Initial Commit
Browse files- README.md +73 -87
- eval_result_ner.json +1 -1
- model.safetensors +1 -1
- training_args.bin +1 -1
README.md
CHANGED
|
@@ -1,14 +1,14 @@
|
|
| 1 |
---
|
| 2 |
-
base_model: microsoft/mdeberta-v3-base
|
| 3 |
library_name: transformers
|
| 4 |
license: mit
|
|
|
|
|
|
|
|
|
|
| 5 |
metrics:
|
| 6 |
- precision
|
| 7 |
- recall
|
| 8 |
- f1
|
| 9 |
- accuracy
|
| 10 |
-
tags:
|
| 11 |
-
- generated_from_trainer
|
| 12 |
model-index:
|
| 13 |
- name: scenario-non-kd-scr-ner-half-mdeberta_data-univner_full44
|
| 14 |
results: []
|
|
@@ -21,11 +21,11 @@ should probably proofread and complete it, then remove this comment. -->
|
|
| 21 |
|
| 22 |
This model is a fine-tuned version of [microsoft/mdeberta-v3-base](https://huggingface.co/microsoft/mdeberta-v3-base) on the None dataset.
|
| 23 |
It achieves the following results on the evaluation set:
|
| 24 |
-
- Loss: 0.
|
| 25 |
-
- Precision: 0.
|
| 26 |
-
- Recall: 0.
|
| 27 |
-
- F1: 0.
|
| 28 |
-
- Accuracy: 0.
|
| 29 |
|
| 30 |
## Model description
|
| 31 |
|
|
@@ -56,85 +56,71 @@ The following hyperparameters were used during training:
|
|
| 56 |
|
| 57 |
| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
|
| 58 |
|:-------------:|:-------:|:-----:|:---------------:|:---------:|:------:|:------:|:--------:|
|
| 59 |
-
| 0.
|
| 60 |
-
| 0.
|
| 61 |
-
| 0.
|
| 62 |
-
| 0.
|
| 63 |
-
| 0.
|
| 64 |
-
| 0.
|
| 65 |
-
| 0.
|
| 66 |
-
| 0.
|
| 67 |
-
| 0.
|
| 68 |
-
| 0.
|
| 69 |
-
| 0.
|
| 70 |
-
| 0.
|
| 71 |
-
| 0.
|
| 72 |
-
| 0.
|
| 73 |
-
| 0.
|
| 74 |
-
| 0.
|
| 75 |
-
| 0.
|
| 76 |
-
| 0.
|
| 77 |
-
| 0.0212 | 5.5297 | 9500 | 0.
|
| 78 |
-
| 0.
|
| 79 |
-
| 0.
|
| 80 |
-
| 0.
|
| 81 |
-
| 0.
|
| 82 |
-
| 0.0166 | 6.9849 | 12000 | 0.
|
| 83 |
-
| 0.
|
| 84 |
-
| 0.
|
| 85 |
-
| 0.
|
| 86 |
-
| 0.
|
| 87 |
-
| 0.
|
| 88 |
-
| 0.
|
| 89 |
-
| 0.
|
| 90 |
-
| 0.
|
| 91 |
-
| 0.
|
| 92 |
-
| 0.
|
| 93 |
-
| 0.
|
| 94 |
-
| 0.
|
| 95 |
-
| 0.
|
| 96 |
-
| 0.
|
| 97 |
-
| 0.
|
| 98 |
-
| 0.0048 | 11.6414 | 20000 | 0.
|
| 99 |
-
| 0.
|
| 100 |
-
| 0.
|
| 101 |
-
| 0.0029 | 12.5146 | 21500 | 0.
|
| 102 |
-
| 0.0037 | 12.8056 | 22000 | 0.
|
| 103 |
-
| 0.
|
| 104 |
-
| 0.
|
| 105 |
-
| 0.
|
| 106 |
-
| 0.
|
| 107 |
-
| 0.
|
| 108 |
-
| 0.
|
| 109 |
-
| 0.
|
| 110 |
-
| 0.
|
| 111 |
-
| 0.
|
| 112 |
-
| 0.
|
| 113 |
-
| 0.
|
| 114 |
-
| 0.
|
| 115 |
-
| 0.
|
| 116 |
-
| 0.
|
| 117 |
-
| 0.
|
| 118 |
-
| 0.
|
| 119 |
-
| 0.
|
| 120 |
-
| 0.
|
| 121 |
-
| 0.0009 | 18.3353 | 31500 | 0.
|
| 122 |
-
| 0.
