": {
|
405 |
+
"content": "β<extra_id_52>",
|
406 |
+
"lstrip": false,
|
407 |
+
"normalized": false,
|
408 |
+
"rstrip": false,
|
409 |
+
"single_word": false,
|
410 |
+
"special": false
|
411 |
+
},
|
412 |
+
"250048": {
|
413 |
+
"content": "β<extra_id_51>",
|
414 |
+
"lstrip": false,
|
415 |
+
"normalized": false,
|
416 |
+
"rstrip": false,
|
417 |
+
"single_word": false,
|
418 |
+
"special": false
|
419 |
+
},
|
420 |
+
"250049": {
|
421 |
+
"content": "β<extra_id_50>",
|
422 |
+
"lstrip": false,
|
423 |
+
"normalized": false,
|
424 |
+
"rstrip": false,
|
425 |
+
"single_word": false,
|
426 |
+
"special": false
|
427 |
+
},
|
428 |
+
"250050": {
|
429 |
+
"content": "οΏ½οΏ½οΏ½<extra_id_49>",
|
430 |
+
"lstrip": false,
|
431 |
+
"normalized": false,
|
432 |
+
"rstrip": false,
|
433 |
+
"single_word": false,
|
434 |
+
"special": false
|
435 |
+
},
|
436 |
+
"250051": {
|
437 |
+
"content": "β<extra_id_48>",
|
438 |
+
"lstrip": false,
|
439 |
+
"normalized": false,
|
440 |
+
"rstrip": false,
|
441 |
+
"single_word": false,
|
442 |
+
"special": false
|
443 |
+
},
|
444 |
+
"250052": {
|
445 |
+
"content": "β<extra_id_47>",
|
446 |
+
"lstrip": false,
|
447 |
+
"normalized": false,
|
448 |
+
"rstrip": false,
|
449 |
+
"single_word": false,
|
450 |
+
"special": false
|
451 |
+
},
|
452 |
+
"250053": {
|
453 |
+
"content": "β<extra_id_46>",
|
454 |
+
"lstrip": false,
|
455 |
+
"normalized": false,
|
456 |
+
"rstrip": false,
|
457 |
+
"single_word": false,
|
458 |
+
"special": false
|
459 |
+
},
|
460 |
+
"250054": {
|
461 |
+
"content": "β<extra_id_45>",
|
462 |
+
"lstrip": false,
|
463 |
+
"normalized": false,
|
464 |
+
"rstrip": false,
|
465 |
+
"single_word": false,
|
466 |
+
"special": false
|
467 |
+
},
|
468 |
+
"250055": {
|
469 |
+
"content": "β<extra_id_44>",
|
470 |
+
"lstrip": false,
|
471 |
+
"normalized": false,
|
472 |
+
"rstrip": false,
|
473 |
+
"single_word": false,
|
474 |
+
"special": false
|
475 |
+
},
|
476 |
+
"250056": {
|
477 |
+
"content": "β<extra_id_43>",
|
478 |
+
"lstrip": false,
|
479 |
+
"normalized": false,
|
480 |
+
"rstrip": false,
|
481 |
+
"single_word": false,
|
482 |
+
"special": false
|
483 |
+
},
|
484 |
+
"250057": {
|
485 |
+
"content": "β<extra_id_42>",
|
486 |
+
"lstrip": false,
|
487 |
+
"normalized": false,
|
488 |
+
"rstrip": false,
|
489 |
+
"single_word": false,
|
490 |
+
"special": false
|
491 |
+
},
|
492 |
+
"250058": {
|
493 |
+
"content": "β<extra_id_41>",
|
494 |
+
"lstrip": false,
|
495 |
+
"normalized": false,
|
496 |
+
"rstrip": false,
|
497 |
+
"single_word": false,
|
498 |
+
"special": false
|
499 |
+
},
|
500 |
+
"250059": {
|
501 |
+
"content": "β<extra_id_40>",
|
502 |
+
"lstrip": false,
|
503 |
+
"normalized": false,
|
504 |
+
"rstrip": false,
|
505 |
+
"single_word": false,
|
506 |
+
"special": false
|
507 |
+
},
|
508 |
+
"250060": {
|
509 |
+
"content": "β<extra_id_39>",
|
510 |
+
"lstrip": false,
|
511 |
+
"normalized": false,
|
512 |
+
"rstrip": false,
|
513 |
+
"single_word": false,
|
514 |
+
"special": false
