Initial Commit
Browse files- README.md +41 -91
- 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-full-mdeberta_data-univner_full55
|
| 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 |
|
|
@@ -54,89 +54,39 @@ The following hyperparameters were used during training:
|
|
| 54 |
|
| 55 |
### Training results
|
| 56 |
|
| 57 |
-
| Training Loss | Epoch
|
| 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 |
-
| 0.0104 | 5.5297
|
| 78 |
-
| 0.
|
| 79 |
-
| 0.
|
| 80 |
-
| 0.
|
| 81 |
-
| 0.
|
| 82 |
-
| 0.
|
| 83 |
-
| 0.
|
| 84 |
-
| 0.
|
| 85 |
-
| 0.
|
| 86 |
-
| 0.
|
| 87 |
-
| 0.
|
| 88 |
-
| 0.
|
| 89 |
-
| 0.
|
| 90 |
-
| 0.0028 | 9.3132 | 16000 | 0.2813 | 0.6061 | 0.6099 | 0.6080 | 0.9627 |
|
| 91 |
-
| 0.0032 | 9.6042 | 16500 | 0.2962 | 0.6134 | 0.5999 | 0.6066 | 0.9627 |
|
| 92 |
-
| 0.0041 | 9.8952 | 17000 | 0.2819 | 0.6097 | 0.5980 | 0.6038 | 0.9625 |
|
| 93 |
-
| 0.0025 | 10.1863 | 17500 | 0.2859 | 0.6138 | 0.6037 | 0.6087 | 0.9627 |
|
| 94 |
-
| 0.0022 | 10.4773 | 18000 | 0.2976 | 0.6018 | 0.6122 | 0.6069 | 0.9624 |
|
| 95 |
-
| 0.0027 | 10.7683 | 18500 | 0.3066 | 0.6387 | 0.5819 | 0.6090 | 0.9626 |
|
| 96 |
-
| 0.003 | 11.0594 | 19000 | 0.2925 | 0.6402 | 0.5921 | 0.6152 | 0.9632 |
|
| 97 |
-
| 0.002 | 11.3504 | 19500 | 0.3069 | 0.5776 | 0.6094 | 0.5931 | 0.9613 |
|
| 98 |
-
| 0.0023 | 11.6414 | 20000 | 0.2979 | 0.6201 | 0.6063 | 0.6131 | 0.9628 |
|
| 99 |
-
| 0.0023 | 11.9325 | 20500 | 0.3015 | 0.5935 | 0.6181 | 0.6056 | 0.9621 |
|
| 100 |
-
| 0.0015 | 12.2235 | 21000 | 0.3179 | 0.6137 | 0.6070 | 0.6103 | 0.9629 |
|
| 101 |
-
| 0.0016 | 12.5146 | 21500 | 0.3073 | 0.6145 | 0.6211 | 0.6178 | 0.9631 |
|
| 102 |
-
| 0.0017 | 12.8056 | 22000 | 0.3159 | 0.6267 | 0.5914 | 0.6085 | 0.9628 |
|
| 103 |
-
| 0.0016 | 13.0966 | 22500 | 0.3224 | 0.6003 | 0.6154 | 0.6077 | 0.9623 |
|
| 104 |
-
| 0.0015 | 13.3877 | 23000 | 0.3160 | 0.6111 | 0.5884 | 0.5995 | 0.9624 |
|
| 105 |
-
| 0.0016 | 13.6787 | 23500 | 0.3201 | 0.6208 | 0.6057 | 0.6132 | 0.9630 |
|
| 106 |
-
| 0.0016 | 13.9697 | 24000 | 0.3187 | 0.6251 | 0.5954 | 0.6099 | 0.9626 |
|
| 107 |
-
| 0.0011 | 14.2608 | 24500 | 0.3188 | 0.6253 | 0.6094 | 0.6173 | 0.9630 |
|
| 108 |
-
| 0.0013 | 14.5518 | 25000 | 0.3178 | 0.6170 | 0.6165 | 0.6168 | 0.9629 |
|
| 109 |
-
| 0.0011 | 14.8428 | 25500 | 0.3311 | 0.6304 | 0.5830 | 0.6058 | 0.9626 |
|
| 110 |
-
| 0.0011 | 15.1339 | 26000 | 0.3345 | 0.6200 | 0.6077 | 0.6138 | 0.9631 |
|
| 111 |
-
| 0.0009 | 15.4249 | 26500 | 0.3385 | 0.6107 | 0.5970 | 0.6038 | 0.9623 |
|
| 112 |
-
| 0.0011 | 15.7159 | 27000 | 0.3289 | 0.6219 | 0.6192 | 0.6206 | 0.9632 |
|
| 113 |
-
| 0.001 | 16.0070 | 27500 | 0.3345 | 0.6101 | 0.5986 | 0.6043 | 0.9627 |
|
| 114 |
-
| 0.0005 | 16.2980 | 28000 | 0.3388 | 0.6202 | 0.6053 | 0.6126 | 0.9627 |
