Model save
Browse files- .gitattributes +1 -0
- README.md +314 -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
- runs/Mar10_23-08-48_1412920010036/events.out.tfevents.1741667746.1412920010036.5471.1 +3 -0
- runs/Mar11_00-36-23_1412920010036/events.out.tfevents.1741667784.1412920010036.5471.2 +3 -0
- runs/Mar11_00-36-23_1412920010036/events.out.tfevents.1741668489.1412920010036.5471.3 +3 -0
- runs/Mar11_00-48-17_1412920010036/events.out.tfevents.1741668498.1412920010036.5471.4 +3 -0
- runs/Mar11_00-48-17_1412920010036/events.out.tfevents.1741673649.1412920010036.5471.5 +3 -0
- runs/Mar11_08-18-41_1412920010036/events.out.tfevents.1741695522.1412920010036.235349.0 +3 -0
- runs/Mar11_08-36-50_1412920010036/events.out.tfevents.1741696613.1412920010036.243166.0 +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 +1,314 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
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
|
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
|
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: 4.4558
|
22 |
+
- Rouge1: 6.9916
|
23 |
+
- Rouge2: 0.6816
|
24 |
+
- Rougel: 5.7118
|
25 |
+
- Rougelsum: 5.7018
|
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: 4
|
51 |
+
|
52 |
+
### Training results
|
53 |
+
|
54 |
+
| Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum |
|
55 |
+
|:-------------:|:------:|:----:|:---------------:|:------:|:------:|:------:|:---------:|
|
56 |
+
| 23.6756 | 0.0160 | 5 | 11.7300 | 0.4936 | 0.0298 | 0.4390 | 0.4355 |
|
57 |
+
| 21.3163 | 0.0319 | 10 | 11.6817 | 0.5950 | 0.0303 | 0.5441 | 0.5398 |
|
58 |
+
| 19.4831 | 0.0479 | 15 | 11.6197 | 0.5874 | 0.0422 | 0.5365 | 0.5379 |
|
59 |
+
| 22.1207 | 0.0639 | 20 | 11.5248 | 0.5548 | 0.0413 | 0.5229 | 0.5198 |
|
60 |
+
| 19.8132 | 0.0799 | 25 | 11.4054 | 0.5510 | 0.0240 | 0.5010 | 0.4974 |
|
61 |
+
| 20.1565 | 0.0958 | 30 | 11.3720 | 0.6226 | 0.0216 | 0.5805 | 0.5763 |
|
62 |
+
| 19.7845 | 0.1118 | 35 | 11.3636 | 0.6424 | 0.0370 | 0.5877 | 0.5833 |
|
63 |
+
| 21.83 | 0.1278 | 40 | 11.3292 | 0.6306 | 0.0416 | 0.5777 | 0.5757 |
|
64 |
+
| 22.8683 | 0.1438 | 45 | 11.2816 | 0.6071 | 0.0340 | 0.5619 | 0.5612 |
|
65 |
+
| 21.5372 | 0.1597 | 50 | 11.2166 | 0.6361 | 0.0311 | 0.5761 | 0.5722 |
|
66 |
+
| 20.4096 | 0.1757 | 55 | 11.1637 | 0.6519 | 0.0339 | 0.5762 | 0.5752 |
|
67 |
+
| 23.4684 | 0.1917 | 60 | 11.1275 | 0.6089 | 0.0326 | 0.5266 | 0.5304 |
|
68 |
+
| 18.1937 | 0.2077 | 65 | 11.0679 | 0.6298 | 0.0284 | 0.5691 | 0.5679 |
|
69 |
+
| 20.9906 | 0.2236 | 70 | 11.0010 | 0.6016 | 0.0294 | 0.5618 | 0.5626 |
|
70 |
+
| 16.9343 | 0.2396 | 75 | 10.9141 | 0.6042 | 0.0341 | 0.5629 | 0.5605 |
|
71 |
+
| 16.213 | 0.2556 | 80 | 10.8014 | 0.5869 | 0.0341 | 0.5468 | 0.5422 |
|
72 |
+
| 23.0994 | 0.2716 | 85 | 10.6858 | 0.6965 | 0.0399 | 0.6411 | 0.6366 |
|
73 |
+
| 21.3159 | 0.2875 | 90 | 10.5525 | 0.7669 | 0.0560 | 0.6992 | 0.6939 |
|
74 |
+
| 17.8493 | 0.3035 | 95 | 10.4093 | 0.7420 | 0.0527 | 0.6913 | 0.6831 |
