Commit
•
ed0f6c9
1
Parent(s):
f95a3a1
End of training
Browse files- README.md +162 -0
- config.json +34 -0
- generation_config.json +6 -0
- pytorch_model.bin +3 -0
- special_tokens_map.json +150 -0
- tokenizer_config.json +157 -0
- training_args.bin +3 -0
README.md
ADDED
|
@@ -0,0 +1,162 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: apache-2.0
|
| 3 |
+
base_model: google/byt5-base
|
| 4 |
+
tags:
|
| 5 |
+
- generated_from_trainer
|
| 6 |
+
metrics:
|
| 7 |
+
- wer
|
| 8 |
+
model-index:
|
| 9 |
+
- name: byt5-finetuned-indocollex-informal-to-formal
|
| 10 |
+
results: []
|
| 11 |
+
---
|
| 12 |
+
|
| 13 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 14 |
+
should probably proofread and complete it, then remove this comment. -->
|
| 15 |
+
|
| 16 |
+
# byt5-finetuned-indocollex-informal-to-formal
|
| 17 |
+
|
| 18 |
+
This model is a fine-tuned version of [google/byt5-base](https://huggingface.co/google/byt5-base) on an unknown dataset.
|
| 19 |
+
It achieves the following results on the evaluation set:
|
| 20 |
+
- Loss: 0.2191
|
| 21 |
+
- Cer: 0.208
|
| 22 |
+
- Wer: 0.5286
|
| 23 |
+
- Word Acc: 0.4714
|
| 24 |
+
- Gen Len: 7.7486
|
| 25 |
+
|
| 26 |
+
## Model description
|
| 27 |
+
|
| 28 |
+
More information needed
|
| 29 |
+
|
| 30 |
+
## Intended uses & limitations
|
| 31 |
+
|
| 32 |
+
More information needed
|
| 33 |
+
|
| 34 |
+
## Training and evaluation data
|
| 35 |
+
|
| 36 |
+
More information needed
|
| 37 |
+
|
| 38 |
+
## Training procedure
|
| 39 |
+
|
| 40 |
+
### Training hyperparameters
|
| 41 |
+
|
| 42 |
+
The following hyperparameters were used during training:
|
| 43 |
+
- learning_rate: 2e-05
|
| 44 |
+
- train_batch_size: 16
|
| 45 |
+
- eval_batch_size: 16
|
| 46 |
+
- seed: 42
|
| 47 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 48 |
+
- lr_scheduler_type: linear
|
| 49 |
+
- num_epochs: 100
|
| 50 |
+
|
| 51 |
+
### Training results
|
| 52 |
+
|
| 53 |
+
| Training Loss | Epoch | Step | Validation Loss | Cer | Wer | Word Acc | Gen Len |
|
| 54 |
+
|:-------------:|:-----:|:----:|:---------------:|:------:|:------:|:--------:|:-------:|
|
| 55 |
+
| No log | 1.0 | 93 | 15.6714 | 2.1749 | 2.0857 | -1.0857 | 19.0 |
|
| 56 |
+
| No log | 2.0 | 186 | 12.9426 | 2.1265 | 1.6619 | -0.6619 | 19.0 |
|
| 57 |
+
| No log | 3.0 | 279 | 9.8664 | 1.9525 | 1.0524 | -0.0524 | 17.8343 |
|
| 58 |
+
| No log | 4.0 | 372 | 4.9424 | 1.0051 | 1.0 | 0.0 | 0.1086 |
|
| 59 |
+
| No log | 5.0 | 465 | 3.8691 | 0.5688 | 0.9667 | 0.0333 | 6.8171 |
|
| 60 |
+
| 11.8639 | 6.0 | 558 | 3.0433 | 0.5161 | 0.9619 | 0.0381 | 6.1486 |
|
| 61 |
+