|
| 115 |
-
| 0.0007 | 16.5891 | 28500 | 0.3375 | 0.6204 | 0.6152 | 0.6178 | 0.9630 |
|
| 116 |
-
| 0.0009 | 16.8801 | 29000 | 0.3439 | 0.6103 | 0.6175 | 0.6139 | 0.9627 |
|
| 117 |
-
| 0.0008 | 17.1711 | 29500 | 0.3406 | 0.6238 | 0.6149 | 0.6193 | 0.9630 |
|
| 118 |
-
| 0.0006 | 17.4622 | 30000 | 0.3436 | 0.6147 | 0.6086 | 0.6116 | 0.9631 |
|
| 119 |
-
| 0.0007 | 17.7532 | 30500 | 0.3336 | 0.6366 | 0.6080 | 0.6219 | 0.9633 |
|
| 120 |
-
| 0.0005 | 18.0442 | 31000 | 0.3510 | 0.6210 | 0.6038 | 0.6123 | 0.9630 |
|
| 121 |
-
| 0.0005 | 18.3353 | 31500 | 0.3560 | 0.6148 | 0.6038 | 0.6093 | 0.9626 |
|
| 122 |
-
| 0.0008 | 18.6263 | 32000 | 0.3578 | 0.6195 | 0.6097 | 0.6146 | 0.9627 |
|
| 123 |
-
| 0.0004 | 18.9173 | 32500 | 0.3573 | 0.6300 | 0.6035 | 0.6165 | 0.9631 |
|
| 124 |
-
| 0.0005 | 19.2084 | 33000 | 0.3565 | 0.6336 | 0.6041 | 0.6185 | 0.9630 |
|
| 125 |
-
| 0.0004 | 19.4994 | 33500 | 0.3627 | 0.6317 | 0.6047 | 0.6179 | 0.9633 |
|
| 126 |
-
| 0.0005 | 19.7905 | 34000 | 0.3632 | 0.6161 | 0.6216 | 0.6188 | 0.9631 |
|
| 127 |
-
| 0.0004 | 20.0815 | 34500 | 0.3581 | 0.6086 | 0.6115 | 0.6100 | 0.9629 |
|
| 128 |
-
| 0.0004 | 20.3725 | 35000 | 0.3638 | 0.6148 | 0.6029 | 0.6088 | 0.9628 |
|
| 129 |
-
| 0.0005 | 20.6636 | 35500 | 0.3579 | 0.6216 | 0.6022 | 0.6118 | 0.9627 |
|
| 130 |
-
| 0.0003 | 20.9546 | 36000 | 0.3601 | 0.6014 | 0.6214 | 0.6112 | 0.9627 |
|
| 131 |
-
| 0.0002 | 21.2456 | 36500 | 0.3671 | 0.6361 | 0.5934 | 0.6140 | 0.9631 |
|
| 132 |
-
| 0.0003 | 21.5367 | 37000 | 0.3706 | 0.6269 | 0.6029 | 0.6147 | 0.9632 |
|
| 133 |
-
| 0.0003 | 21.8277 | 37500 | 0.3645 | 0.6128 | 0.6080 | 0.6104 | 0.9628 |
|
| 134 |
-
| 0.0004 | 22.1187 | 38000 | 0.3660 | 0.6157 | 0.6099 | 0.6128 | 0.9628 |
|
| 135 |
-
| 0.0003 | 22.4098 | 38500 | 0.3625 | 0.6214 | 0.6054 | 0.6133 | 0.9633 |
|
| 136 |
-
| 0.0003 | 22.7008 | 39000 | 0.3602 | 0.6125 | 0.6109 | 0.6117 | 0.9631 |
|
| 137 |
-
| 0.0003 | 22.9919 | 39500 | 0.3692 | 0.6196 | 0.5931 | 0.6061 | 0.9630 |
|
| 138 |
-
| 0.0001 | 23.2829 | 40000 | 0.3713 | 0.6226 | 0.6035 | 0.6129 | 0.9631 |
|
| 139 |
-
| 0.0002 | 23.5739 | 40500 | 0.3730 | 0.6215 | 0.6022 | 0.6117 | 0.9630 |
|
| 140 |
|
| 141 |
|
| 142 |
### 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-full-mdeberta_data-univner_full55
|
| 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: 0.2741
|
| 25 |
+
- Precision: 0.5988
|
| 26 |
+
- Recall: 0.6128
|
| 27 |
+
- F1: 0.6057
|
| 28 |
+
- Accuracy: 0.9621
|
| 29 |
|
| 30 |
## Model description
|
| 31 |
|
|
|
|
| 54 |
|
| 55 |
### Training results
|
| 56 |
|
| 57 |
+
| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
|
| 58 |
+
|:-------------:|:------:|:-----:|:---------------:|:---------:|:------:|:------:|:--------:|
|
| 59 |
+