|
| 123 |
-
| 0.0014 | 18.9173 | 32500 | 0.
|
| 124 |
-
| 0.0013 | 19.2084 | 33000 | 0.3241 | 0.6114 | 0.5892 | 0.6001 | 0.9614 |
|
| 125 |
-
| 0.0011 | 19.4994 | 33500 | 0.3270 | 0.6190 | 0.5858 | 0.6019 | 0.9614 |
|
| 126 |
-
| 0.0011 | 19.7905 | 34000 | 0.3284 | 0.6254 | 0.5722 | 0.5976 | 0.9611 |
|
| 127 |
-
| 0.0009 | 20.0815 | 34500 | 0.3245 | 0.6250 | 0.5884 | 0.6061 | 0.9618 |
|
| 128 |
-
| 0.0012 | 20.3725 | 35000 | 0.3238 | 0.6221 | 0.5833 | 0.6021 | 0.9616 |
|
| 129 |
-
| 0.0009 | 20.6636 | 35500 | 0.3231 | 0.6015 | 0.6029 | 0.6022 | 0.9612 |
|
| 130 |
-
| 0.0009 | 20.9546 | 36000 | 0.3270 | 0.6204 | 0.5914 | 0.6056 | 0.9617 |
|
| 131 |
-
| 0.0008 | 21.2456 | 36500 | 0.3288 | 0.6288 | 0.5807 | 0.6038 | 0.9615 |
|
| 132 |
-
| 0.0006 | 21.5367 | 37000 | 0.3358 | 0.6196 | 0.5829 | 0.6007 | 0.9614 |
|
| 133 |
-
| 0.0009 | 21.8277 | 37500 | 0.3353 | 0.6323 | 0.5784 | 0.6042 | 0.9618 |
|
| 134 |
-
| 0.0008 | 22.1187 | 38000 | 0.3339 | 0.6295 | 0.5891 | 0.6086 | 0.9620 |
|
| 135 |
-
| 0.0005 | 22.4098 | 38500 | 0.3380 | 0.6170 | 0.5923 | 0.6044 | 0.9617 |
|
| 136 |
-
| 0.0007 | 22.7008 | 39000 | 0.3382 | 0.6183 | 0.5866 | 0.6021 | 0.9619 |
|
| 137 |
-
| 0.0008 | 22.9919 | 39500 | 0.3378 | 0.6195 | 0.5879 | 0.6033 | 0.9616 |
|
| 138 |
|
| 139 |
|
| 140 |
### Framework versions
|
|
|
|
| 1 |
---
|
|
|
|
| 2 |
library_name: transformers
|
| 3 |
license: mit
|
| 4 |
+
base_model: microsoft/mdeberta-v3-base
|
| 5 |
+
tags:
|
| 6 |
+
- generated_from_trainer
|
| 7 |
metrics:
|
| 8 |
- precision
|
| 9 |
- recall
|
| 10 |
- f1
|
| 11 |
- accuracy
|
|
|
|
|
|
|
| 12 |
model-index:
|
| 13 |
- name: scenario-non-kd-scr-ner-half-mdeberta_data-univner_full44
|
| 14 |
results: []
|
|
|
|
| 21 |
|
| 22 |
This model is a fine-tuned version of [microsoft/mdeberta-v3-base](https://huggingface.co/microsoft/mdeberta-v3-base) on the None dataset.