|
75 |
+
| 18.3706 | 0.3195 | 100 | 10.2754 | 0.7243 | 0.0332 | 0.6716 | 0.6648 |
|
76 |
+
| 18.2941 | 0.3355 | 105 | 10.1246 | 0.7495 | 0.0387 | 0.6865 | 0.6772 |
|
77 |
+
| 19.6502 | 0.3514 | 110 | 9.9765 | 0.7874 | 0.0579 | 0.7173 | 0.7144 |
|
78 |
+
| 17.7381 | 0.3674 | 115 | 9.8496 | 0.7391 | 0.0366 | 0.6777 | 0.6765 |
|
79 |
+
| 15.6761 | 0.3834 | 120 | 9.7321 | 0.8022 | 0.0563 | 0.7337 | 0.7291 |
|
80 |
+
| 16.2067 | 0.3994 | 125 | 9.6046 | 0.7913 | 0.0531 | 0.7319 | 0.7289 |
|
81 |
+
| 13.8577 | 0.4153 | 130 | 9.4678 | 0.8529 | 0.0571 | 0.7788 | 0.7763 |
|
82 |
+
| 15.4965 | 0.4313 | 135 | 9.3599 | 0.8251 | 0.0542 | 0.7540 | 0.7478 |
|
83 |
+
| 14.362 | 0.4473 | 140 | 9.2515 | 0.8661 | 0.0632 | 0.7880 | 0.7862 |
|
84 |
+
| 17.1324 | 0.4633 | 145 | 9.0933 | 0.8565 | 0.0416 | 0.8081 | 0.8043 |
|
85 |
+
| 15.5484 | 0.4792 | 150 | 8.9389 | 0.8524 | 0.0501 | 0.7688 | 0.7655 |
|
86 |
+
| 13.7671 | 0.4952 | 155 | 8.7882 | 0.9513 | 0.0701 | 0.8614 | 0.8538 |
|
87 |
+
| 14.2473 | 0.5112 | 160 | 8.6085 | 0.9936 | 0.0760 | 0.8882 | 0.8819 |
|
88 |
+
| 16.2646 | 0.5272 | 165 | 8.4261 | 1.0280 | 0.0825 | 0.9123 | 0.9112 |
|
89 |
+
| 14.422 | 0.5431 | 170 | 8.2682 | 0.9989 | 0.0732 | 0.9057 | 0.9046 |
|
90 |
+
| 12.8457 | 0.5591 | 175 | 8.1451 | 1.1030 | 0.0744 | 0.9912 | 0.9920 |
|
91 |
+
| 13.1231 | 0.5751 | 180 | 8.0125 | 1.2091 | 0.0769 | 1.0877 | 1.0854 |
|
92 |
+
| 12.4348 | 0.5911 | 185 | 7.8906 | 1.2220 | 0.0873 | 1.1092 | 1.1044 |
|
93 |
+
| 12.7066 | 0.6070 | 190 | 7.7846 | 1.2845 | 0.0905 | 1.1493 | 1.1445 |
|
94 |
+
| 12.6802 | 0.6230 | 195 | 7.6824 | 1.2024 | 0.0764 | 1.0739 | 1.0730 |
|
95 |
+
| 12.6226 | 0.6390 | 200 | 7.5869 | 1.2994 | 0.1020 | 1.1752 | 1.1781 |
|
96 |
+
| 11.7003 | 0.6550 | 205 | 7.4930 | 1.3573 | 0.0789 | 1.2515 | 1.2518 |
|
97 |
+
| 11.7344 | 0.6709 | 210 | 7.4188 | 1.3916 | 0.0922 | 1.2819 | 1.2819 |
|
98 |
+
| 11.7628 | 0.6869 | 215 | 7.3503 | 1.4452 | 0.0918 | 1.3172 | 1.3105 |
|
99 |
+
| 10.2049 | 0.7029 | 220 | 7.2817 | 1.6040 | 0.0990 | 1.4637 | 1.4567 |
|
100 |
+
| 10.803 | 0.7188 | 225 | 7.2149 | 1.8393 | 0.1138 | 1.6247 | 1.6199 |
|
101 |
+
| 10.014 | 0.7348 | 230 | 7.1472 | 1.9519 | 0.1254 | 1.7554 | 1.7515 |
|
102 |
+
| 10.6801 | 0.7508 | 235 | 7.0828 | 2.1037 | 0.1414 | 1.8470 | 1.8434 |
|
103 |
+
| 10.0471 | 0.7668 | 240 | 7.0481 | 2.0665 | 0.1527 | 1.7971 | 1.7958 |
|
104 |
+
| 9.7399 | 0.7827 | 245 | 7.0096 | 2.0347 | 0.1374 | 1.7735 | 1.7707 |
|
105 |
+
| 9.1483 | 0.7987 | 250 | 6.9719 | 2.1064 | 0.0887 | 1.8688 | 1.8726 |
|
106 |
+
| 8.8226 | 0.8147 | 255 | 6.9016 | 2.3382 | 0.1402 | 2.0657 | 2.0607 |
|
107 |
+
| 8.6236 | 0.8307 | 260 | 6.8058 | 2.2605 | 0.1258 | 2.0048 | 1.9982 |
|
108 |
+
| 8.8137 | 0.8466 | 265 | 6.7130 | 2.4050 | 0.1255 | 2.1567 | 2.1508 |
|
109 |
+
| 8.4192 | 0.8626 | 270 | 6.6078 | 2.4312 | 0.0998 | 2.2026 | 2.1954 |
|
110 |
+
| 8.3304 | 0.8786 | 275 | 6.4693 | 2.5363 | 0.1506 | 2.3432 | 2.3501 |
|
111 |
+
| 8.0673 | 0.8946 | 280 | 6.3136 | 2.5803 | 0.1364 | 2.3812 | 2.3723 |