|
515 |
+
},
|
516 |
+
"250061": {
|
517 |
+
"content": "β<extra_id_38>",
|
518 |
+
"lstrip": false,
|
519 |
+
"normalized": false,
|
520 |
+
"rstrip": false,
|
521 |
+
"single_word": false,
|
522 |
+
"special": false
|
523 |
+
},
|
524 |
+
"250062": {
|
525 |
+
"content": "β<extra_id_37>",
|
526 |
+
"lstrip": false,
|
527 |
+
"normalized": false,
|
528 |
+
"rstrip": false,
|
529 |
+
"single_word": false,
|
530 |
+
"special": false
|
531 |
+
},
|
532 |
+
"250063": {
|
533 |
+
"content": "β<extra_id_36>",
|
534 |
+
"lstrip": false,
|
535 |
+
"normalized": false,
|
536 |
+
"rstrip": false,
|
537 |
+
"single_word": false,
|
538 |
+
"special": false
|
539 |
+
},
|
540 |
+
"250064": {
|
541 |
+
"content": "β<extra_id_35>",
|
542 |
+
"lstrip": false,
|
543 |
+
"normalized": false,
|
544 |
+
"rstrip": false,
|
545 |
+
"single_word": false,
|
546 |
+
"special": false
|
547 |
+
},
|
548 |
+
"250065": {
|
549 |
+
"content": "β<extra_id_34>",
|
550 |
+
"lstrip": false,
|
551 |
+
"normalized": false,
|
552 |
+
"rstrip": false,
|
553 |
+
"single_word": false,
|
554 |
+
"special": false
|
555 |
+
},
|
556 |
+
"250066": {
|
557 |
+
"content": "β<extra_id_33>",
|
558 |
+
"lstrip": false,
|
559 |
+
"normalized": false,
|
560 |
+
"rstrip": false,
|
561 |
+
"single_word": false,
|
562 |
+
"special": false
|
563 |
+
},
|
564 |
+
"250067": {
|
565 |
+
"content": "β<extra_id_32>",
|
566 |
+
"lstrip": false,
|
567 |
+
"normalized": false,
|
568 |
+
"rstrip": false,
|
569 |
+
"single_word": false,
|
570 |
+
"special": false
|
571 |
+
},
|
572 |
+
"250068": {
|
573 |
+
"content": "β<extra_id_31>",
|
574 |
+
"lstrip": false,
|
575 |
+
"normalized": false,
|
576 |
+
"rstrip": false,
|
577 |
+
"single_word": false,
|
578 |
+
"special": false
|
579 |
+
},
|
580 |
+
"250069": {
|
581 |
+
"content": "β<extra_id_30>",
|
582 |
+
"lstrip": false,
|
583 |
+
"normalized": false,
|
584 |
+
"rstrip": false,
|
585 |
+
"single_word": false,
|
586 |
+
"special": false
|
587 |
+
},
|
588 |
+
"250070": {
|
589 |
+
"content": "β<extra_id_29>",
|
590 |
+
"lstrip": false,
|
591 |
+
"normalized": false,
|
592 |
+
"rstrip": false,
|
593 |
+
"single_word": false,
|
594 |
+
"special": false
|
595 |
+
},
|
596 |
+
"250071": {
|
597 |
+
"content": "β<extra_id_28>",
|
598 |
+
"lstrip": false,
|
599 |
+
"normalized": false,
|
600 |
+
"rstrip": false,
|
601 |
+
"single_word": false,
|
602 |
+
"special": false
|
603 |
+
},
|
604 |
+
"250072": {
|
605 |
+
"content": "β<extra_id_27>",
|
606 |
+
"lstrip": false,
|
607 |
+
"normalized": false,
|
608 |
+
"rstrip": false,
|
609 |
+
"single_word": false,
|
610 |
+
"special": false
|
611 |
+
},
|
612 |
+
"250073": {
|
613 |
+
"content": "β<extra_id_26>",
|
614 |
+
"lstrip": false,
|
615 |
+
"normalized": false,
|
616 |
+
"rstrip": false,
|
617 |
+
"single_word": false,
|
618 |
+
"special": false
|
619 |
+
},
|
620 |
+
"250074": {
|
621 |
+
"content": "β<extra_id_25>",
|
622 |
+
"lstrip": false,
|
623 |
+
"normalized": false,
|
624 |
+
"rstrip": false,
|
625 |
+
"single_word": false,
|
