End of training
Browse files- README.md +165 -0
- config.json +18 -20
- model.safetensors +2 -2
- special_tokens_map.json +6 -42
- tokenizer.json +2 -2
- tokenizer_config.json +2 -1
- training_args.bin +2 -2
README.md
ADDED
|
@@ -0,0 +1,165 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: mit
|
| 3 |
+
base_model: microsoft/Multilingual-MiniLM-L12-H384
|
| 4 |
+
tags:
|
| 5 |
+
- generated_from_trainer
|
| 6 |
+
metrics:
|
| 7 |
+
- precision
|
| 8 |
+
- recall
|
| 9 |
+
- f1
|
| 10 |
+
- accuracy
|
| 11 |
+
model-index:
|
| 12 |
+
- name: ner-coin-v3
|
| 13 |
+
results: []
|
| 14 |
+
---
|
| 15 |
+
|
| 16 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 17 |
+
should probably proofread and complete it, then remove this comment. -->
|
| 18 |
+
|
| 19 |
+
# ner-coin-v3
|
| 20 |
+
|
| 21 |
+
This model is a fine-tuned version of [microsoft/Multilingual-MiniLM-L12-H384](https://huggingface.co/microsoft/Multilingual-MiniLM-L12-H384) on the None dataset.
|
| 22 |
+
It achieves the following results on the evaluation set:
|
| 23 |
+
- Loss: 0.0147
|
| 24 |
+
- Precision: 0.9941
|
| 25 |
+
- Recall: 0.9931
|
| 26 |
+
- F1: 0.9936
|
| 27 |
+
- Accuracy: 0.9978
|
| 28 |
+
|
| 29 |
+
## Model description
|
| 30 |
+
|
| 31 |
+
More information needed
|
| 32 |
+
|
| 33 |
+
## Intended uses & limitations
|
| 34 |
+
|
| 35 |
+
More information needed
|
| 36 |
+
|
| 37 |
+
## Training and evaluation data
|
| 38 |
+
|
| 39 |
+
More information needed
|
| 40 |
+
|
| 41 |
+
## Training procedure
|
| 42 |
+
|
| 43 |
+
### Training hyperparameters
|
| 44 |
+
|
| 45 |
+
The following hyperparameters were used during training:
|
| 46 |
+
- learning_rate: 5e-05
|
| 47 |
+
- train_batch_size: 64
|
| 48 |
+
- eval_batch_size: 64
|
| 49 |
+
- seed: 42
|
| 50 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 51 |
+
- lr_scheduler_type: linear
|
| 52 |
+
- num_epochs: 100
|
| 53 |
+
|
| 54 |
+
### Training results
|
| 55 |
+
|
| 56 |
+
| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
|
| 57 |
+
|:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
|
| 58 |
+
| No log | 1.0 | 52 | 0.1916 | 0.9775 | 0.9777 | 0.9776 | 0.9935 |
|
| 59 |
+
| No log | 2.0 | 104 | 0.1443 | 0.9815 | 0.9823 | 0.9819 | 0.9948 |