|
| 23 |
It achieves the following results on the evaluation set:
|
| 24 |
+
- Loss: 0.3227
|
| 25 |
+
- Precision: 0.6152
|
| 26 |
+
- Recall: 0.5804
|
| 27 |
+
- F1: 0.5973
|
| 28 |
+
- Accuracy: 0.9617
|
| 29 |
|
| 30 |
## Model description
|
| 31 |
|
|
|
|
| 56 |
|
| 57 |
| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
|
| 58 |
|:-------------:|:-------:|:-----:|:---------------:|:---------:|:------:|:------:|:--------:|
|
| 59 |
+
| 0.357 | 0.2910 | 500 | 0.2880 | 0.3006 | 0.1147 | 0.1660 | 0.9285 |
|
| 60 |
+
| 0.2425 | 0.5821 | 1000 | 0.2106 | 0.3468 | 0.2782 | 0.3087 | 0.9383 |
|
| 61 |
+
| 0.1767 | 0.8731 | 1500 | 0.1785 | 0.4322 | 0.3857 | 0.4076 | 0.9469 |
|
| 62 |
+
| 0.1352 | 1.1641 | 2000 | 0.1621 | 0.4749 | 0.4745 | 0.4747 | 0.9520 |
|
| 63 |
+
| 0.1107 | 1.4552 | 2500 | 0.1556 | 0.5238 | 0.4991 | 0.5111 | 0.9553 |
|
| 64 |
+
| 0.1031 | 1.7462 | 3000 | 0.1480 | 0.5536 | 0.5207 | 0.5367 | 0.9576 |
|
| 65 |
+
| 0.0912 | 2.0373 | 3500 | 0.1435 | 0.5286 | 0.5578 | 0.5428 | 0.9579 |
|
| 66 |
+
| 0.0661 | 2.3283 | 4000 | 0.1496 | 0.5510 | 0.5698 | 0.5602 | 0.9589 |
|
| 67 |
+
| 0.066 | 2.6193 | 4500 | 0.1502 | 0.5587 | 0.5742 | 0.5663 | 0.9594 |
|
| 68 |
+
| 0.0646 | 2.9104 | 5000 | 0.1440 | 0.5779 | 0.5803 | 0.5791 | 0.9609 |
|
| 69 |
+
| 0.0492 | 3.2014 | 5500 | 0.1590 | 0.5898 | 0.5656 | 0.5774 | 0.9608 |
|
| 70 |
+
| 0.0428 | 3.4924 | 6000 | 0.1613 | 0.5819 | 0.5634 | 0.5725 | 0.9603 |
|
| 71 |
+
| 0.0447 | 3.7835 | 6500 | 0.1602 | 0.5970 | 0.5742 | 0.5854 | 0.9615 |
|
| 72 |
+
| 0.0407 | 4.0745 | 7000 | 0.1667 | 0.5744 | 0.5995 | 0.5867 | 0.9611 |
|
| 73 |
+
| 0.0311 | 4.3655 | 7500 | 0.1762 | 0.5897 | 0.5754 | 0.5824 | 0.9610 |
|
| 74 |
+
| 0.0308 | 4.6566 | 8000 | 0.1707 | 0.5928 | 0.5862 | 0.5895 | 0.9609 |
|
| 75 |
+
| 0.0303 | 4.9476 | 8500 | 0.1717 | 0.5882 | 0.5915 | 0.5899 | 0.9610 |
|
| 76 |
+
| 0.0217 | 5.2386 | 9000 | 0.1826 | 0.5808 | 0.6025 | 0.5915 | 0.9611 |
|
| 77 |
+
| 0.0212 | 5.5297 | 9500 | 0.1827 | 0.5949 | 0.6006 | 0.5977 | 0.9613 |
|
| 78 |
+
| 0.0228 | 5.8207 | 10000 | 0.1942 | 0.5760 | 0.5809 | 0.5784 | 0.9601 |
|
| 79 |
+
| 0.02 | 6.1118 | 10500 | 0.1973 | 0.5982 | 0.5913 | 0.5947 | 0.9611 |
|
| 80 |
+
| 0.0146 | 6.4028 | 11000 | 0.2058 | 0.5938 | 0.5871 | 0.5904 | 0.9608 |
|
| 81 |
+
| 0.0161 | 6.6938 | 11500 | 0.2025 | 0.5973 | 0.5878 | 0.5925 | 0.9612 |
|
| 82 |
+
| 0.0166 | 6.9849 | 12000 | 0.2053 | 0.5972 | 0.5921 | 0.5947 | 0.9613 |
|
| 83 |
+
| 0.0115 | 7.2759 | 12500 | 0.2259 | 0.6083 | 0.5601 | 0.5832 | 0.9609 |
|
| 84 |
+
| 0.0116 | 7.5669 | 13000 | 0.2133 | 0.5944 | 0.6029 | 0.5986 | 0.9608 |
|
| 85 |
+
| 0.0114 | 7.8580 | 13500 | 0.2208 | 0.5883 | 0.5973 | 0.5928 | 0.9608 |
|
| 86 |
+
| 0.0098 | 8.1490 | 14000 | 0.2363 | 0.6118 | 0.5745 | 0.5926 | 0.9611 |
|
| 87 |
+
| 0.0084 | 8.4400 | 14500 | 0.2387 | 0.6094 | 0.5748 | 0.5916 | 0.9611 |
|
| 88 |
+
| 0.0097 | 8.7311 | 15000 | 0.2285 | 0.5819 | 0.5998 | 0.5907 | 0.9602 |
|
| 89 |
+
| 0.0083 | 9.0221 | 15500 | 0.2402 | 0.5992 | 0.5806 | 0.5897 | 0.9610 |
|
| 90 |
+