|
112 |
+
| 7.8489 | 0.9105 | 285 | 6.1742 | 2.5226 | 0.1223 | 2.3425 | 2.3377 |
|
113 |
+
| 8.9521 | 0.9265 | 290 | 6.0328 | 2.5598 | 0.1001 | 2.3583 | 2.3461 |
|
114 |
+
| 7.6618 | 0.9425 | 295 | 5.8830 | 2.7390 | 0.1270 | 2.5325 | 2.5231 |
|
115 |
+
| 7.6692 | 0.9585 | 300 | 5.7741 | 2.7669 | 0.0933 | 2.5127 | 2.5096 |
|
116 |
+
| 7.9787 | 0.9744 | 305 | 5.7020 | 2.7929 | 0.0678 | 2.5641 | 2.5689 |
|
117 |
+
| 7.577 | 0.9904 | 310 | 5.6454 | 2.7002 | 0.0625 | 2.4869 | 2.4944 |
|
118 |
+
| 7.7221 | 1.0064 | 315 | 5.6025 | 2.7943 | 0.0410 | 2.5835 | 2.5853 |
|
119 |
+
| 7.3943 | 1.0224 | 320 | 5.5779 | 2.8294 | 0.0574 | 2.6103 | 2.6068 |
|
120 |
+
| 7.2515 | 1.0383 | 325 | 5.5558 | 2.6871 | 0.0391 | 2.5212 | 2.5114 |
|
121 |
+
| 7.13 | 1.0543 | 330 | 5.5428 | 2.7466 | 0.0538 | 2.5637 | 2.5593 |
|
122 |
+
| 6.7682 | 1.0703 | 335 | 5.5243 | 2.5682 | 0.0561 | 2.4248 | 2.4171 |
|
123 |
+
| 6.6841 | 1.0863 | 340 | 5.5019 | 2.5695 | 0.0390 | 2.4028 | 2.3910 |
|
124 |
+
| 7.061 | 1.1022 | 345 | 5.4904 | 2.6353 | 0.0232 | 2.4626 | 2.4600 |
|
125 |
+
| 6.8416 | 1.1182 | 350 | 5.4781 | 2.7188 | 0.0364 | 2.5442 | 2.5418 |
|
126 |
+
| 6.833 | 1.1342 | 355 | 5.4651 | 2.7963 | 0.0946 | 2.6191 | 2.6053 |
|
127 |
+
| 6.6498 | 1.1502 | 360 | 5.4439 | 2.7616 | 0.0794 | 2.5699 | 2.5632 |
|
128 |
+
| 6.5082 | 1.1661 | 365 | 5.4256 | 2.8136 | 0.0643 | 2.6238 | 2.6181 |
|
129 |
+
| 6.7253 | 1.1821 | 370 | 5.4129 | 2.8281 | 0.0564 | 2.6235 | 2.6203 |
|
130 |
+
| 6.3954 | 1.1981 | 375 | 5.3968 | 2.9543 | 0.0471 | 2.7386 | 2.7316 |
|
131 |
+
| 6.381 | 1.2141 | 380 | 5.3664 | 3.0891 | 0.1198 | 2.8635 | 2.8481 |
|
132 |
+
| 6.2691 | 1.2300 | 385 | 5.3405 | 3.1817 | 0.0991 | 2.9678 | 2.9600 |
|
133 |
+
| 6.3465 | 1.2460 | 390 | 5.3137 | 3.2596 | 0.0955 | 3.0371 | 3.0193 |
|
134 |
+
| 7.5564 | 1.2620 | 395 | 5.2915 | 3.4445 | 0.1965 | 3.2355 | 3.2178 |
|
135 |
+
| 6.297 | 1.2780 | 400 | 5.2659 | 3.3451 | 0.1735 | 3.1460 | 3.1341 |
|
136 |
+
| 6.0585 | 1.2939 | 405 | 5.2356 | 3.5268 | 0.1811 | 3.2960 | 3.2930 |
|
137 |
+
| 6.146 | 1.3099 | 410 | 5.2035 | 3.5298 | 0.2186 | 3.3129 | 3.3068 |
|
138 |
+
| 5.8611 | 1.3259 | 415 | 5.1748 | 3.5515 | 0.2134 | 3.3375 | 3.3356 |
|
139 |
+
| 6.1246 | 1.3419 | 420 | 5.1458 | 3.5293 | 0.1791 | 3.3109 | 3.3109 |
|
140 |
+
| 5.941 | 1.3578 | 425 | 5.1199 | 3.6252 | 0.1844 | 3.3822 | 3.3820 |
|
141 |
+
| 5.9336 | 1.3738 | 430 | 5.0968 | 3.7394 | 0.2487 | 3.4850 | 3.4839 |
|
142 |
+
| 6.0573 | 1.3898 | 435 | 5.0772 | 3.8920 | 0.2854 | 3.5845 | 3.5833 |
|
143 |
+
| 5.8787 | 1.4058 | 440 | 5.0583 | 3.9947 | 0.3167 | 3.7099 | 3.7060 |
|
144 |
+
| 5.742 | 1.4217 | 445 | 5.0390 | 4.2624 | 0.3612 | 3.9232 | 3.9237 |
|
145 |
+
| 5.9164 | 1.4377 | 450 | 5.0187 | 4.5394 | 0.3685 | 4.1808 | 4.1667 |
|
146 |
+
| 5.8206 | 1.4537 | 455 | 4.9996 | 4.7519 | 0.4171 | 4.3353 | 4.3228 |
|
147 |
+
| 5.7587 | 1.4696 | 460 | 4.9800 | 4.8192 | 0.4494 | 4.4227 | 4.4091 |
|
148 |
+