|
| 60 |
+
| No log | 3.0 | 156 | 0.1142 | 0.9844 | 0.9844 | 0.9844 | 0.9953 |
|
| 61 |
+
| No log | 4.0 | 208 | 0.0938 | 0.9852 | 0.9834 | 0.9843 | 0.9952 |
|
| 62 |
+
| No log | 5.0 | 260 | 0.0764 | 0.9870 | 0.9870 | 0.9870 | 0.9959 |
|
| 63 |
+
| No log | 6.0 | 312 | 0.0649 | 0.9876 | 0.9874 | 0.9875 | 0.9962 |
|
| 64 |
+
| No log | 7.0 | 364 | 0.0552 | 0.9903 | 0.9893 | 0.9898 | 0.9968 |
|
| 65 |
+
| No log | 8.0 | 416 | 0.0500 | 0.9884 | 0.9876 | 0.988 | 0.9962 |
|
| 66 |
+
| No log | 9.0 | 468 | 0.0443 | 0.9882 | 0.9878 | 0.9880 | 0.9963 |
|
| 67 |
+
| 0.1249 | 10.0 | 520 | 0.0402 | 0.9882 | 0.9880 | 0.9881 | 0.9962 |
|
| 68 |
+
| 0.1249 | 11.0 | 572 | 0.0351 | 0.9901 | 0.9884 | 0.9893 | 0.9967 |
|
| 69 |
+
| 0.1249 | 12.0 | 624 | 0.0315 | 0.9909 | 0.9882 | 0.9896 | 0.9969 |
|
| 70 |
+
| 0.1249 | 13.0 | 676 | 0.0307 | 0.9897 | 0.9888 | 0.9893 | 0.9966 |
|
| 71 |
+
| 0.1249 | 14.0 | 728 | 0.0268 | 0.9897 | 0.9895 | 0.9896 | 0.9967 |
|
| 72 |
+
| 0.1249 | 15.0 | 780 | 0.0277 | 0.9897 | 0.9861 | 0.9879 | 0.9962 |
|
| 73 |
+
| 0.1249 | 16.0 | 832 | 0.0242 | 0.9916 | 0.9893 | 0.9904 | 0.9971 |
|
| 74 |
+
| 0.1249 | 17.0 | 884 | 0.0214 | 0.9920 | 0.9901 | 0.9910 | 0.9973 |
|
| 75 |
+
| 0.1249 | 18.0 | 936 | 0.0216 | 0.9920 | 0.9895 | 0.9907 | 0.9972 |
|
| 76 |
+
| 0.1249 | 19.0 | 988 | 0.0211 | 0.9922 | 0.9899 | 0.9910 | 0.9972 |
|
| 77 |
+
| 0.0243 | 20.0 | 1040 | 0.0183 | 0.9930 | 0.9912 | 0.9921 | 0.9975 |
|
| 78 |
+
| 0.0243 | 21.0 | 1092 | 0.0161 | 0.9922 | 0.9907 | 0.9915 | 0.9974 |
|
| 79 |
+
| 0.0243 | 22.0 | 1144 | 0.0169 | 0.9935 | 0.9914 | 0.9924 | 0.9975 |
|
| 80 |
+
| 0.0243 | 23.0 | 1196 | 0.0176 | 0.9914 | 0.9897 | 0.9905 | 0.9972 |
|
| 81 |
+
| 0.0243 | 24.0 | 1248 | 0.0160 | 0.9918 | 0.9905 | 0.9912 | 0.9973 |
|
| 82 |
+
| 0.0243 | 25.0 | 1300 | 0.0150 | 0.9928 | 0.9918 | 0.9923 | 0.9974 |
|
| 83 |
+
| 0.0243 | 26.0 | 1352 | 0.0143 | 0.9935 | 0.9918 | 0.9926 | 0.9977 |
|
| 84 |
+
| 0.0243 | 27.0 | 1404 | 0.0140 | 0.9920 | 0.9918 | 0.9919 | 0.9973 |
|
| 85 |
+
| 0.0243 | 28.0 | 1456 | 0.0152 | 0.9909 | 0.9905 | 0.9907 | 0.9970 |
|
| 86 |
+
| 0.0111 | 29.0 | 1508 | 0.0147 | 0.9916 | 0.9907 | 0.9912 | 0.9972 |
|
| 87 |
+
| 0.0111 | 30.0 | 1560 | 0.0146 | 0.9920 | 0.9912 | 0.9916 | 0.9973 |