| 11.8639 | 7.0 | 651 | 1.1874 | 0.5374 | 0.9619 | 0.0381 | 5.9143 |
|
| 62 |
+
| 11.8639 | 8.0 | 744 | 0.5482 | 0.5756 | 0.9714 | 0.0286 | 7.2457 |
|
| 63 |
+
| 11.8639 | 9.0 | 837 | 0.4749 | 0.5195 | 0.9476 | 0.0524 | 7.1771 |
|
| 64 |
+
| 11.8639 | 10.0 | 930 | 0.3678 | 0.3591 | 0.8952 | 0.1048 | 7.0286 |
|
| 65 |
+
| 1.4703 | 11.0 | 1023 | 0.3154 | 0.2988 | 0.8524 | 0.1476 | 7.0343 |
|
| 66 |
+
| 1.4703 | 12.0 | 1116 | 0.2753 | 0.2895 | 0.819 | 0.181 | 7.3314 |
|
| 67 |
+
| 1.4703 | 13.0 | 1209 | 0.2561 | 0.2674 | 0.7667 | 0.2333 | 7.1543 |
|
| 68 |
+
| 1.4703 | 14.0 | 1302 | 0.2386 | 0.2581 | 0.7667 | 0.2333 | 7.3657 |
|
| 69 |
+
| 1.4703 | 15.0 | 1395 | 0.2249 | 0.2453 | 0.7429 | 0.2571 | 7.4629 |
|
| 70 |
+
| 1.4703 | 16.0 | 1488 | 0.2163 | 0.2428 | 0.7286 | 0.2714 | 7.4514 |
|
| 71 |
+
| 0.3131 | 17.0 | 1581 | 0.2093 | 0.2538 | 0.7286 | 0.2714 | 7.4743 |
|
| 72 |
+
| 0.3131 | 18.0 | 1674 | 0.2027 | 0.2436 | 0.7143 | 0.2857 | 7.6057 |
|
| 73 |
+
| 0.3131 | 19.0 | 1767 | 0.1986 | 0.2453 | 0.7 | 0.3 | 7.6229 |
|
| 74 |
+
| 0.3131 | 20.0 | 1860 | 0.1923 | 0.2453 | 0.6952 | 0.3048 | 7.6571 |
|
| 75 |
+
| 0.3131 | 21.0 | 1953 | 0.1907 | 0.2411 | 0.6667 | 0.3333 | 7.5829 |
|
| 76 |
+
| 0.2093 | 22.0 | 2046 | 0.1876 | 0.2368 | 0.6571 | 0.3429 | 7.6171 |
|
| 77 |
+
| 0.2093 | 23.0 | 2139 | 0.1889 | 0.2351 | 0.6476 | 0.3524 | 7.5543 |
|
| 78 |
+
| 0.2093 | 24.0 | 2232 | 0.1864 | 0.2334 | 0.6429 | 0.3571 | 7.6 |
|
| 79 |
+
| 0.2093 | 25.0 | 2325 | 0.1802 | 0.2284 | 0.6238 | 0.3762 | 7.6 |
|
| 80 |
+
| 0.2093 | 26.0 | 2418 | 0.1786 | 0.2292 | 0.6381 | 0.3619 | 7.6 |
|
| 81 |
+
| 0.1641 | 27.0 | 2511 | 0.1760 | 0.2182 | 0.6286 | 0.3714 | 7.56 |
|
| 82 |
+
| 0.1641 | 28.0 | 2604 | 0.1769 | 0.2199 | 0.6143 | 0.3857 | 7.6057 |
|
| 83 |
+
| 0.1641 | 29.0 | 2697 | 0.1735 | 0.225 | 0.619 | 0.381 | 7.6114 |
|
| 84 |
+
| 0.1641 | 30.0 | 2790 | 0.1764 | 0.2207 | 0.6 | 0.4 | 7.6057 |
|
| 85 |
+
| 0.1641 | 31.0 | 2883 | 0.1727 | 0.208 | 0.5952 | 0.4048 | 7.5943 |
|
| 86 |
+
| 0.1641 | 32.0 | 2976 | 0.1735 | 0.208 | 0.5905 | 0.4095 | 7.64 |
|
| 87 |
+
| 0.1336 | 33.0 | 3069 | 0.1694 | 0.2063 | 0.581 | 0.419 | 7.6743 |
|
| 88 |
+
| 0.1336 | 34.0 | 3162 | 0.1728 | 0.2114 | 0.5857 | 0.4143 | 7.6914 |
|
| 89 |
+
| 0.1336 | 35.0 | 3255 | 0.1722 | 0.2207 | 0.5857 | 0.4143 | 7.64 |
|
| 90 |
+
| 0.1336 | 36.0 | 3348 | 0.1703 | 0.2224 | 0.6 | 0.4 | 7.6857 |
|
| 91 |
+
| 0.1336 | 37.0 | 3441 | 0.1715 | 0.2173 | 0.581 | 0.419 | 7.6629 |
|
| 92 |
+
| 0.1115 | 38.0 | 3534 | 0.1735 | 0.2148 | 0.5762 | 0.4238 | 7.68 |
|
| 93 |
+
| 0.1115 | 39.0 | 3627 | 0.1715 | 0.2088 | 0.5762 | 0.4238 | 7.7143 |
|
| 94 |
+