| 5.782 | 1.4856 | 465 | 4.9617 | 4.8078 | 0.4496 | 4.3912 | 4.3769 |
|
149 |
+
| 6.0275 | 1.5016 | 470 | 4.9466 | 4.8523 | 0.5041 | 4.4154 | 4.3983 |
|
150 |
+
| 5.9688 | 1.5176 | 475 | 4.9314 | 4.8285 | 0.4628 | 4.4055 | 4.3831 |
|
151 |
+
| 6.2916 | 1.5335 | 480 | 4.9161 | 4.8893 | 0.4697 | 4.4384 | 4.4320 |
|
152 |
+
| 5.8275 | 1.5495 | 485 | 4.9018 | 4.8905 | 0.4666 | 4.4296 | 4.4204 |
|
153 |
+
| 5.7246 | 1.5655 | 490 | 4.8863 | 4.8774 | 0.4725 | 4.4002 | 4.3823 |
|
154 |
+
| 5.6779 | 1.5815 | 495 | 4.8671 | 4.7665 | 0.4170 | 4.2980 | 4.2936 |
|
155 |
+
| 5.6032 | 1.5974 | 500 | 4.8466 | 4.9297 | 0.4819 | 4.4265 | 4.4229 |
|
156 |
+
| 5.8246 | 1.6134 | 505 | 4.8283 | 5.0824 | 0.4941 | 4.4664 | 4.4746 |
|
157 |
+
| 5.6855 | 1.6294 | 510 | 4.8129 | 5.0445 | 0.5022 | 4.4670 | 4.4665 |
|
158 |
+
| 5.4763 | 1.6454 | 515 | 4.7979 | 5.1488 | 0.4781 | 4.5613 | 4.5503 |
|
159 |
+
| 5.5418 | 1.6613 | 520 | 4.7839 | 5.3006 | 0.4677 | 4.7011 | 4.6898 |
|
160 |
+
| 5.489 | 1.6773 | 525 | 4.7723 | 5.3246 | 0.4893 | 4.7215 | 4.7127 |
|
161 |
+
| 5.6303 | 1.6933 | 530 | 4.7623 | 5.5604 | 0.5124 | 4.8999 | 4.8991 |
|
162 |
+
| 6.2405 | 1.7093 | 535 | 4.7547 | 5.5092 | 0.4656 | 4.8064 | 4.7866 |
|
163 |
+
| 5.8127 | 1.7252 | 540 | 4.7469 | 5.5956 | 0.5156 | 4.8723 | 4.8640 |
|
164 |
+
| 5.5919 | 1.7412 | 545 | 4.7389 | 5.6788 | 0.5618 | 4.9519 | 4.9475 |
|
165 |
+
| 5.574 | 1.7572 | 550 | 4.7309 | 5.7099 | 0.5667 | 5.0054 | 4.9991 |
|
166 |
+
| 5.415 | 1.7732 | 555 | 4.7239 | 5.6398 | 0.5503 | 4.8735 | 4.8653 |
|
167 |
+
| 5.5172 | 1.7891 | 560 | 4.7158 | 5.5743 | 0.4962 | 4.8134 | 4.7998 |
|
168 |
+
| 5.3554 | 1.8051 | 565 | 4.7086 | 5.6326 | 0.5413 | 4.7946 | 4.7893 |
|
169 |
+
| 5.632 | 1.8211 | 570 | 4.6997 | 5.6395 | 0.5585 | 4.8162 | 4.8135 |
|
170 |
+
| 5.6441 | 1.8371 | 575 | 4.6913 | 5.6594 | 0.5934 | 4.8383 | 4.8440 |
|
171 |
+
| 5.6121 | 1.8530 | 580 | 4.6848 | 5.7094 | 0.6287 | 4.8887 | 4.8955 |
|
172 |
+
| 5.6247 | 1.8690 | 585 | 4.6811 | 5.7092 | 0.5953 | 4.8865 | 4.8931 |
|
173 |
+
| 5.5127 | 1.8850 | 590 | 4.6774 | 5.7369 | 0.6294 | 4.9060 | 4.9123 |
|
174 |
+
| 5.3986 | 1.9010 | 595 | 4.6725 | 5.8236 | 0.6239 | 5.0256 | 5.0308 |
|
175 |
+
| 5.3653 | 1.9169 | 600 | 4.6657 | 5.8826 | 0.6295 | 5.0282 | 5.0357 |
|
176 |
+
| 5.5225 | 1.9329 | 605 | 4.6599 | 5.8561 | 0.6483 | 5.0548 | 5.0661 |
|
177 |
+
| 5.4748 | 1.9489 | 610 | 4.6542 | 5.8777 | 0.6013 | 5.0208 | 5.0236 |
|
178 |
+
| 5.4552 | 1.9649 | 615 | 4.6488 | 5.8850 | 0.6102 | 4.9776 | 4.9827 |
|
179 |
+
| 5.4006 | 1.9808 | 620 | 4.6435 | 5.8263 | 0.5668 | 4.9280 | 4.9319 |
|
180 |
+
| 5.2525 | 1.9968 | 625 | 4.6374 | 5.8090 | 0.5567 | 4.8903 | 4.8934 |
|
181 |
+
| 5.3651 | 2.0128 | 630 | 4.6327 | 5.8141 | 0.5850 | 4.8955 | 4.9018 |
|
182 |
+
| 5.3102 | 2.0288 | 635 | 4.6288 | 5.7891 | 0.6054 | 4.9275 | 4.9390 |
|
183 |
+
| 5.4252 | 2.0447 | 640 | 4.6243 | 5.7595 | 0.5903 | 4.9053 | 4.9143 |
|
184 |
+
| 5.623 | 2.0607 | 645 | 4.6207 | 5.8272 | 0.5991 | 4.9243 | 4.9271 |
|
185 |
+