|
| 88 |
+
| 0.0111 | 31.0 | 1612 | 0.0143 | 0.9912 | 0.9905 | 0.9908 | 0.9970 |
|
| 89 |
+
| 0.0111 | 32.0 | 1664 | 0.0139 | 0.9907 | 0.9905 | 0.9906 | 0.9970 |
|
| 90 |
+
| 0.0111 | 33.0 | 1716 | 0.0144 | 0.9912 | 0.9912 | 0.9912 | 0.9970 |
|
| 91 |
+
| 0.0111 | 34.0 | 1768 | 0.0137 | 0.9922 | 0.9916 | 0.9919 | 0.9973 |
|
| 92 |
+
| 0.0111 | 35.0 | 1820 | 0.0139 | 0.9937 | 0.9926 | 0.9932 | 0.9977 |
|
| 93 |
+
| 0.0111 | 36.0 | 1872 | 0.0146 | 0.9912 | 0.9914 | 0.9913 | 0.9970 |
|
| 94 |
+
| 0.0111 | 37.0 | 1924 | 0.0138 | 0.9928 | 0.9920 | 0.9924 | 0.9975 |
|
| 95 |
+
| 0.0111 | 38.0 | 1976 | 0.0125 | 0.9933 | 0.9928 | 0.9931 | 0.9977 |
|
| 96 |
+
| 0.0062 | 39.0 | 2028 | 0.0138 | 0.9922 | 0.9914 | 0.9918 | 0.9973 |
|
| 97 |
+
| 0.0062 | 40.0 | 2080 | 0.0131 | 0.9918 | 0.9910 | 0.9914 | 0.9972 |
|
| 98 |
+
| 0.0062 | 41.0 | 2132 | 0.0141 | 0.9914 | 0.9912 | 0.9913 | 0.9971 |
|
| 99 |
+
| 0.0062 | 42.0 | 2184 | 0.0137 | 0.9930 | 0.9922 | 0.9926 | 0.9975 |
|
| 100 |
+
| 0.0062 | 43.0 | 2236 | 0.0139 | 0.9920 | 0.9910 | 0.9915 | 0.9973 |
|
| 101 |
+
| 0.0062 | 44.0 | 2288 | 0.0146 | 0.9924 | 0.9920 | 0.9922 | 0.9974 |
|
| 102 |
+
| 0.0062 | 45.0 | 2340 | 0.0134 | 0.9933 | 0.9924 | 0.9928 | 0.9977 |
|
| 103 |
+
| 0.0062 | 46.0 | 2392 | 0.0149 | 0.9935 | 0.9924 | 0.9929 | 0.9977 |
|
| 104 |
+
| 0.0062 | 47.0 | 2444 | 0.0124 | 0.9933 | 0.9926 | 0.9929 | 0.9977 |
|
| 105 |
+
| 0.0062 | 48.0 | 2496 | 0.0125 | 0.9931 | 0.9924 | 0.9927 | 0.9976 |
|
| 106 |
+
| 0.0037 | 49.0 | 2548 | 0.0130 | 0.9916 | 0.9910 | 0.9913 | 0.9972 |
|
| 107 |
+
| 0.0037 | 50.0 | 2600 | 0.0129 | 0.9928 | 0.9924 | 0.9926 | 0.9975 |
|
| 108 |
+
| 0.0037 | 51.0 | 2652 | 0.0128 | 0.9935 | 0.9926 | 0.9931 | 0.9975 |
|
| 109 |
+
| 0.0037 | 52.0 | 2704 | 0.0136 | 0.9922 | 0.9918 | 0.9920 | 0.9973 |
|
| 110 |
+
| 0.0037 | 53.0 | 2756 | 0.0141 | 0.9926 | 0.9916 | 0.9921 | 0.9974 |
|
| 111 |
+
| 0.0037 | 54.0 | 2808 | 0.0135 | 0.9933 | 0.9926 | 0.9929 | 0.9978 |
|
| 112 |
+
| 0.0037 | 55.0 | 2860 | 0.0147 | 0.9935 | 0.9922 | 0.9928 | 0.9975 |
|
| 113 |
+
| 0.0037 | 56.0 | 2912 | 0.0142 | 0.9935 | 0.9926 | 0.9931 | 0.9977 |
|
| 114 |
+
| 0.0037 | 57.0 | 2964 | 0.0139 | 0.9931 | 0.9926 | 0.9928 | 0.9975 |