626 |
+
"special": false
|
627 |
+
},
|
628 |
+
"250075": {
|
629 |
+
"content": "β<extra_id_24>",
|
630 |
+
"lstrip": false,
|
631 |
+
"normalized": false,
|
632 |
+
"rstrip": false,
|
633 |
+
"single_word": false,
|
634 |
+
"special": false
|
635 |
+
},
|
636 |
+
"250076": {
|
637 |
+
"content": "β<extra_id_23>",
|
638 |
+
"lstrip": false,
|
639 |
+
"normalized": false,
|
640 |
+
"rstrip": false,
|
641 |
+
"single_word": false,
|
642 |
+
"special": false
|
643 |
+
},
|
644 |
+
"250077": {
|
645 |
+
"content": "β<extra_id_22>",
|
646 |
+
"lstrip": false,
|
647 |
+
"normalized": false,
|
648 |
+
"rstrip": false,
|
649 |
+
"single_word": false,
|
650 |
+
"special": false
|
651 |
+
},
|
652 |
+
"250078": {
|
653 |
+
"content": "β<extra_id_21>",
|
654 |
+
"lstrip": false,
|
655 |
+
"normalized": false,
|
656 |
+
"rstrip": false,
|
657 |
+
"single_word": false,
|
658 |
+
"special": false
|
659 |
+
},
|
660 |
+
"250079": {
|
661 |
+
"content": "β<extra_id_20>",
|
662 |
+
"lstrip": false,
|
663 |
+
"normalized": false,
|
664 |
+
"rstrip": false,
|
665 |
+
"single_word": false,
|
666 |
+
"special": false
|
667 |
+
},
|
668 |
+
"250080": {
|
669 |
+
"content": "β<extra_id_19>",
|
670 |
+
"lstrip": false,
|
671 |
+
"normalized": false,
|
672 |
+
"rstrip": false,
|
673 |
+
"single_word": false,
|
674 |
+
"special": false
|
675 |
+
},
|
676 |
+
"250081": {
|
677 |
+
"content": "β<extra_id_18>",
|
678 |
+
"lstrip": false,
|
679 |
+
"normalized": false,
|
680 |
+
"rstrip": false,
|
681 |
+
"single_word": false,
|
682 |
+
"special": false
|
683 |
+
},
|
684 |
+
"250082": {
|
685 |
+
"content": "β<extra_id_17>",
|
686 |
+
"lstrip": false,
|
687 |
+
"normalized": false,
|
688 |
+
"rstrip": false,
|
689 |
+
"single_word": false,
|
690 |
+
"special": false
|
691 |
+
},
|
692 |
+
"250083": {
|
693 |
+
"content": "β<extra_id_16>",
|
694 |
+
"lstrip": false,
|
695 |
+
"normalized": false,
|
696 |
+
"rstrip": false,
|
697 |
+
"single_word": false,
|
698 |
+
"special": false
|
699 |
+
},
|
700 |
+
"250084": {
|
701 |
+
"content": "β<extra_id_15>",
|
702 |
+
"lstrip": false,
|
703 |
+
"normalized": false,
|
704 |
+
"rstrip": false,
|
705 |
+
"single_word": false,
|
706 |
+
"special": false
|
707 |
+
},
|
708 |
+
"250085": {
|
709 |
+
"content": "β<extra_id_14>",
|
710 |
+
"lstrip": false,
|
711 |
+
"normalized": false,
|
712 |
+
"rstrip": false,
|
713 |
+
"single_word": false,
|
714 |
+
"special": false
|
715 |
+
},
|
716 |
+
"250086": {
|
717 |
+
"content": "β<extra_id_13>",
|
718 |
+
"lstrip": false,
|
719 |
+
"normalized": false,
|
720 |
+
"rstrip": false,
|
721 |
+
"single_word": false,
|
722 |
+
"special": false
|
723 |
+
},
|
724 |
+
"250087": {
|
725 |
+
"content": "β<extra_id_12>",
|
726 |
+
"lstrip": false,
|
727 |
+
"normalized": false,
|
728 |
+
"rstrip": false,
|
729 |
+
"single_word": false,
|
730 |
+
"special": false
|
731 |
+
},
|
732 |
+
"250088": {
|
733 |
+
"content": "β<extra_id_11>",
|
734 |
+
"lstrip": false,
|
735 |
+
"normalized": false,
|
736 |
+
"rstrip": false,
|
737 |
+