| 0.1115 | 40.0 | 3720 | 0.1754 | 0.2131 | 0.5714 | 0.4286 | 7.72 |
|
| 95 |
+
| 0.1115 | 41.0 | 3813 | 0.1757 | 0.2122 | 0.5524 | 0.4476 | 7.76 |
|
| 96 |
+
| 0.1115 | 42.0 | 3906 | 0.1725 | 0.2122 | 0.5571 | 0.4429 | 7.7714 |
|
| 97 |
+
| 0.1115 | 43.0 | 3999 | 0.1724 | 0.2173 | 0.5619 | 0.4381 | 7.76 |
|
| 98 |
+
| 0.0954 | 44.0 | 4092 | 0.1799 | 0.2071 | 0.5429 | 0.4571 | 7.7371 |
|
| 99 |
+
| 0.0954 | 45.0 | 4185 | 0.1771 | 0.2097 | 0.5524 | 0.4476 | 7.7657 |
|
| 100 |
+
| 0.0954 | 46.0 | 4278 | 0.1780 | 0.2063 | 0.5476 | 0.4524 | 7.72 |
|
| 101 |
+
| 0.0954 | 47.0 | 4371 | 0.1791 | 0.2088 | 0.5381 | 0.4619 | 7.7714 |
|
| 102 |
+
| 0.0954 | 48.0 | 4464 | 0.1799 | 0.2105 | 0.5429 | 0.4571 | 7.7486 |
|
| 103 |
+
| 0.0814 | 49.0 | 4557 | 0.1799 | 0.2054 | 0.5333 | 0.4667 | 7.7657 |
|
| 104 |
+
| 0.0814 | 50.0 | 4650 | 0.1830 | 0.2037 | 0.5381 | 0.4619 | 7.6971 |
|
| 105 |
+
| 0.0814 | 51.0 | 4743 | 0.1824 | 0.2088 | 0.5429 | 0.4571 | 7.76 |
|
| 106 |
+
| 0.0814 | 52.0 | 4836 | 0.1846 | 0.2037 | 0.5286 | 0.4714 | 7.7771 |
|
| 107 |
+
| 0.0814 | 53.0 | 4929 | 0.1837 | 0.2046 | 0.5286 | 0.4714 | 7.7429 |
|
| 108 |
+
| 0.073 | 54.0 | 5022 | 0.1816 | 0.2054 | 0.5333 | 0.4667 | 7.7943 |
|
| 109 |
+
| 0.073 | 55.0 | 5115 | 0.1825 | 0.2029 | 0.519 | 0.481 | 7.7771 |
|
| 110 |
+
| 0.073 | 56.0 | 5208 | 0.1870 | 0.208 | 0.5286 | 0.4714 | 7.7829 |
|
| 111 |
+
| 0.073 | 57.0 | 5301 | 0.1870 | 0.2105 | 0.5381 | 0.4619 | 7.7829 |
|
| 112 |
+
| 0.073 | 58.0 | 5394 | 0.1932 | 0.2054 | 0.5286 | 0.4714 | 7.7543 |
|
| 113 |
+
| 0.073 | 59.0 | 5487 | 0.1880 | 0.2046 | 0.5143 | 0.4857 | 7.7886 |
|
| 114 |
+
| 0.0653 | 60.0 | 5580 | 0.1890 | 0.2071 | 0.519 | 0.481 | 7.7714 |
|
| 115 |
+
| 0.0653 | 61.0 | 5673 | 0.1952 | 0.2105 | 0.5286 | 0.4714 | 7.7886 |
|
| 116 |
+
| 0.0653 | 62.0 | 5766 | 0.1940 | 0.2054 | 0.5238 | 0.4762 | 7.8 |
|
| 117 |
+
| 0.0653 | 63.0 | 5859 | 0.1948 | 0.2063 | 0.5143 | 0.4857 | 7.7829 |
|
| 118 |
+
| 0.0653 | 64.0 | 5952 | 0.1972 | 0.208 | 0.5238 | 0.4762 | 7.7943 |
|
| 119 |
+
| 0.0582 | 65.0 | 6045 | 0.1965 | 0.2046 | 0.5238 | 0.4762 | 7.7543 |
|
| 120 |
+
| 0.0582 | 66.0 | 6138 | 0.1968 | 0.2046 | 0.5095 | 0.4905 | 7.7657 |
|
| 121 |
+
| 0.0582 | 67.0 | 6231 | 0.1981 | 0.2071 | 0.519 | 0.481 | 7.7886 |
|
| 122 |
+
| 0.0582 | 68.0 | 6324 | 0.1977 | 0.2063 | 0.519 | 0.481 | 7.7771 |
|
| 123 |
+
| 0.0582 | 69.0 | 6417 | 0.2018 | 0.2054 | 0.5238 | 0.4762 | 7.7657 |
|
| 124 |
+
| 0.0522 | 70.0 | 6510 | 0.1992 | 0.2088 | 0.5286 | 0.4714 | 7.7657 |
|
| 125 |
+
| 0.0522 | 71.0 | 6603 | 0.1999 | 0.2131 | 0.5381 | 0.4619 | 7.7714 |
|
| 126 |
+
| 0.0522 | 72.0 | 6696 | 0.1998 | 0.2173 | 0.5429 | 0.4571 | 7.7943 |