|
| 115 |
+
| 0.0027 | 58.0 | 3016 | 0.0136 | 0.9935 | 0.9928 | 0.9932 | 0.9977 |
|
| 116 |
+
| 0.0027 | 59.0 | 3068 | 0.0143 | 0.9935 | 0.9926 | 0.9931 | 0.9976 |
|
| 117 |
+
| 0.0027 | 60.0 | 3120 | 0.0141 | 0.9933 | 0.9926 | 0.9929 | 0.9975 |
|
| 118 |
+
| 0.0027 | 61.0 | 3172 | 0.0129 | 0.9939 | 0.9931 | 0.9935 | 0.9978 |
|
| 119 |
+
| 0.0027 | 62.0 | 3224 | 0.0137 | 0.9939 | 0.9931 | 0.9935 | 0.9978 |
|
| 120 |
+
| 0.0027 | 63.0 | 3276 | 0.0136 | 0.9935 | 0.9924 | 0.9929 | 0.9977 |
|
| 121 |
+
| 0.0027 | 64.0 | 3328 | 0.0141 | 0.9933 | 0.9926 | 0.9929 | 0.9977 |
|
| 122 |
+
| 0.0027 | 65.0 | 3380 | 0.0141 | 0.9939 | 0.9931 | 0.9935 | 0.9978 |
|
| 123 |
+
| 0.0027 | 66.0 | 3432 | 0.0137 | 0.9939 | 0.9928 | 0.9934 | 0.9978 |
|
| 124 |
+
| 0.0027 | 67.0 | 3484 | 0.0145 | 0.9924 | 0.9916 | 0.992 | 0.9973 |
|
| 125 |
+
| 0.0019 | 68.0 | 3536 | 0.0150 | 0.9937 | 0.9924 | 0.9931 | 0.9977 |
|
| 126 |
+
| 0.0019 | 69.0 | 3588 | 0.0152 | 0.9930 | 0.9920 | 0.9925 | 0.9975 |
|
| 127 |
+
| 0.0019 | 70.0 | 3640 | 0.0149 | 0.9926 | 0.9918 | 0.9922 | 0.9973 |
|
| 128 |
+
| 0.0019 | 71.0 | 3692 | 0.0143 | 0.9935 | 0.9924 | 0.9929 | 0.9976 |
|
| 129 |
+
| 0.0019 | 72.0 | 3744 | 0.0152 | 0.9937 | 0.9924 | 0.9931 | 0.9977 |
|
| 130 |
+
| 0.0019 | 73.0 | 3796 | 0.0149 | 0.9933 | 0.9922 | 0.9927 | 0.9975 |
|
| 131 |
+
| 0.0019 | 74.0 | 3848 | 0.0158 | 0.9935 | 0.9922 | 0.9928 | 0.9976 |
|
| 132 |
+
| 0.0019 | 75.0 | 3900 | 0.0153 | 0.9928 | 0.9918 | 0.9923 | 0.9975 |
|
| 133 |
+
| 0.0019 | 76.0 | 3952 | 0.0154 | 0.9928 | 0.9920 | 0.9924 | 0.9975 |
|
| 134 |
+
| 0.0015 | 77.0 | 4004 | 0.0145 | 0.9937 | 0.9928 | 0.9933 | 0.9977 |
|
| 135 |
+
| 0.0015 | 78.0 | 4056 | 0.0158 | 0.9928 | 0.9920 | 0.9924 | 0.9975 |
|
| 136 |
+
| 0.0015 | 79.0 | 4108 | 0.0161 | 0.9933 | 0.9922 | 0.9927 | 0.9975 |
|
| 137 |
+
| 0.0015 | 80.0 | 4160 | 0.0155 | 0.9935 | 0.9924 | 0.9929 | 0.9976 |
|
| 138 |
+
| 0.0015 | 81.0 | 4212 | 0.0157 | 0.9933 | 0.9922 | 0.9927 | 0.9975 |
|
| 139 |
+
| 0.0015 | 82.0 | 4264 | 0.0155 | 0.9933 | 0.9922 | 0.9927 | 0.9975 |
|
| 140 |
+
| 0.0015 | 83.0 | 4316 | 0.0144 | 0.9939 | 0.9931 | 0.9935 | 0.9978 |
|
| 141 |
+
| 0.0015 | 84.0 | 4368 | 0.0142 | 0.9939 | 0.9931 | 0.9935 | 0.9978 |
|
| 142 |
+