| 0.0064 | 9.3132 | 16000 | 0.2456 | 0.6297 | 0.5679 | 0.5972 | 0.9617 |
|
| 91 |
+
| 0.0068 | 9.6042 | 16500 | 0.2487 | 0.6035 | 0.5752 | 0.5890 | 0.9607 |
|
| 92 |
+
| 0.0072 | 9.8952 | 17000 | 0.2403 | 0.5910 | 0.6009 | 0.5959 | 0.9610 |
|
| 93 |
+
| 0.0062 | 10.1863 | 17500 | 0.2465 | 0.5981 | 0.5972 | 0.5976 | 0.9615 |
|
| 94 |
+
| 0.0045 | 10.4773 | 18000 | 0.2562 | 0.6062 | 0.5776 | 0.5915 | 0.9611 |
|
| 95 |
+
| 0.0055 | 10.7683 | 18500 | 0.2542 | 0.6139 | 0.5826 | 0.5978 | 0.9615 |
|
| 96 |
+
| 0.0054 | 11.0594 | 19000 | 0.2596 | 0.6128 | 0.5807 | 0.5963 | 0.9616 |
|
| 97 |
+
| 0.0037 | 11.3504 | 19500 | 0.2631 | 0.5872 | 0.6015 | 0.5943 | 0.9607 |
|
| 98 |
+
| 0.0048 | 11.6414 | 20000 | 0.2613 | 0.5998 | 0.6012 | 0.6005 | 0.9615 |
|
| 99 |
+
| 0.004 | 11.9325 | 20500 | 0.2576 | 0.6108 | 0.5892 | 0.5998 | 0.9616 |
|
| 100 |
+
| 0.0042 | 12.2235 | 21000 | 0.2647 | 0.5943 | 0.6027 | 0.5984 | 0.9611 |
|
| 101 |
+
| 0.0029 | 12.5146 | 21500 | 0.2773 | 0.6058 | 0.5819 | 0.5936 | 0.9613 |
|
| 102 |
+
| 0.0037 | 12.8056 | 22000 | 0.2785 | 0.6111 | 0.5874 | 0.5990 | 0.9612 |
|
| 103 |
+
| 0.0031 | 13.0966 | 22500 | 0.2819 | 0.6281 | 0.5790 | 0.6026 | 0.9618 |
|
| 104 |
+
| 0.0029 | 13.3877 | 23000 | 0.2794 | 0.6002 | 0.5915 | 0.5958 | 0.9609 |
|
| 105 |
+
| 0.0024 | 13.6787 | 23500 | 0.2842 | 0.6017 | 0.6019 | 0.6018 | 0.9615 |
|
| 106 |
+
| 0.0034 | 13.9697 | 24000 | 0.2889 | 0.6133 | 0.5806 | 0.5965 | 0.9616 |
|
| 107 |
+
| 0.0021 | 14.2608 | 24500 | 0.2876 | 0.6133 | 0.5803 | 0.5963 | 0.9616 |
|
| 108 |
+
| 0.0025 | 14.5518 | 25000 | 0.2871 | 0.6130 | 0.5845 | 0.5984 | 0.9614 |
|
| 109 |
+
| 0.0027 | 14.8428 | 25500 | 0.2921 | 0.6087 | 0.5835 | 0.5958 | 0.9613 |
|
| 110 |
+
| 0.0021 | 15.1339 | 26000 | 0.2888 | 0.5822 | 0.5998 | 0.5909 | 0.9607 |
|
| 111 |
+
| 0.0017 | 15.4249 | 26500 | 0.2899 | 0.6095 | 0.5911 | 0.6002 | 0.9613 |
|
| 112 |
+
| 0.0026 | 15.7159 | 27000 | 0.2968 | 0.6065 | 0.5839 | 0.5950 | 0.9613 |
|
| 113 |
+
| 0.002 | 16.0070 | 27500 | 0.3023 | 0.6158 | 0.5752 | 0.5949 | 0.9614 |
|
| 114 |
+
| 0.0015 | 16.2980 | 28000 | 0.2988 | 0.6006 | 0.5954 | 0.5980 | 0.9614 |
|
| 115 |
+
| 0.002 | 16.5891 | 28500 | 0.2983 | 0.5905 | 0.6045 | 0.5974 | 0.9611 |
|
| 116 |
+
| 0.0017 | 16.8801 | 29000 | 0.3006 | 0.6080 | 0.5838 | 0.5956 | 0.9614 |
|
| 117 |
+
| 0.0016 | 17.1711 | 29500 | 0.3078 | 0.5986 | 0.5921 | 0.5953 | 0.9612 |
|
| 118 |
+
| 0.0016 | 17.4622 | 30000 | 0.3066 | 0.6084 | 0.5892 | 0.5987 | 0.9617 |
|
| 119 |
+
| 0.0015 | 17.7532 | 30500 | 0.3153 | 0.6110 | 0.5786 | 0.5943 | 0.9617 |
|
| 120 |
+
| 0.0015 | 18.0442 | 31000 | 0.3134 | 0.5952 | 0.5954 | 0.5953 | 0.9611 |
|
| 121 |
+
| 0.0009 | 18.3353 | 31500 | 0.3201 | 0.6045 | 0.5904 | 0.5974 | 0.9615 |
|
| 122 |
+
| 0.0017 | 18.6263 | 32000 | 0.3149 | 0.6095 | 0.5875 | 0.5983 | 0.9614 |
|
| 123 |
+
| 0.0014 | 18.9173 | 32500 | 0.3227 | 0.6152 | 0.5804 | 0.5973 | 0.9617 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 124 |
|
| 125 |
|
| 126 |
### Framework versions
|
eval_result_ner.json
CHANGED
|
@@ -1 +1 @@
|
|
| 1 |
-
{"ceb_gja": {"precision": 0.