"single_word": false,
|
738 |
+
"special": false
|
739 |
+
},
|
740 |
+
"250089": {
|
741 |
+
"content": "β<extra_id_10>",
|
742 |
+
"lstrip": false,
|
743 |
+
"normalized": false,
|
744 |
+
"rstrip": false,
|
745 |
+
"single_word": false,
|
746 |
+
"special": false
|
747 |
+
},
|
748 |
+
"250090": {
|
749 |
+
"content": "β<extra_id_9>",
|
750 |
+
"lstrip": false,
|
751 |
+
"normalized": false,
|
752 |
+
"rstrip": false,
|
753 |
+
"single_word": false,
|
754 |
+
"special": false
|
755 |
+
},
|
756 |
+
"250091": {
|
757 |
+
"content": "β<extra_id_8>",
|
758 |
+
"lstrip": false,
|
759 |
+
"normalized": false,
|
760 |
+
"rstrip": false,
|
761 |
+
"single_word": false,
|
762 |
+
"special": false
|
763 |
+
},
|
764 |
+
"250092": {
|
765 |
+
"content": "β<extra_id_7>",
|
766 |
+
"lstrip": false,
|
767 |
+
"normalized": false,
|
768 |
+
"rstrip": false,
|
769 |
+
"single_word": false,
|
770 |
+
"special": false
|
771 |
+
},
|
772 |
+
"250093": {
|
773 |
+
"content": "β<extra_id_6>",
|
774 |
+
"lstrip": false,
|
775 |
+
"normalized": false,
|
776 |
+
"rstrip": false,
|
777 |
+
"single_word": false,
|
778 |
+
"special": false
|
779 |
+
},
|
780 |
+
"250094": {
|
781 |
+
"content": "β<extra_id_5>",
|
782 |
+
"lstrip": false,
|
783 |
+
"normalized": false,
|
784 |
+
"rstrip": false,
|
785 |
+
"single_word": false,
|
786 |
+
"special": false
|
787 |
+
},
|
788 |
+
"250095": {
|
789 |
+
"content": "β<extra_id_4>",
|
790 |
+
"lstrip": false,
|
791 |
+
"normalized": false,
|
792 |
+
"rstrip": false,
|
793 |
+
"single_word": false,
|
794 |
+
"special": false
|
795 |
+
},
|
796 |
+
"250096": {
|
797 |
+
"content": "β<extra_id_3>",
|
798 |
+
"lstrip": false,
|
799 |
+
"normalized": false,
|
800 |
+
"rstrip": false,
|
801 |
+
"single_word": false,
|
802 |
+
"special": false
|
803 |
+
},
|
804 |
+
"250097": {
|
805 |
+
"content": "β<extra_id_2>",
|
806 |
+
"lstrip": false,
|
807 |
+
"normalized": false,
|
808 |
+
"rstrip": false,
|
809 |
+
"single_word": false,
|
810 |
+
"special": false
|
811 |
+
},
|
812 |
+
"250098": {
|
813 |
+
"content": "β<extra_id_1>",
|
814 |
+
"lstrip": false,
|
815 |
+
"normalized": false,
|
816 |
+
"rstrip": false,
|
817 |
+
"single_word": false,
|
818 |
+
"special": false
|
819 |
+
},
|
820 |
+
"250099": {
|
821 |
+
"content": "β<extra_id_0>",
|
822 |
+
"lstrip": false,
|
823 |
+
"normalized": false,
|
824 |
+
"rstrip": false,
|
825 |
+
"single_word": false,
|
826 |
+
"special": false
|
827 |
+
}
|
828 |
+
},
|
829 |
+
"additional_special_tokens": [],
|
830 |
+
"clean_up_tokenization_spaces": false,
|
831 |
+
"eos_token": "</s>",
|
832 |
+
"extra_ids": 0,
|
833 |
+
"extra_special_tokens": {},
|
834 |
+
"legacy": false,
|
835 |
+
"model_max_length": 1000000000000000019884624838656,
|
836 |
+
"pad_token": "<pad>",
|
837 |
+
"sp_model_kwargs": {},
|
838 |
+
"tokenizer_class": "T5Tokenizer",
|
839 |
+
"unk_token": "<unk>"
|
840 |
+
}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:7127b15260aad6c202ef7467485e9ffa0bfdf9156881ddff23aa1f73e8c177f4
|
3 |
+
size 5496
|