|
| 127 |
+
| 0.0522 | 73.0 | 6789 | 0.1991 | 0.2156 | 0.5381 | 0.4619 | 7.7829 |
|
| 128 |
+
| 0.0522 | 74.0 | 6882 | 0.2024 | 0.2088 | 0.5333 | 0.4667 | 7.72 |
|
| 129 |
+
| 0.0522 | 75.0 | 6975 | 0.2053 | 0.2046 | 0.5286 | 0.4714 | 7.7257 |
|
| 130 |
+
| 0.0494 | 76.0 | 7068 | 0.2055 | 0.2054 | 0.5333 | 0.4667 | 7.7429 |
|
| 131 |
+
| 0.0494 | 77.0 | 7161 | 0.2064 | 0.208 | 0.5333 | 0.4667 | 7.7029 |
|
| 132 |
+
| 0.0494 | 78.0 | 7254 | 0.2057 | 0.208 | 0.5286 | 0.4714 | 7.7257 |
|
| 133 |
+
| 0.0494 | 79.0 | 7347 | 0.2087 | 0.2097 | 0.5381 | 0.4619 | 7.68 |
|
| 134 |
+
| 0.0494 | 80.0 | 7440 | 0.2085 | 0.2131 | 0.5476 | 0.4524 | 7.6971 |
|
| 135 |
+
| 0.0462 | 81.0 | 7533 | 0.2099 | 0.2122 | 0.5476 | 0.4524 | 7.6914 |
|
| 136 |
+
| 0.0462 | 82.0 | 7626 | 0.2090 | 0.2071 | 0.5286 | 0.4714 | 7.7429 |
|
| 137 |
+
| 0.0462 | 83.0 | 7719 | 0.2127 | 0.2088 | 0.5286 | 0.4714 | 7.7086 |
|
| 138 |
+
| 0.0462 | 84.0 | 7812 | 0.2135 | 0.2012 | 0.519 | 0.481 | 7.7371 |
|
| 139 |
+
| 0.0462 | 85.0 | 7905 | 0.2148 | 0.2029 | 0.519 | 0.481 | 7.7486 |
|
| 140 |
+
| 0.0462 | 86.0 | 7998 | 0.2148 | 0.2046 | 0.5238 | 0.4762 | 7.7657 |
|
| 141 |
+
| 0.0434 | 87.0 | 8091 | 0.2148 | 0.2029 | 0.519 | 0.481 | 7.7543 |
|
| 142 |
+
| 0.0434 | 88.0 | 8184 | 0.2150 | 0.2037 | 0.519 | 0.481 | 7.7657 |
|
| 143 |
+
| 0.0434 | 89.0 | 8277 | 0.2160 | 0.2063 | 0.5238 | 0.4762 | 7.7543 |
|
| 144 |
+
| 0.0434 | 90.0 | 8370 | 0.2167 | 0.2054 | 0.5238 | 0.4762 | 7.7486 |
|
| 145 |
+
| 0.0434 | 91.0 | 8463 | 0.2168 | 0.2037 | 0.519 | 0.481 | 7.7657 |
|
| 146 |
+
| 0.0419 | 92.0 | 8556 | 0.2172 | 0.2037 | 0.5238 | 0.4762 | 7.7543 |
|
| 147 |
+
| 0.0419 | 93.0 | 8649 | 0.2183 | 0.2037 | 0.5238 | 0.4762 | 7.7486 |
|
| 148 |
+
| 0.0419 | 94.0 | 8742 | 0.2190 | 0.2063 | 0.5286 | 0.4714 | 7.7371 |
|
| 149 |
+
| 0.0419 | 95.0 | 8835 | 0.2185 | 0.2054 | 0.5238 | 0.4762 | 7.7543 |
|
| 150 |
+
| 0.0419 | 96.0 | 8928 | 0.2184 | 0.2054 | 0.5238 | 0.4762 | 7.7543 |
|
| 151 |
+
| 0.0402 | 97.0 | 9021 | 0.2190 | 0.208 | 0.5286 | 0.4714 | 7.7429 |
|
| 152 |
+
| 0.0402 | 98.0 | 9114 | 0.2189 | 0.208 | 0.5286 | 0.4714 | 7.7486 |
|
| 153 |
+
| 0.0402 | 99.0 | 9207 | 0.2190 | 0.208 | 0.5286 | 0.4714 | 7.7486 |
|
| 154 |
+
| 0.0402 | 100.0 | 9300 | 0.2191 | 0.208 | 0.5286 | 0.4714 | 7.7486 |
|
| 155 |
+
|
| 156 |
+
|
| 157 |
+
### Framework versions
|
| 158 |
+
|
| 159 |
+
- Transformers 4.33.0
|
| 160 |
+
- Pytorch 2.0.0
|
| 161 |
+
- Datasets 2.1.0
|
| 162 |
+
- Tokenizers 0.13.3
|
config.json
ADDED
|
@@ -0,0 +1,34 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "google/byt5-base",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"T5ForConditionalGeneration"