| 0.3006 | 0.2910 | 500 | 0.2357 | 0.3668 | 0.2130 | 0.2695 | 0.9352 |
|
| 60 |
+
| 0.1928 | 0.5821 | 1000 | 0.1875 | 0.4361 | 0.3503 | 0.3885 | 0.9462 |
|
| 61 |
+
| 0.1489 | 0.8731 | 1500 | 0.1576 | 0.4740 | 0.4823 | 0.4782 | 0.9525 |
|
| 62 |
+
| 0.1075 | 1.1641 | 2000 | 0.1615 | 0.5266 | 0.4835 | 0.5041 | 0.9564 |
|
| 63 |
+
| 0.0865 | 1.4552 | 2500 | 0.1481 | 0.5230 | 0.5670 | 0.5441 | 0.9570 |
|
| 64 |
+
| 0.0797 | 1.7462 | 3000 | 0.1483 | 0.5544 | 0.5787 | 0.5663 | 0.9586 |
|
| 65 |
+
| 0.0709 | 2.0373 | 3500 | 0.1547 | 0.5766 | 0.5763 | 0.5764 | 0.9603 |
|
| 66 |
+
| 0.0471 | 2.3283 | 4000 | 0.1697 | 0.5880 | 0.5657 | 0.5767 | 0.9610 |
|
| 67 |
+
| 0.0456 | 2.6193 | 4500 | 0.1599 | 0.5935 | 0.6014 | 0.5974 | 0.9611 |
|
| 68 |
+
| 0.0453 | 2.9104 | 5000 | 0.1579 | 0.5927 | 0.6063 | 0.5994 | 0.9623 |
|
| 69 |
+
| 0.0312 | 3.2014 | 5500 | 0.1729 | 0.6139 | 0.6103 | 0.6121 | 0.9630 |
|
| 70 |
+
| 0.0269 | 3.4924 | 6000 | 0.1828 | 0.5998 | 0.6096 | 0.6047 | 0.9619 |
|
| 71 |
+
| 0.0274 | 3.7835 | 6500 | 0.1853 | 0.6104 | 0.5940 | 0.6021 | 0.9626 |
|
| 72 |
+
| 0.0245 | 4.0745 | 7000 | 0.1989 | 0.5772 | 0.5986 | 0.5877 | 0.9609 |
|
| 73 |
+
| 0.0153 | 4.3655 | 7500 | 0.2130 | 0.6058 | 0.6055 | 0.6057 | 0.9623 |
|
| 74 |
+
| 0.0174 | 4.6566 | 8000 | 0.1978 | 0.6002 | 0.6005 | 0.6004 | 0.9620 |
|
| 75 |
+
| 0.0179 | 4.9476 | 8500 | 0.2038 | 0.5669 | 0.6331 | 0.5982 | 0.9610 |
|
| 76 |
+
| 0.0113 | 5.2386 | 9000 | 0.2109 | 0.5876 | 0.6327 | 0.6093 | 0.9617 |
|
| 77 |
+
| 0.0104 | 5.5297 | 9500 | 0.2223 | 0.5911 | 0.6080 | 0.5994 | 0.9622 |
|
| 78 |
+
| 0.0115 | 5.8207 | 10000 | 0.2274 | 0.6097 | 0.6011 | 0.6053 | 0.9619 |
|
| 79 |
+
| 0.0098 | 6.1118 | 10500 | 0.2458 | 0.6230 | 0.5838 | 0.6028 | 0.9623 |
|
| 80 |
+
| 0.0067 | 6.4028 | 11000 | 0.2512 | 0.6039 | 0.6001 | 0.6020 | 0.9625 |
|
| 81 |
+
| 0.0077 | 6.6938 | 11500 | 0.2492 | 0.6103 | 0.5977 | 0.6039 | 0.9625 |
|
| 82 |
+
| 0.0079 | 6.9849 | 12000 | 0.2522 | 0.6054 | 0.6019 | 0.6037 | 0.9615 |
|
| 83 |
+
| 0.0054 | 7.2759 | 12500 | 0.2577 | 0.5999 | 0.6168 | 0.6082 | 0.9618 |
|
| 84 |
+
| 0.0056 | 7.5669 | 13000 | 0.2564 | 0.6114 | 0.6025 | 0.6069 | 0.9625 |
|
| 85 |
+
| 0.0058 | 7.8580 | 13500 | 0.2621 | 0.6105 | 0.5881 | 0.5991 | 0.9611 |
|
| 86 |
+
| 0.0051 | 8.1490 | 14000 | 0.2644 | 0.6069 | 0.6051 | 0.6060 | 0.9623 |
|
| 87 |
+
| 0.0041 | 8.4400 | 14500 | 0.2655 | 0.5858 | 0.6115 | 0.5983 | 0.9607 |
|
| 88 |
+
| 0.0045 | 8.7311 | 15000 | 0.2714 | 0.6130 | 0.6035 | 0.6082 | 0.9629 |
|
| 89 |
+
| 0.0041 | 9.0221 | 15500 | 0.2741 | 0.5988 | 0.6128 | 0.6057 | 0.9621 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 90 |
|
| 91 |
|
| 92 |
### Framework versions
|
eval_result_ner.json
CHANGED
|
@@ -1 +1 @@
|
|
| 1 |
-
{"ceb_gja": {"precision": 0.
