Initial Commit
Browse files- README.md +49 -65
- 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_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 |
|
|
@@ -56,63 +56,47 @@ 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.
|
| 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.
|
| 91 |
-
| 0.
|
| 92 |
-
| 0.
|
| 93 |
-
| 0.
|
| 94 |
-
| 0.
|
| 95 |
-
| 0.
|
| 96 |
-
| 0.
|
| 97 |
-
| 0.
|
| 98 |
-
| 0.
|
| 99 |
-
| 0.0021 | 11.9325 | 20500 | 0.
|
| 100 |
-
| 0.0017 | 12.2235 | 21000 | 0.3067 | 0.6186 | 0.6045 | 0.6115 | 0.9632 |
|
| 101 |
-
| 0.0015 | 12.5146 | 21500 | 0.3029 | 0.6147 | 0.6104 | 0.6126 | 0.9625 |
|
| 102 |
-
| 0.0022 | 12.8056 | 22000 | 0.3038 | 0.6093 | 0.6230 | 0.6161 | 0.9630 |
|
| 103 |
-
| 0.0017 | 13.0966 | 22500 | 0.3025 | 0.6118 | 0.6119 | 0.6118 | 0.9625 |
|
| 104 |
-
| 0.0014 | 13.3877 | 23000 | 0.3071 | 0.6407 | 0.5970 | 0.6181 | 0.9636 |
|
| 105 |
-
| 0.0013 | 13.6787 | 23500 | 0.3082 | 0.6325 | 0.6032 | 0.6175 | 0.9632 |
|
| 106 |
-
| 0.0015 | 13.9697 | 24000 | 0.3119 | 0.6248 | 0.5952 | 0.6096 | 0.9627 |
|
| 107 |
-
| 0.0013 | 14.2608 | 24500 | 0.3149 | 0.6358 | 0.6040 | 0.6195 | 0.9636 |
|
| 108 |
-
| 0.0011 | 14.5518 | 25000 | 0.3147 | 0.6165 | 0.6058 | 0.6111 | 0.9631 |
|
| 109 |
-
| 0.0014 | 14.8428 | 25500 | 0.3088 | 0.6074 | 0.6128 | 0.6101 | 0.9630 |
|
| 110 |
-
| 0.0011 | 15.1339 | 26000 | 0.3060 | 0.6150 | 0.6229 | 0.6189 | 0.9634 |
|
| 111 |
-
| 0.0008 | 15.4249 | 26500 | 0.3148 | 0.6219 | 0.6089 | 0.6153 | 0.9633 |
|
| 112 |
-
| 0.0008 | 15.7159 | 27000 | 0.3311 | 0.6357 | 0.5765 | 0.6047 | 0.9627 |
|
| 113 |
-
| 0.0012 | 16.0070 | 27500 | 0.3238 | 0.6355 | 0.5924 | 0.6132 | 0.9631 |
|
| 114 |
-
| 0.0009 | 16.2980 | 28000 | 0.3187 | 0.6016 | 0.6247 | 0.6130 | 0.9631 |
|
| 115 |
-
| 0.0011 | 16.5891 | 28500 | 0.3192 | 0.6332 | 0.5988 | 0.6155 | 0.9635 |
|
| 116 |
|
| 117 |
|
| 118 |
### 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_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: 0.3003
|
| 25 |
+
- Precision: 0.6230
|
| 26 |
+
- Recall: 0.5993
|
| 27 |
+
- F1: 0.6109
|
| 28 |
+
- Accuracy: 0.9631
|
| 29 |
|
| 30 |
## Model description
|
| 31 |
|
|
|
|
| 56 |
|
| 57 |
| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
|
| 58 |
|:-------------:|:-------:|:-----:|:---------------:|:---------:|:------:|:------:|:--------:|
|
| 59 |
+
| 0.3129 | 0.2910 | 500 | 0.2430 | 0.3687 | 0.2001 | 0.2594 | 0.9351 |
|
| 60 |
+
| 0.201 | 0.5821 | 1000 | 0.1893 | 0.3603 | 0.3711 | 0.3656 | 0.9430 |
|
| 61 |
+
| 0.1493 | 0.8731 | 1500 | 0.1664 | 0.4946 | 0.4279 | 0.4588 | 0.9519 |
|
| 62 |
+
| 0.1081 | 1.1641 | 2000 | 0.1566 | 0.5297 | 0.5299 | 0.5298 | 0.9563 |
|
| 63 |
+
| 0.0881 | 1.4552 | 2500 | 0.1487 | 0.5472 | 0.5748 | 0.5607 | 0.9581 |
|
| 64 |
+
| 0.0825 | 1.7462 | 3000 | 0.1487 | 0.5918 | 0.5183 | 0.5526 | 0.9594 |
|
| 65 |