| 5.9216 | 2.0767 | 650 | 4.6182 | 5.7977 | 0.5746 | 4.8630 | 4.8650 |
|
186 |
+
| 5.2885 | 2.0927 | 655 | 4.6160 | 5.8832 | 0.6089 | 4.9655 | 4.9590 |
|
187 |
+
| 5.4478 | 2.1086 | 660 | 4.6143 | 6.1030 | 0.6493 | 5.1520 | 5.1469 |
|
188 |
+
| 5.4389 | 2.1246 | 665 | 4.6138 | 6.2193 | 0.6379 | 5.2267 | 5.2330 |
|
189 |
+
| 5.3506 | 2.1406 | 670 | 4.6115 | 6.2155 | 0.6610 | 5.2507 | 5.2505 |
|
190 |
+
| 5.2738 | 2.1565 | 675 | 4.6067 | 6.4144 | 0.6590 | 5.3567 | 5.3562 |
|
191 |
+
| 5.2637 | 2.1725 | 680 | 4.6028 | 6.6140 | 0.6895 | 5.5451 | 5.5404 |
|
192 |
+
| 5.4674 | 2.1885 | 685 | 4.5991 | 6.6112 | 0.6680 | 5.5371 | 5.5289 |
|
193 |
+
| 5.4239 | 2.2045 | 690 | 4.5962 | 6.6814 | 0.6930 | 5.6114 | 5.6027 |
|
194 |
+
| 5.5427 | 2.2204 | 695 | 4.5940 | 6.6225 | 0.6488 | 5.5083 | 5.5054 |
|
195 |
+
| 5.33 | 2.2364 | 700 | 4.5913 | 6.5749 | 0.6924 | 5.4796 | 5.4663 |
|
196 |
+
| 5.326 | 2.2524 | 705 | 4.5876 | 6.5141 | 0.6854 | 5.4379 | 5.4275 |
|
197 |
+
| 5.1821 | 2.2684 | 710 | 4.5827 | 6.5709 | 0.7154 | 5.4791 | 5.4750 |
|
198 |
+
| 5.3379 | 2.2843 | 715 | 4.5779 | 6.6474 | 0.7288 | 5.5817 | 5.5757 |
|
199 |
+
| 5.5842 | 2.3003 | 720 | 4.5742 | 6.6228 | 0.6962 | 5.5504 | 5.5346 |
|
200 |
+
| 5.3523 | 2.3163 | 725 | 4.5706 | 6.6456 | 0.7115 | 5.5543 | 5.5382 |
|
201 |
+
| 5.3367 | 2.3323 | 730 | 4.5668 | 6.6447 | 0.7167 | 5.5495 | 5.5403 |
|
202 |
+
| 5.3159 | 2.3482 | 735 | 4.5639 | 6.6856 | 0.7344 | 5.6046 | 5.5874 |
|
203 |
+
| 5.2955 | 2.3642 | 740 | 4.5617 | 6.6819 | 0.7438 | 5.6109 | 5.5915 |
|
204 |
+
| 5.3509 | 2.3802 | 745 | 4.5588 | 6.6925 | 0.7367 | 5.6635 | 5.6420 |
|
205 |
+
| 5.4309 | 2.3962 | 750 | 4.5564 | 6.6572 | 0.7239 | 5.6270 | 5.6078 |
|
206 |
+
| 5.3232 | 2.4121 | 755 | 4.5549 | 6.6658 | 0.7242 | 5.6407 | 5.6248 |
|
207 |
+
| 5.3663 | 2.4281 | 760 | 4.5545 | 6.6939 | 0.7227 | 5.6980 | 5.6823 |
|
208 |
+
| 5.2839 | 2.4441 | 765 | 4.5528 | 6.6417 | 0.7172 | 5.6179 | 5.6046 |
|
209 |
+
| 5.1068 | 2.4601 | 770 | 4.5507 | 6.6977 | 0.7300 | 5.6509 | 5.6364 |
|
210 |
+
| 5.2285 | 2.4760 | 775 | 4.5483 | 6.6988 | 0.7397 | 5.6623 | 5.6474 |
|
211 |
+
| 5.3325 | 2.4920 | 780 | 4.5455 | 6.6992 | 0.7395 | 5.6787 | 5.6597 |
|
212 |
+
| 5.2692 | 2.5080 | 785 | 4.5423 | 6.7269 | 0.7354 | 5.6832 | 5.6717 |
|
213 |
+
| 5.2416 | 2.5240 | 790 | 4.5402 | 6.6987 | 0.7277 | 5.6825 | 5.6674 |
|
214 |
+
| 5.2668 | 2.5399 | 795 | 4.5380 | 6.7267 | 0.7257 | 5.7369 | 5.7216 |
|
215 |
+
| 5.3415 | 2.5559 | 800 | 4.5363 | 6.7654 | 0.7323 | 5.7682 | 5.7448 |
|
216 |
+
| 5.2675 | 2.5719 | 805 | 4.5346 | 6.9076 | 0.7348 | 5.8630 | 5.8460 |
|
217 |
+
| 5.1813 | 2.5879 | 810 | 4.5333 | 6.9111 | 0.7139 | 5.8215 | 5.8088 |
|
218 |
+
| 5.3719 | 2.6038 | 815 | 4.5319 | 6.9676 | 0.7501 | 5.8938 | 5.8751 |
|
219 |
+
| 5.2826 | 2.6198 | 820 | 4.5296 | 6.9759 | 0.7424 | 5.9081 | 5.8935 |
|
220 |
+
| 5.2366 | 2.6358 | 825 | 4.5281 | 6.9508 | 0.7371 | 5.8471 | 5.8354 |
|
221 |
+
| 5.1769 | 2.6518 | 830 | 4.5276 | 6.9875 | 0.7161 | 5.8823 | 5.8731 |
|