|
| 5 |
+
],
|
| 6 |
+
"classifier_dropout": 0.0,
|
| 7 |
+
"d_ff": 3968,
|
| 8 |
+
"d_kv": 64,
|
| 9 |
+
"d_model": 1536,
|
| 10 |
+
"decoder_start_token_id": 0,
|
| 11 |
+
"dense_act_fn": "gelu_new",
|
| 12 |
+
"dropout_rate": 0.1,
|
| 13 |
+
"eos_token_id": 1,
|
| 14 |
+
"feed_forward_proj": "gated-gelu",
|
| 15 |
+
"gradient_checkpointing": false,
|
| 16 |
+
"initializer_factor": 1.0,
|
| 17 |
+
"is_encoder_decoder": true,
|
| 18 |
+
"is_gated_act": true,
|
| 19 |
+
"layer_norm_epsilon": 1e-06,
|
| 20 |
+
"model_type": "t5",
|
| 21 |
+
"num_decoder_layers": 6,
|
| 22 |
+
"num_heads": 12,
|
| 23 |
+
"num_layers": 18,
|
| 24 |
+
"output_past": true,
|
| 25 |
+
"pad_token_id": 0,
|
| 26 |
+
"relative_attention_max_distance": 128,
|
| 27 |
+
"relative_attention_num_buckets": 32,
|
| 28 |
+
"tie_word_embeddings": false,
|
| 29 |
+
"tokenizer_class": "ByT5Tokenizer",
|
| 30 |
+
"torch_dtype": "float32",
|
| 31 |
+
"transformers_version": "4.33.0",
|
| 32 |
+
"use_cache": true,
|
| 33 |
+
"vocab_size": 384
|
| 34 |
+
}
|
generation_config.json
ADDED
|
@@ -0,0 +1,6 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"decoder_start_token_id": 0,
|
| 3 |
+
"eos_token_id": 1,
|
| 4 |
+
"pad_token_id": 0,
|
| 5 |
+
"transformers_version": "4.33.0"
|
| 6 |
+
}
|
pytorch_model.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:6832a31eedf025b4ebe3165498f479346c21af302fb1c11b9d516a37bad35bef
|
| 3 |
+
size 2326700029
|
special_tokens_map.json
ADDED
|
@@ -0,0 +1,150 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"additional_special_tokens": [
|
| 3 |
+
"<extra_id_0>",
|
| 4 |
+
"<extra_id_1>",
|
| 5 |
+
"<extra_id_2>",
|
| 6 |
+
"<extra_id_3>",
|
| 7 |
+
"<extra_id_4>",
|
| 8 |
+
"<extra_id_5>",
|
| 9 |
+
"<extra_id_6>",
|
| 10 |
+
"<extra_id_7>",
|
| 11 |
+
"<extra_id_8>",
|
| 12 |
+
"<extra_id_9>",
|
| 13 |
+
"<extra_id_10>",
|
| 14 |
+
"<extra_id_11>",
|
| 15 |
+
"<extra_id_12>",
|
| 16 |
+
"<extra_id_13>",
|
| 17 |
+
"<extra_id_14>",
|
| 18 |
+
"<extra_id_15>",
|
| 19 |
+
"<extra_id_16>",
|
| 20 |
+
"<extra_id_17>",
|
| 21 |
+
"<extra_id_18>",
|
| 22 |
+
"<extra_id_19>",
|
| 23 |
+
"<extra_id_20>",
|
| 24 |
+
"<extra_id_21>",
|
| 25 |
+
"<extra_id_22>",
|
| 26 |
+
"<extra_id_23>",
|
| 27 |
+
"<extra_id_24>",
|
| 28 |
+
"<extra_id_25>",
|
| 29 |
+
"<extra_id_26>",
|
| 30 |
+
"<extra_id_27>",
|
| 31 |
+
"<extra_id_28>",
|
| 32 |
+
"<extra_id_29>",
|
| 33 |
+
"<extra_id_30>",
|
| 34 |
+
"<extra_id_31>",
|
| 35 |
+
"<extra_id_32>",
|
| 36 |
+
"<extra_id_33>",
|
| 37 |
+
"<extra_id_34>",
|
| 38 |
+
"<extra_id_35>",
|
| 39 |
+