|
|
|
|
| 1 |
+
{"ceb_gja": {"precision": 0.26, "recall": 0.5306122448979592, "f1": 0.348993288590604, "accuracy": 0.9196911196911197}, "en_pud": {"precision": 0.493491124260355, "recall": 0.38790697674418606, "f1": 0.434375, "accuracy": 0.9478655081224027}, "de_pud": {"precision": 0.128099173553719, "recall": 0.2685274302213667, "f1": 0.1734535281317998, "accuracy": 0.8564530495522947}, "pt_pud": {"precision": 0.554679802955665, "recall": 0.5122838944494995, "f1": 0.532639545884579, "accuracy": 0.9577904045798266}, "ru_pud": {"precision": 0.01598173515981735, "recall": 0.04054054054054054, "f1": 0.02292576419213974, "accuracy": 0.7532937225523121}, "sv_pud": {"precision": 0.5259938837920489, "recall": 0.33430515063168126, "f1": 0.4087938205585264, "accuracy": 0.9465296707905221}, "tl_trg": {"precision": 0.24193548387096775, "recall": 0.6521739130434783, "f1": 0.35294117647058826, "accuracy": 0.9277929155313351}, "tl_ugnayan": {"precision": 0.06666666666666667, "recall": 0.15151515151515152, "f1": 0.09259259259259259, "accuracy": 0.8997265268915223}, "zh_gsd": {"precision": 0.5648535564853556, "recall": 0.5280312907431551, "f1": 0.545822102425876, "accuracy": 0.9410589410589411}, "zh_gsdsimp": {"precision": 0.5839017735334243, "recall": 0.5609436435124509, "f1": 0.5721925133689839, "accuracy": 0.9446386946386947}, "hr_set": {"precision": 0.7600585223116313, "recall": 0.7405559515324305, "f1": 0.7501805054151623, "accuracy": 0.9703627370156637}, "da_ddt": {"precision": 0.6727748691099477, "recall": 0.5749440715883669, "f1": 0.6200241254523522, "accuracy": 0.9720642522198942}, "en_ewt": {"precision": 0.6070686070686071, "recall": 0.5367647058823529, "f1": 0.5697560975609756, "accuracy": 0.9593576921544408}, "pt_bosque": {"precision": 0.6539130434782608, "recall": 0.6189300411522634, "f1": 0.6359408033826638, "accuracy": 0.9660194174757282}, "sr_set": {"precision": 0.7801672640382318, "recall": 0.7709563164108618, "f1": 0.7755344418052256, "accuracy": 0.9667279572716925}, "sk_snk": {"precision": 0.39080459770114945, "recall": 0.26010928961748636, "f1": 0.3123359580052494, "accuracy": 0.914572864321608}, "sv_talbanken": {"precision": 0.7088607594936709, "recall": 0.5714285714285714, "f1": 0.632768361581921, "accuracy": 0.993963782696177}}
|
model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 428939068
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:44344290029bdd862c294ff09e558ab6f3207276283256111bd7e74ab26bfbb9
|
| 3 |
size 428939068
|
training_args.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 5304
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:3e8bd72e6d5081aa3461c60ff89546899aaf2ea31dee6c5683937c951e13801b
|
| 3 |
size 5304
|