222 |
+
| 5.2484 | 2.6677 | 835 | 4.5270 | 6.9863 | 0.7222 | 5.8866 | 5.8754 |
|
223 |
+
| 5.2323 | 2.6837 | 840 | 4.5263 | 6.9414 | 0.6963 | 5.8284 | 5.8195 |
|
224 |
+
| 5.1327 | 2.6997 | 845 | 4.5240 | 6.9841 | 0.6984 | 5.8296 | 5.8195 |
|
225 |
+
| 5.138 | 2.7157 | 850 | 4.5209 | 7.0102 | 0.7134 | 5.8757 | 5.8637 |
|
226 |
+
| 5.1938 | 2.7316 | 855 | 4.5168 | 6.9719 | 0.7021 | 5.8537 | 5.8429 |
|
227 |
+
| 5.1618 | 2.7476 | 860 | 4.5136 | 6.8674 | 0.6884 | 5.7749 | 5.7624 |
|
228 |
+
| 5.1931 | 2.7636 | 865 | 4.5116 | 6.8026 | 0.6750 | 5.7132 | 5.7083 |
|
229 |
+
| 5.0372 | 2.7796 | 870 | 4.5097 | 6.7480 | 0.6611 | 5.6958 | 5.6879 |
|
230 |
+
| 5.2144 | 2.7955 | 875 | 4.5084 | 6.7780 | 0.6605 | 5.7056 | 5.6933 |
|
231 |
+
| 5.3514 | 2.8115 | 880 | 4.5070 | 6.7706 | 0.6476 | 5.7317 | 5.7224 |
|
232 |
+
| 5.3267 | 2.8275 | 885 | 4.5049 | 6.7649 | 0.6556 | 5.7269 | 5.7248 |
|
233 |
+
| 5.2012 | 2.8435 | 890 | 4.5025 | 6.7671 | 0.6727 | 5.7185 | 5.7078 |
|
234 |
+
| 5.231 | 2.8594 | 895 | 4.5000 | 6.7752 | 0.6605 | 5.7131 | 5.7062 |
|
235 |
+
| 5.5058 | 2.8754 | 900 | 4.4982 | 6.8061 | 0.6414 | 5.7308 | 5.7243 |
|
236 |
+
| 5.1725 | 2.8914 | 905 | 4.4971 | 6.7574 | 0.6312 | 5.6988 | 5.6969 |
|
237 |
+
| 5.1605 | 2.9073 | 910 | 4.4953 | 6.7771 | 0.6541 | 5.7257 | 5.7234 |
|
238 |
+
| 5.205 | 2.9233 | 915 | 4.4932 | 6.7896 | 0.6608 | 5.7603 | 5.7574 |
|
239 |
+
| 5.3089 | 2.9393 | 920 | 4.4916 | 6.7881 | 0.6504 | 5.7507 | 5.7542 |
|
240 |
+
| 5.2994 | 2.9553 | 925 | 4.4903 | 6.7905 | 0.6427 | 5.7104 | 5.7157 |
|
241 |
+
| 5.0648 | 2.9712 | 930 | 4.4885 | 6.7691 | 0.6338 | 5.7117 | 5.7143 |
|
242 |
+
| 5.1906 | 2.9872 | 935 | 4.4870 | 6.7841 | 0.6414 | 5.7250 | 5.7231 |
|
243 |
+
| 5.2381 | 3.0032 | 940 | 4.4852 | 6.8148 | 0.6582 | 5.7312 | 5.7279 |
|
244 |
+
| 5.2319 | 3.0192 | 945 | 4.4837 | 6.8141 | 0.6613 | 5.7176 | 5.7204 |
|
245 |
+
| 5.1976 | 3.0351 | 950 | 4.4823 | 6.7903 | 0.6651 | 5.6967 | 5.6950 |
|
246 |
+
| 5.0499 | 3.0511 | 955 | 4.4804 | 6.8182 | 0.6681 | 5.7180 | 5.7155 |
|
247 |
+
| 5.2995 | 3.0671 | 960 | 4.4784 | 6.8703 | 0.6622 | 5.7614 | 5.7628 |
|
248 |
+
| 5.1794 | 3.0831 | 965 | 4.4767 | 6.8704 | 0.6576 | 5.7600 | 5.7633 |
|
249 |
+
| 5.0923 | 3.0990 | 970 | 4.4757 | 6.8784 | 0.6412 | 5.7703 | 5.7741 |
|
250 |
+
| 5.1729 | 3.1150 | 975 | 4.4747 | 6.9144 | 0.6403 | 5.8102 | 5.8064 |
|
251 |
+
| 5.1864 | 3.1310 | 980 | 4.4742 | 6.9348 | 0.6531 | 5.8079 | 5.8027 |
|
252 |
+
| 5.2251 | 3.1470 | 985 | 4.4737 | 6.9469 | 0.6869 | 5.8021 | 5.8002 |
|
253 |
+
| 5.1631 | 3.1629 | 990 | 4.4733 | 6.9770 | 0.6909 | 5.8255 | 5.8155 |
|
254 |
+
| 5.2361 | 3.1789 | 995 | 4.4732 | 6.9978 | 0.7205 | 5.8385 | 5.8312 |
|
255 |
+
| 5.2153 | 3.1949 | 1000 | 4.4727 | 7.0194 | 0.7462 | 5.8473 | 5.8427 |
|
256 |
+
| 4.949 | 3.2109 | 1005 | 4.4724 | 7.0442 | 0.7346 | 5.8631 | 5.8543 |
|
257 |
+
| 5.0817 | 3.2268 | 1010 | 4.4721 | 7.0183 | 0.7229 | 5.8697 | 5.8590 |
|
258 |
+
| 5.0898 | 3.2428 | 1015 | 4.4716 | 7.0135 | 0.7131 | 5.8406 | 5.8362 |