"<extra_id_36>",
|
| 40 |
+
"<extra_id_37>",
|
| 41 |
+
"<extra_id_38>",
|
| 42 |
+
"<extra_id_39>",
|
| 43 |
+
"<extra_id_40>",
|
| 44 |
+
"<extra_id_41>",
|
| 45 |
+
"<extra_id_42>",
|
| 46 |
+
"<extra_id_43>",
|
| 47 |
+
"<extra_id_44>",
|
| 48 |
+
"<extra_id_45>",
|
| 49 |
+
"<extra_id_46>",
|
| 50 |
+
"<extra_id_47>",
|
| 51 |
+
"<extra_id_48>",
|
| 52 |
+
"<extra_id_49>",
|
| 53 |
+
"<extra_id_50>",
|
| 54 |
+
"<extra_id_51>",
|
| 55 |
+
"<extra_id_52>",
|
| 56 |
+
"<extra_id_53>",
|
| 57 |
+
"<extra_id_54>",
|
| 58 |
+
"<extra_id_55>",
|
| 59 |
+
"<extra_id_56>",
|
| 60 |
+
"<extra_id_57>",
|
| 61 |
+
"<extra_id_58>",
|
| 62 |
+
"<extra_id_59>",
|
| 63 |
+
"<extra_id_60>",
|
| 64 |
+
"<extra_id_61>",
|
| 65 |
+
"<extra_id_62>",
|
| 66 |
+
"<extra_id_63>",
|
| 67 |
+
"<extra_id_64>",
|
| 68 |
+
"<extra_id_65>",
|
| 69 |
+
"<extra_id_66>",
|
| 70 |
+
"<extra_id_67>",
|
| 71 |
+
"<extra_id_68>",
|
| 72 |
+
"<extra_id_69>",
|
| 73 |
+
"<extra_id_70>",
|
| 74 |
+
"<extra_id_71>",
|
| 75 |
+
"<extra_id_72>",
|
| 76 |
+
"<extra_id_73>",
|
| 77 |
+
"<extra_id_74>",
|
| 78 |
+
"<extra_id_75>",
|
| 79 |
+
"<extra_id_76>",
|
| 80 |
+
"<extra_id_77>",
|
| 81 |
+
"<extra_id_78>",
|
| 82 |
+
"<extra_id_79>",
|
| 83 |
+
"<extra_id_80>",
|
| 84 |
+
"<extra_id_81>",
|
| 85 |
+
"<extra_id_82>",
|
| 86 |
+
"<extra_id_83>",
|
| 87 |
+
"<extra_id_84>",
|
| 88 |
+
"<extra_id_85>",
|
| 89 |
+
"<extra_id_86>",
|
| 90 |
+
"<extra_id_87>",
|
| 91 |
+
"<extra_id_88>",
|
| 92 |
+
"<extra_id_89>",
|
| 93 |
+
"<extra_id_90>",
|
| 94 |
+
"<extra_id_91>",
|
| 95 |
+
"<extra_id_92>",
|
| 96 |
+
"<extra_id_93>",
|
| 97 |
+
"<extra_id_94>",
|
| 98 |
+
"<extra_id_95>",
|
| 99 |
+
"<extra_id_96>",
|
| 100 |
+
"<extra_id_97>",
|
| 101 |
+
"<extra_id_98>",
|
| 102 |
+
"<extra_id_99>",
|
| 103 |
+
"<extra_id_100>",
|
| 104 |
+
"<extra_id_101>",
|
| 105 |
+
"<extra_id_102>",
|
| 106 |
+
"<extra_id_103>",
|
| 107 |
+
"<extra_id_104>",
|
| 108 |
+
"<extra_id_105>",
|
| 109 |
+
"<extra_id_106>",
|
| 110 |
+
"<extra_id_107>",
|
| 111 |
+
"<extra_id_108>",
|
| 112 |
+
"<extra_id_109>",
|
| 113 |
+
"<extra_id_110>",
|
| 114 |
+
"<extra_id_111>",
|
| 115 |
+
"<extra_id_112>",
|
| 116 |
+
"<extra_id_113>",
|
| 117 |
+
"<extra_id_114>",
|
| 118 |
+
"<extra_id_115>",
|
| 119 |
+
"<extra_id_116>",
|
| 120 |
+
"<extra_id_117>",
|
| 121 |
+
"<extra_id_118>",
|
| 122 |
+
"<extra_id_119>",
|
| 123 |
+
"<extra_id_120>",
|
| 124 |
+
"<extra_id_121>",
|
| 125 |
+
"<extra_id_122>",
|
| 126 |
+
"<extra_id_123>",
|
| 127 |
+
"<extra_id_124>"
|
| 128 |
+
],
|
| 129 |
+
"eos_token": {
|
| 130 |
+
"content": "</s>",
|
| 131 |
+
"lstrip": false,