|
|
|
|
| 1 |
+
{"ceb_gja": {"precision": 0.35802469135802467, "recall": 0.5918367346938775, "f1": 0.4461538461538461, "accuracy": 0.9420849420849421}, "en_pud": {"precision": 0.47845303867403316, "recall": 0.4027906976744186, "f1": 0.4373737373737374, "accuracy": 0.9488099735549679}, "de_pud": {"precision": 0.11877828054298642, "recall": 0.30317613089509143, "f1": 0.17068545109726357, "accuracy": 0.8338568280905724}, "pt_pud": {"precision": 0.584958217270195, "recall": 0.5732484076433121, "f1": 0.579044117647059, "accuracy": 0.9621480753620711}, "ru_pud": {"precision": 0.01828110161443495, "recall": 0.07432432432432433, "f1": 0.02934451219512195, "accuracy": 0.6327563936967192}, "sv_pud": {"precision": 0.5242566510172144, "recall": 0.32555879494655005, "f1": 0.40167865707434053, "accuracy": 0.9453239672887398}, "tl_trg": {"precision": 0.20967741935483872, "recall": 0.5652173913043478, "f1": 0.30588235294117644, "accuracy": 0.9237057220708447}, "tl_ugnayan": {"precision": 0.05263157894736842, "recall": 0.12121212121212122, "f1": 0.07339449541284404, "accuracy": 0.9051959890610757}, "zh_gsd": {"precision": 0.5702179176755447, "recall": 0.6140808344198174, "f1": 0.591337099811676, "accuracy": 0.9468864468864469}, "zh_gsdsimp": {"precision": 0.5624227441285538, "recall": 0.5963302752293578, "f1": 0.5788804071246818, "accuracy": 0.9459706959706959}, "hr_set": {"precision": 0.7391304347826086, "recall": 0.7633642195295794, "f1": 0.7510518934081346, "accuracy": 0.9725474031327288}, "da_ddt": {"precision": 0.6384615384615384, "recall": 0.5570469798657718, "f1": 0.5949820788530465, "accuracy": 0.9722637932754664}, "en_ewt": {"precision": 0.6191489361702127, "recall": 0.5349264705882353, "f1": 0.57396449704142, "accuracy": 0.9612304259473243}, "pt_bosque": {"precision": 0.6318367346938776, "recall": 0.6370370370370371, "f1": 0.6344262295081967, "accuracy": 0.9668164034197942}, "sr_set": {"precision": 0.7838452787258248, "recall": 0.8134592680047226, "f1": 0.7983777520278099, "accuracy": 0.9711058576306804}, "sk_snk": {"precision": 0.4550989345509893, "recall": 0.326775956284153, "f1": 0.38040712468193383, "accuracy": 0.9251727386934674}, "sv_talbanken": {"precision": 0.6685393258426966, "recall": 0.6071428571428571, "f1": 0.6363636363636364, "accuracy": 0.9935711831967414}}
|
model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 942800188
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:3ed1fa0e46fdb82c0c49bf7037b3a9b98bed6b1cc822ded7f0e5c6de5992571a
|
| 3 |
size 942800188
|
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 sha256:3e6d85b99c71e32ccec3552dc8e029f4fd58d303a617fd5a8702630e82a81fbe
|
| 3 |
size 5304
|