|
259 |
+
| 5.1289 | 3.2588 | 1020 | 4.4715 | 6.9679 | 0.7175 | 5.8269 | 5.8193 |
|
260 |
+
| 5.2497 | 3.2748 | 1025 | 4.4708 | 6.9824 | 0.7243 | 5.8302 | 5.8229 |
|
261 |
+
| 5.2646 | 3.2907 | 1030 | 4.4700 | 6.9954 | 0.7178 | 5.8304 | 5.8193 |
|
262 |
+
| 5.2577 | 3.3067 | 1035 | 4.4689 | 6.9859 | 0.7132 | 5.8183 | 5.8091 |
|
263 |
+
| 5.0303 | 3.3227 | 1040 | 4.4675 | 6.9681 | 0.7205 | 5.7512 | 5.7422 |
|
264 |
+
| 5.0681 | 3.3387 | 1045 | 4.4662 | 6.9814 | 0.7321 | 5.7606 | 5.7567 |
|
265 |
+
| 5.1703 | 3.3546 | 1050 | 4.4648 | 6.9691 | 0.7201 | 5.7592 | 5.7554 |
|
266 |
+
| 5.1361 | 3.3706 | 1055 | 4.4635 | 6.9370 | 0.7088 | 5.7440 | 5.7445 |
|
267 |
+
| 5.2493 | 3.3866 | 1060 | 4.4625 | 6.9814 | 0.7020 | 5.7481 | 5.7480 |
|
268 |
+
| 5.2599 | 3.4026 | 1065 | 4.4615 | 6.9617 | 0.7029 | 5.7426 | 5.7407 |
|
269 |
+
| 5.6987 | 3.4185 | 1070 | 4.4608 | 6.9748 | 0.7117 | 5.7502 | 5.7481 |
|
270 |
+
| 5.1897 | 3.4345 | 1075 | 4.4606 | 6.9616 | 0.7094 | 5.7620 | 5.7587 |
|
271 |
+
| 5.1351 | 3.4505 | 1080 | 4.4608 | 6.9574 | 0.7200 | 5.7551 | 5.7568 |
|
272 |
+
| 5.1565 | 3.4665 | 1085 | 4.4612 | 6.9928 | 0.7335 | 5.7861 | 5.7773 |
|
273 |
+
| 5.0921 | 3.4824 | 1090 | 4.4611 | 6.9979 | 0.7437 | 5.7963 | 5.7911 |
|
274 |
+
| 5.2995 | 3.4984 | 1095 | 4.4613 | 6.9737 | 0.7398 | 5.7852 | 5.7807 |
|
275 |
+
| 5.2095 | 3.5144 | 1100 | 4.4610 | 6.9365 | 0.7029 | 5.7513 | 5.7477 |
|
276 |
+
| 4.9812 | 3.5304 | 1105 | 4.4608 | 6.9247 | 0.7040 | 5.7530 | 5.7444 |
|
277 |
+
| 5.0206 | 3.5463 | 1110 | 4.4604 | 6.9237 | 0.7161 | 5.7440 | 5.7371 |
|
278 |
+
| 5.1183 | 3.5623 | 1115 | 4.4602 | 6.9120 | 0.7013 | 5.7443 | 5.7361 |
|
279 |
+
| 5.1914 | 3.5783 | 1120 | 4.4603 | 6.9370 | 0.7057 | 5.7433 | 5.7367 |
|
280 |
+
| 4.9982 | 3.5942 | 1125 | 4.4603 | 6.9551 | 0.7008 | 5.7582 | 5.7546 |
|
281 |
+
| 5.0126 | 3.6102 | 1130 | 4.4604 | 6.9574 | 0.6951 | 5.7389 | 5.7325 |
|
282 |
+
| 5.1075 | 3.6262 | 1135 | 4.4603 | 6.9903 | 0.7045 | 5.7472 | 5.7432 |
|
283 |
+
| 5.1985 | 3.6422 | 1140 | 4.4601 | 6.9734 | 0.6858 | 5.7350 | 5.7301 |
|
284 |
+
| 5.3398 | 3.6581 | 1145 | 4.4600 | 6.9579 | 0.6883 | 5.7210 | 5.7124 |
|
285 |
+
| 5.1475 | 3.6741 | 1150 | 4.4596 | 6.9668 | 0.6785 | 5.7307 | 5.7186 |
|
286 |
+
| 5.016 | 3.6901 | 1155 | 4.4594 | 6.9717 | 0.6789 | 5.7341 | 5.7186 |
|
287 |
+
| 5.2785 | 3.7061 | 1160 | 4.4592 | 7.0314 | 0.6962 | 5.7750 | 5.7639 |
|
288 |
+
| 5.295 | 3.7220 | 1165 | 4.4589 | 7.0075 | 0.6895 | 5.7655 | 5.7547 |
|
289 |
+
| 5.1939 | 3.7380 | 1170 | 4.4587 | 7.0287 | 0.6944 | 5.7671 | 5.7590 |
|
290 |
+
| 5.2976 | 3.7540 | 1175 | 4.4585 | 7.0327 | 0.6917 | 5.7685 | 5.7589 |
|
291 |
+
| 4.9886 | 3.7700 | 1180 | 4.4581 | 7.0105 | 0.6844 | 5.7469 | 5.7372 |
|
292 |
+
| 5.2187 | 3.7859 | 1185 | 4.4577 | 6.9933 | 0.6810 | 5.7267 | 5.7187 |
|
293 |
+
| 5.3142 | 3.8019 | 1190 | 4.4573 | 7.0135 | 0.6810 | 5.7426 | 5.7333 |
|
294 |
+
| 5.1089 | 3.8179 | 1195 | 4.4572 | 7.0202 | 0.6810 | 5.7430 | 5.7323 |
|
295 |