| 0.0015 | 85.0 | 4420 | 0.0145 | 0.9941 | 0.9931 | 0.9936 | 0.9978 |
|
| 143 |
+
| 0.0015 | 86.0 | 4472 | 0.0151 | 0.9935 | 0.9924 | 0.9929 | 0.9977 |
|
| 144 |
+
| 0.0013 | 87.0 | 4524 | 0.0143 | 0.9935 | 0.9924 | 0.9929 | 0.9977 |
|
| 145 |
+
| 0.0013 | 88.0 | 4576 | 0.0145 | 0.9933 | 0.9924 | 0.9928 | 0.9976 |
|
| 146 |
+
| 0.0013 | 89.0 | 4628 | 0.0142 | 0.9935 | 0.9926 | 0.9931 | 0.9976 |
|
| 147 |
+
| 0.0013 | 90.0 | 4680 | 0.0142 | 0.9941 | 0.9933 | 0.9937 | 0.9978 |
|
| 148 |
+
| 0.0013 | 91.0 | 4732 | 0.0145 | 0.9941 | 0.9931 | 0.9936 | 0.9978 |
|
| 149 |
+
| 0.0013 | 92.0 | 4784 | 0.0146 | 0.9941 | 0.9931 | 0.9936 | 0.9978 |
|
| 150 |
+
| 0.0013 | 93.0 | 4836 | 0.0146 | 0.9939 | 0.9931 | 0.9935 | 0.9978 |
|
| 151 |
+
| 0.0013 | 94.0 | 4888 | 0.0147 | 0.9941 | 0.9931 | 0.9936 | 0.9978 |
|
| 152 |
+
| 0.0013 | 95.0 | 4940 | 0.0148 | 0.9941 | 0.9931 | 0.9936 | 0.9978 |
|
| 153 |
+
| 0.0013 | 96.0 | 4992 | 0.0147 | 0.9941 | 0.9931 | 0.9936 | 0.9978 |
|
| 154 |
+
| 0.0011 | 97.0 | 5044 | 0.0147 | 0.9939 | 0.9931 | 0.9935 | 0.9978 |
|
| 155 |
+
| 0.0011 | 98.0 | 5096 | 0.0147 | 0.9939 | 0.9931 | 0.9935 | 0.9978 |
|
| 156 |
+
| 0.0011 | 99.0 | 5148 | 0.0147 | 0.9939 | 0.9931 | 0.9935 | 0.9978 |
|
| 157 |
+
| 0.0011 | 100.0 | 5200 | 0.0147 | 0.9941 | 0.9931 | 0.9936 | 0.9978 |
|
| 158 |
+
|
| 159 |
+
|
| 160 |
+
### Framework versions
|
| 161 |
+
|
| 162 |
+
- Transformers 4.41.2
|
| 163 |
+
- Pytorch 2.3.0+cu121
|
| 164 |
+
- Datasets 2.14.6
|
| 165 |
+
- Tokenizers 0.19.1
|
config.json
CHANGED
|
@@ -1,39 +1,37 @@
|
|
| 1 |
{
|
| 2 |
-
"_name_or_path": "
|
| 3 |
"architectures": [
|
| 4 |
-
"
|
| 5 |
],
|
| 6 |
"attention_probs_dropout_prob": 0.1,
|
| 7 |
-
"bos_token_id": 0,
|
| 8 |
"classifier_dropout": null,
|
| 9 |
-
"eos_token_id": 2,
|
| 10 |
"finetuning_task": "ner",
|
| 11 |
"hidden_act": "gelu",
|
| 12 |
"hidden_dropout_prob": 0.1,
|
| 13 |
-
"hidden_size":
|
| 14 |
"id2label": {
|
| 15 |
-
"0": "
|
| 16 |
"1": "B-COIN",
|
| 17 |
-
"2": "
|
| 18 |
},
|
| 19 |
"initializer_range": 0.02,
|
| 20 |
-
"intermediate_size":
|
| 21 |
"label2id": {
|
| 22 |
"B-COIN": 1,
|
| 23 |
-
"I-COIN":
|
| 24 |
-
"O":
|
| 25 |
},
|
| 26 |
-
"layer_norm_eps": 1e-
|
| 27 |
-
"max_position_embeddings":