+
| 0.0721 | 2.0373 | 3500 | 0.1490 | 0.5893 | 0.5660 | 0.5774 | 0.9613 |
|
| 66 |
+
| 0.0454 | 2.3283 | 4000 | 0.1648 | 0.5981 | 0.5498 | 0.5730 | 0.9609 |
|
| 67 |
+
| 0.0457 | 2.6193 | 4500 | 0.1633 | 0.5882 | 0.5934 | 0.5908 | 0.9617 |
|
| 68 |
+
| 0.046 | 2.9104 | 5000 | 0.1505 | 0.6074 | 0.5959 | 0.6016 | 0.9627 |
|
| 69 |
+
| 0.0302 | 3.2014 | 5500 | 0.1771 | 0.6159 | 0.5788 | 0.5968 | 0.9620 |
|
| 70 |
+
| 0.0249 | 3.4924 | 6000 | 0.1871 | 0.6064 | 0.5751 | 0.5903 | 0.9615 |
|
| 71 |
+
| 0.0271 | 3.7835 | 6500 | 0.1806 | 0.6146 | 0.5882 | 0.6011 | 0.9628 |
|
| 72 |
+
| 0.0235 | 4.0745 | 7000 | 0.1966 | 0.6161 | 0.5804 | 0.5977 | 0.9626 |
|
| 73 |
+
| 0.0152 | 4.3655 | 7500 | 0.2110 | 0.6071 | 0.5887 | 0.5978 | 0.9621 |
|
| 74 |
+
| 0.0165 | 4.6566 | 8000 | 0.1978 | 0.6008 | 0.6174 | 0.6090 | 0.9620 |
|
| 75 |
+
| 0.0164 | 4.9476 | 8500 | 0.2096 | 0.6029 | 0.5750 | 0.5886 | 0.9611 |
|
| 76 |
+
| 0.011 | 5.2386 | 9000 | 0.2174 | 0.6055 | 0.6027 | 0.6041 | 0.9626 |
|
| 77 |
+
| 0.0101 | 5.5297 | 9500 | 0.2234 | 0.5919 | 0.6080 | 0.5999 | 0.9615 |
|
| 78 |
+
| 0.0109 | 5.8207 | 10000 | 0.2246 | 0.6148 | 0.5975 | 0.6060 | 0.9623 |
|
| 79 |
+
| 0.0099 | 6.1118 | 10500 | 0.2228 | 0.6115 | 0.6164 | 0.6139 | 0.9626 |
|
| 80 |
+
| 0.0062 | 6.4028 | 11000 | 0.2401 | 0.6099 | 0.6060 | 0.6079 | 0.9623 |
|
| 81 |
+
| 0.0073 | 6.6938 | 11500 | 0.2560 | 0.6161 | 0.5897 | 0.6026 | 0.9621 |
|
| 82 |
+
| 0.0082 | 6.9849 | 12000 | 0.2488 | 0.6008 | 0.5914 | 0.5960 | 0.9614 |
|
| 83 |
+
| 0.0049 | 7.2759 | 12500 | 0.2573 | 0.6155 | 0.5832 | 0.5989 | 0.9620 |
|
| 84 |
+
| 0.0057 | 7.5669 | 13000 | 0.2583 | 0.6320 | 0.5882 | 0.6093 | 0.9628 |
|
| 85 |
+
| 0.0058 | 7.8580 | 13500 | 0.2601 | 0.6040 | 0.6188 | 0.6113 | 0.9623 |
|
| 86 |
+
| 0.0044 | 8.1490 | 14000 | 0.2676 | 0.5962 | 0.6006 | 0.5984 | 0.9616 |
|
| 87 |
+
| 0.0039 | 8.4400 | 14500 | 0.2747 | 0.6194 | 0.5930 | 0.6059 | 0.9624 |
|
| 88 |
+
| 0.004 | 8.7311 | 15000 | 0.2796 | 0.6080 | 0.5776 | 0.5924 | 0.9614 |
|
| 89 |
+
| 0.0044 | 9.0221 | 15500 | 0.2836 | 0.6095 | 0.5875 | 0.5983 | 0.9623 |
|
| 90 |
+
| 0.0028 | 9.3132 | 16000 | 0.2907 | 0.6315 | 0.5891 | 0.6095 | 0.9631 |
|
| 91 |
+
| 0.003 | 9.6042 | 16500 | 0.2962 | 0.6212 | 0.5787 | 0.5992 | 0.9626 |
|
| 92 |
+
| 0.0038 | 9.8952 | 17000 | 0.2864 | 0.6232 | 0.5823 | 0.6021 | 0.9625 |
|
| 93 |
+
| 0.0029 | 10.1863 | 17500 | 0.2912 | 0.6240 | 0.5892 | 0.6061 | 0.9623 |
|
| 94 |
+
| 0.0023 | 10.4773 | 18000 | 0.2990 | 0.6344 | 0.5728 | 0.6020 | 0.9625 |
|
| 95 |
+
| 0.0028 | 10.7683 | 18500 | 0.2953 | 0.6186 | 0.5965 | 0.6073 | 0.9628 |
|
| 96 |
+
| 0.0021 | 11.0594 | 19000 | 0.2989 | 0.6216 | 0.5988 | 0.6100 | 0.9630 |
|
| 97 |
+
| 0.0017 | 11.3504 | 19500 | 0.3025 | 0.6161 | 0.6057 | 0.6108 | 0.9631 |
|
| 98 |
+
| 0.0023 | 11.6414 | 20000 | 0.2973 | 0.6148 | 0.6057 | 0.6102 | 0.9629 |