|
| 132 |
+
"normalized": true,
|
| 133 |
+
"rstrip": false,
|
| 134 |
+
"single_word": false
|
| 135 |
+
},
|
| 136 |
+
"pad_token": {
|
| 137 |
+
"content": "<pad>",
|
| 138 |
+
"lstrip": false,
|
| 139 |
+
"normalized": true,
|
| 140 |
+
"rstrip": false,
|
| 141 |
+
"single_word": false
|
| 142 |
+
},
|
| 143 |
+
"unk_token": {
|
| 144 |
+
"content": "<unk>",
|
| 145 |
+
"lstrip": false,
|
| 146 |
+
"normalized": true,
|
| 147 |
+
"rstrip": false,
|
| 148 |
+
"single_word": false
|
| 149 |
+
}
|
| 150 |
+
}
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,157 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"additional_special_tokens": [
|
| 3 |
+
"<extra_id_0>",
|
| 4 |
+
"<extra_id_1>",
|
| 5 |
+
"<extra_id_2>",
|
| 6 |
+
"<extra_id_3>",
|
| 7 |
+
"<extra_id_4>",
|
| 8 |
+
"<extra_id_5>",
|
| 9 |
+
"<extra_id_6>",
|
| 10 |
+
"<extra_id_7>",
|
| 11 |
+
"<extra_id_8>",
|
| 12 |
+
"<extra_id_9>",
|
| 13 |
+
"<extra_id_10>",
|
| 14 |
+
"<extra_id_11>",
|
| 15 |
+
"<extra_id_12>",
|
| 16 |
+
"<extra_id_13>",
|
| 17 |
+
"<extra_id_14>",
|
| 18 |
+
"<extra_id_15>",
|
| 19 |
+
"<extra_id_16>",
|
| 20 |
+
"<extra_id_17>",
|
| 21 |
+
"<extra_id_18>",
|
| 22 |
+
"<extra_id_19>",
|
| 23 |
+
"<extra_id_20>",
|
| 24 |
+
"<extra_id_21>",
|
| 25 |
+
"<extra_id_22>",
|
| 26 |
+
"<extra_id_23>",
|
| 27 |
+
"<extra_id_24>",
|
| 28 |
+
"<extra_id_25>",
|
| 29 |
+
"<extra_id_26>",
|
| 30 |
+
"<extra_id_27>",
|
| 31 |
+
"<extra_id_28>",
|
| 32 |
+
"<extra_id_29>",
|
| 33 |
+
"<extra_id_30>",
|
| 34 |
+
"<extra_id_31>",
|
| 35 |
+
"<extra_id_32>",
|
| 36 |
+
"<extra_id_33>",
|
| 37 |
+
"<extra_id_34>",
|
| 38 |
+
"<extra_id_35>",
|
| 39 |
+
"<extra_id_36>",
|
| 40 |
+
"<extra_id_37>",
|
| 41 |
+
"<extra_id_38>",
|
| 42 |
+
"<extra_id_39>",
|
| 43 |
+
"<extra_id_40>",
|
| 44 |
+
"<extra_id_41>",
|
| 45 |
+
"<extra_id_42>",
|
| 46 |
+
"<extra_id_43>",
|
| 47 |
+
"<extra_id_44>",
|
| 48 |
+
"<extra_id_45>",
|
| 49 |
+
"<extra_id_46>",
|
| 50 |
+
"<extra_id_47>",
|
| 51 |
+
"<extra_id_48>",
|
| 52 |
+
"<extra_id_49>",
|
| 53 |
+
"<extra_id_50>",
|
| 54 |
+
"<extra_id_51>",
|
| 55 |
+
"<extra_id_52>",
|
| 56 |
+
"<extra_id_53>",
|
| 57 |
+
"<extra_id_54>",
|
| 58 |
+
"<extra_id_55>",
|
| 59 |
+
"<extra_id_56>",
|
| 60 |
+
"<extra_id_57>",
|
| 61 |
+
"<extra_id_58>",
|
| 62 |
+
"<extra_id_59>",
|
| 63 |
+
"<extra_id_60>",
|
| 64 |
+
"<extra_id_61>",
|
| 65 |
+
"<extra_id_62>",
|
| 66 |
+
"<extra_id_63>",
|
| 67 |
+
"<extra_id_64>",
|
| 68 |
+
"<extra_id_65>",
|
| 69 |
+
"<extra_id_66>",
|
| 70 |
+
"<extra_id_67>",
|
| 71 |
+
"<extra_id_68>",
|
| 72 |
+
"<extra_id_69>",
|
| 73 |
+