|
| 28 |
-
"model_type": "
|
| 29 |
-
"num_attention_heads":
|
| 30 |
-
"num_hidden_layers":
|
| 31 |
-
"
|
| 32 |
-
"pad_token_id": 1,
|
| 33 |
"position_embedding_type": "absolute",
|
|
|
|
| 34 |
"torch_dtype": "float32",
|
| 35 |
-
"transformers_version": "4.
|
| 36 |
-
"type_vocab_size":
|
| 37 |
"use_cache": true,
|
| 38 |
-
"vocab_size":
|
| 39 |
}
|
|
|
|
| 1 |
{
|
| 2 |
+
"_name_or_path": "microsoft/Multilingual-MiniLM-L12-H384",
|
| 3 |
"architectures": [
|
| 4 |
+
"BertForTokenClassification"
|
| 5 |
],
|
| 6 |
"attention_probs_dropout_prob": 0.1,
|
|
|
|
| 7 |
"classifier_dropout": null,
|
|
|
|
| 8 |
"finetuning_task": "ner",
|
| 9 |
"hidden_act": "gelu",
|
| 10 |
"hidden_dropout_prob": 0.1,
|
| 11 |
+
"hidden_size": 384,
|
| 12 |
"id2label": {
|
| 13 |
+
"0": "O",
|
| 14 |
"1": "B-COIN",
|
| 15 |
+
"2": "I-COIN"
|
| 16 |
},
|
| 17 |
"initializer_range": 0.02,
|
| 18 |
+
"intermediate_size": 1536,
|
| 19 |
"label2id": {
|
| 20 |
"B-COIN": 1,
|
| 21 |
+
"I-COIN": 2,
|
| 22 |
+
"O": 0
|
| 23 |
},
|
| 24 |
+
"layer_norm_eps": 1e-12,
|
| 25 |
+
"max_position_embeddings": 512,
|
| 26 |
+
"model_type": "bert",
|
| 27 |
+
"num_attention_heads": 12,
|
| 28 |
+
"num_hidden_layers": 12,
|
| 29 |
+
"pad_token_id": 0,
|
|
|
|
| 30 |
"position_embedding_type": "absolute",
|
| 31 |
+
"tokenizer_class": "XLMRobertaTokenizer",
|
| 32 |
"torch_dtype": "float32",
|
| 33 |
+
"transformers_version": "4.41.2",
|
| 34 |
+
"type_vocab_size": 2,
|
| 35 |
"use_cache": true,
|
| 36 |
+
"vocab_size": 250037
|
| 37 |
}
|
model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4322cbc382b07176575dad19c17383491cc473580391c297016fa86afbfa79e1
|
| 3 |
+
size 470051652
|
special_tokens_map.json
CHANGED
|
@@ -1,25 +1,7 @@
|
|
| 1 |
{
|
| 2 |
-
"bos_token":
|
| 3 |
-
|
| 4 |
-
|
| 5 |
-
"normalized": false,
|
| 6 |
-
"rstrip": false,
|
| 7 |
-
"single_word": false
|
| 8 |
-
},
|
| 9 |
-
"cls_token": {
|
| 10 |
-
"content": "<s>",
|
| 11 |
-
"lstrip": false,
|
| 12 |
-
"normalized": false,
|
| 13 |
-
"rstrip": false,
|
| 14 |
-
"single_word": false
|
| 15 |
-
},
|
| 16 |
-
"eos_token": {
|
| 17 |
-
"content": "</s>",
|
| 18 |
-
"lstrip": false,
|
| 19 |
-
"normalized": false,
|
| 20 |
-
"rstrip": false,