|
| 99 |
+
| 0.0021 | 11.9325 | 20500 | 0.3003 | 0.6230 | 0.5993 | 0.6109 | 0.9631 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 100 |
|
| 101 |
|
| 102 |
### Framework versions
|
eval_result_ner.json
CHANGED
|
@@ -1 +1 @@
|
|
| 1 |
-
{"ceb_gja": {"precision": 0.
|
|
|
|
| 1 |
+
{"ceb_gja": {"precision": 0.2711864406779661, "recall": 0.6530612244897959, "f1": 0.3832335329341317, "accuracy": 0.9173745173745174}, "en_pud": {"precision": 0.4605647517039922, "recall": 0.44, "f1": 0.45004757373929594, "accuracy": 0.9471571590479788}, "de_pud": {"precision": 0.11804258498319013, "recall": 0.3041385948026949, "f1": 0.17007534983853603, "accuracy": 0.8365758754863813}, "pt_pud": {"precision": 0.5774774774774775, "recall": 0.5832575068243858, "f1": 0.5803531009506564, "accuracy": 0.9628743538257786}, "ru_pud": {"precision": 0.017737399956738047, "recall": 0.07915057915057915, "f1": 0.02898038522707192, "accuracy": 0.6227848101265823}, "sv_pud": {"precision": 0.5208053691275167, "recall": 0.3770651117589893, "f1": 0.43742953776775645, "accuracy": 0.9470538897043406}, "tl_trg": {"precision": 0.18292682926829268, "recall": 0.6521739130434783, "f1": 0.28571428571428575, "accuracy": 0.8896457765667575}, "tl_ugnayan": {"precision": 0.07317073170731707, "recall": 0.2727272727272727, "f1": 0.11538461538461536, "accuracy": 0.8632634457611669}, "zh_gsd": {"precision": 0.5587529976019184, "recall": 0.6075619295958279, "f1": 0.5821361648969393, "accuracy": 0.9434731934731935}, "zh_gsdsimp": {"precision": 0.5505882352941176, "recall": 0.6133682830930537, "f1": 0.5802851828890266, "accuracy": 0.943972693972694}, "hr_set": {"precision": 0.7477288609364081, "recall": 0.7626514611546685, "f1": 0.7551164431898376, "accuracy": 0.9718878812860676}, "da_ddt": {"precision": 0.6460396039603961, "recall": 0.5838926174496645, "f1": 0.6133960047003526, "accuracy": 0.9724633343310386}, "en_ewt": {"precision": 0.5944333996023857, "recall": 0.5496323529411765, "f1": 0.5711556829035339, "accuracy": 0.9605132087500498}, "pt_bosque": {"precision": 0.6528791565287916, "recall": 0.6625514403292181, "f1": 0.6576797385620915, "accuracy": 0.9688813215476018}, "sr_set": {"precision": 0.8002322880371661, "recall": 0.8134592680047226, "f1": 0.8067915690866511, "accuracy": 0.9715436476665791}, "sk_snk": {"precision": 0.4393305439330544, "recall": 0.3442622950819672, "f1": 0.3860294117647059, "accuracy": 0.922660175879397}, "sv_talbanken": {"precision": 0.5911330049261084, "recall": 0.6122448979591837, "f1": 0.6015037593984963, "accuracy": 0.993522108259312}}
|
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 sha256:4fa6630f7acba8d252787aea30f11a1b45eaad3a7f1a19ec6c1c7d98fcd0f137
|
| 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 sha256:39b210a6f128bfd66cc55a75fd32b53f82ad7735898bc6414cc432dee272cc1a
|
| 3 |
size 5304
|