"<extra_id_70>",
|
| 74 |
+
"<extra_id_71>",
|
| 75 |
+
"<extra_id_72>",
|
| 76 |
+
"<extra_id_73>",
|
| 77 |
+
"<extra_id_74>",
|
| 78 |
+
"<extra_id_75>",
|
| 79 |
+
"<extra_id_76>",
|
| 80 |
+
"<extra_id_77>",
|
| 81 |
+
"<extra_id_78>",
|
| 82 |
+
"<extra_id_79>",
|
| 83 |
+
"<extra_id_80>",
|
| 84 |
+
"<extra_id_81>",
|
| 85 |
+
"<extra_id_82>",
|
| 86 |
+
"<extra_id_83>",
|
| 87 |
+
"<extra_id_84>",
|
| 88 |
+
"<extra_id_85>",
|
| 89 |
+
"<extra_id_86>",
|
| 90 |
+
"<extra_id_87>",
|
| 91 |
+
"<extra_id_88>",
|
| 92 |
+
"<extra_id_89>",
|
| 93 |
+
"<extra_id_90>",
|
| 94 |
+
"<extra_id_91>",
|
| 95 |
+
"<extra_id_92>",
|
| 96 |
+
"<extra_id_93>",
|
| 97 |
+
"<extra_id_94>",
|
| 98 |
+
"<extra_id_95>",
|
| 99 |
+
"<extra_id_96>",
|
| 100 |
+
"<extra_id_97>",
|
| 101 |
+
"<extra_id_98>",
|
| 102 |
+
"<extra_id_99>",
|
| 103 |
+
"<extra_id_100>",
|
| 104 |
+
"<extra_id_101>",
|
| 105 |
+
"<extra_id_102>",
|
| 106 |
+
"<extra_id_103>",
|
| 107 |
+
"<extra_id_104>",
|
| 108 |
+
"<extra_id_105>",
|
| 109 |
+
"<extra_id_106>",
|
| 110 |
+
"<extra_id_107>",
|
| 111 |
+
"<extra_id_108>",
|
| 112 |
+
"<extra_id_109>",
|
| 113 |
+
"<extra_id_110>",
|
| 114 |
+
"<extra_id_111>",
|
| 115 |
+
"<extra_id_112>",
|
| 116 |
+
"<extra_id_113>",
|
| 117 |
+
"<extra_id_114>",
|
| 118 |
+
"<extra_id_115>",
|
| 119 |
+
"<extra_id_116>",
|
| 120 |
+
"<extra_id_117>",
|
| 121 |
+
"<extra_id_118>",
|
| 122 |
+
"<extra_id_119>",
|
| 123 |
+
"<extra_id_120>",
|
| 124 |
+
"<extra_id_121>",
|
| 125 |
+
"<extra_id_122>",
|
| 126 |
+
"<extra_id_123>",
|
| 127 |
+
"<extra_id_124>"
|
| 128 |
+
],
|
| 129 |
+
"clean_up_tokenization_spaces": true,
|
| 130 |
+
"eos_token": {
|
| 131 |
+
"__type": "AddedToken",
|
| 132 |
+
"content": "</s>",
|
| 133 |
+
"lstrip": false,
|
| 134 |
+
"normalized": true,
|
| 135 |
+
"rstrip": false,
|
| 136 |
+
"single_word": false
|
| 137 |
+
},
|
| 138 |
+
"extra_ids": 125,
|
| 139 |
+
"model_max_length": 1000000000000000019884624838656,
|
| 140 |
+
"pad_token": {
|
| 141 |
+
"__type": "AddedToken",
|
| 142 |
+
"content": "<pad>",
|
| 143 |
+
"lstrip": false,
|
| 144 |
+
"normalized": true,
|
| 145 |
+
"rstrip": false,
|
| 146 |
+
"single_word": false
|
| 147 |
+
},
|
| 148 |
+
"tokenizer_class": "ByT5Tokenizer",
|
| 149 |
+
"unk_token": {
|
| 150 |
+
"__type": "AddedToken",
|
| 151 |
+
"content": "<unk>",
|
| 152 |
+
"lstrip": false,
|
| 153 |
+
"normalized": true,
|
| 154 |
+
"rstrip": false,
|
| 155 |
+
"single_word": false
|
| 156 |
+
}
|
| 157 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:3690d27efe2fc6037c3cf4122d08784aee66211fea4c5ac6839dc17bedc7c61d
|
| 3 |
+
size 4219
|