+
| 5.2423 | 3.8339 | 1200 | 4.4569 | 7.0209 | 0.6810 | 5.7376 | 5.7267 |
|
296 |
+
| 5.1709 | 3.8498 | 1205 | 4.4566 | 7.0130 | 0.6810 | 5.7197 | 5.7088 |
|
297 |
+
| 5.2386 | 3.8658 | 1210 | 4.4564 | 7.0002 | 0.6753 | 5.7134 | 5.7056 |
|
298 |
+
| 5.0235 | 3.8818 | 1215 | 4.4562 | 6.9875 | 0.6753 | 5.7133 | 5.7057 |
|
299 |
+
| 5.1144 | 3.8978 | 1220 | 4.4561 | 6.9713 | 0.6816 | 5.6947 | 5.6868 |
|
300 |
+
| 5.1089 | 3.9137 | 1225 | 4.4560 | 6.9713 | 0.6816 | 5.6947 | 5.6868 |
|
301 |
+
| 5.1123 | 3.9297 | 1230 | 4.4559 | 6.9656 | 0.6816 | 5.6991 | 5.6932 |
|
302 |
+
| 4.9316 | 3.9457 | 1235 | 4.4559 | 6.9584 | 0.6673 | 5.6909 | 5.6877 |
|
303 |
+
| 5.1495 | 3.9617 | 1240 | 4.4558 | 6.9390 | 0.6673 | 5.6744 | 5.6706 |
|
304 |
+
| 5.169 | 3.9776 | 1245 | 4.4558 | 6.9656 | 0.6816 | 5.6991 | 5.6932 |
|
305 |
+
| 5.3732 | 3.9936 | 1250 | 4.4558 | 6.9916 | 0.6816 | 5.7118 | 5.7018 |
|
306 |
+
|
307 |
+
|
308 |
+
### Framework versions
|
309 |
+
|
310 |
+
- PEFT 0.14.0
|
311 |
+
- Transformers 4.49.0
|
312 |
+
- Pytorch 2.6.0+cu124
|
313 |
+
- Datasets 3.3.2
|
314 |
+
- 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:ab84c67bf39faad4430fe4535f82f1a98fe51a6533dfa4b555f715fbb4bbb8c0
|
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
|
runs/Mar10_23-08-48_1412920010036/events.out.tfevents.1741667746.1412920010036.5471.1
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:792a75e640434bf8aa50b1ef06323080a1c16079af61c3bf8694eb452fad42a6
|
3 |
+
size 562
|
runs/Mar11_00-36-23_1412920010036/events.out.tfevents.1741667784.1412920010036.5471.2
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:14a0ec7de23abb4f0a5d2089d151629190d92f5ec867f3f325c6be120106b2fe
|
3 |
+
size 59508
|
runs/Mar11_00-36-23_1412920010036/events.out.tfevents.1741668489.1412920010036.5471.3
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:bf2e319d10421337f47f1e8b3f46bae0ad327b388a3e7f90b0e1965ffdbc5d5a
|
3 |
+
size 562
|
runs/Mar11_00-48-17_1412920010036/events.out.tfevents.1741668498.1412920010036.5471.4
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d85e822375a87e28f05d12ef333b2fb6fd159fe4f9a19f1f70ba612647cfb70a
|
3 |
+
size 91030
|
runs/Mar11_00-48-17_1412920010036/events.out.tfevents.1741673649.1412920010036.5471.5
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:00f80e0e8a6988580e823614cd7f35439cdb0938a3ace2d1fd4358ba8f788052
|
3 |
+
size 562
|
runs/Mar11_08-18-41_1412920010036/events.out.tfevents.1741695522.1412920010036.235349.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:2a351088403358a6e3ed6d487f24a9e6b63a3c00043cebc546bf195ce0ad75e0
|
3 |
+
size 8924
|
runs/Mar11_08-36-50_1412920010036/events.out.tfevents.1741696613.1412920010036.243166.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d8b85c7d0e23e119678b0ca6026c0a32bbd115ca0c00d66d7557d08945fcbb2a
|
3 |
+
size 176636
|
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:d9d2672bec5bd307f293ca79ff6e078266d6920b7544c0453b400fb231e7e61c
|
3 |
+
size 5496
|