|
| 21 |
-
"single_word": false
|
| 22 |
-
},
|
| 23 |
"mask_token": {
|
| 24 |
"content": "<mask>",
|
| 25 |
"lstrip": true,
|
|
@@ -27,25 +9,7 @@
|
|
| 27 |
"rstrip": false,
|
| 28 |
"single_word": false
|
| 29 |
},
|
| 30 |
-
"pad_token":
|
| 31 |
-
|
| 32 |
-
|
| 33 |
-
"normalized": false,
|
| 34 |
-
"rstrip": false,
|
| 35 |
-
"single_word": false
|
| 36 |
-
},
|
| 37 |
-
"sep_token": {
|
| 38 |
-
"content": "</s>",
|
| 39 |
-
"lstrip": false,
|
| 40 |
-
"normalized": false,
|
| 41 |
-
"rstrip": false,
|
| 42 |
-
"single_word": false
|
| 43 |
-
},
|
| 44 |
-
"unk_token": {
|
| 45 |
-
"content": "<unk>",
|
| 46 |
-
"lstrip": false,
|
| 47 |
-
"normalized": false,
|
| 48 |
-
"rstrip": false,
|
| 49 |
-
"single_word": false
|
| 50 |
-
}
|
| 51 |
}
|
|
|
|
| 1 |
{
|
| 2 |
+
"bos_token": "<s>",
|
| 3 |
+
"cls_token": "<s>",
|
| 4 |
+
"eos_token": "</s>",
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 5 |
"mask_token": {
|
| 6 |
"content": "<mask>",
|
| 7 |
"lstrip": true,
|
|
|
|
| 9 |
"rstrip": false,
|
| 10 |
"single_word": false
|
| 11 |
},
|
| 12 |
+
"pad_token": "<pad>",
|
| 13 |
+
"sep_token": "</s>",
|
| 14 |
+
"unk_token": "<unk>"
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 15 |
}
|
tokenizer.json
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b74659c780d49afad7a7b9799868f75cbd3014fb6c34956e85a793028d38094a
|
| 3 |
+
size 17098251
|
tokenizer_config.json
CHANGED
|
@@ -46,9 +46,10 @@
|
|
| 46 |
"cls_token": "<s>",
|
| 47 |
"eos_token": "</s>",
|
| 48 |
"mask_token": "<mask>",
|
| 49 |
-
"model_max_length":
|
| 50 |
"pad_token": "<pad>",
|
| 51 |
"sep_token": "</s>",
|
|
|
|
| 52 |
"tokenizer_class": "XLMRobertaTokenizer",
|
| 53 |
"unk_token": "<unk>"
|
| 54 |
}
|
|
|
|
| 46 |
"cls_token": "<s>",
|
| 47 |
"eos_token": "</s>",
|
| 48 |
"mask_token": "<mask>",
|
| 49 |
+
"model_max_length": 1000000000000000019884624838656,
|
| 50 |
"pad_token": "<pad>",
|
| 51 |
"sep_token": "</s>",
|
| 52 |
+
"sp_model_kwargs": {},
|
| 53 |
"tokenizer_class": "XLMRobertaTokenizer",
|
| 54 |
"unk_token": "<unk>"
|
| 55 |
}
|
training_args.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:0c38ec699469bac39e2b254d6b478139bdb1db105ef1183b6ca42d4c6ade7c27
|
| 3 |
+
size 5112
|