Hugging Face's logo

ABrinkmann
/
deberta-v3-large-finetuned-ner-10epochs-V2

Token Classification
Transformers
PyTorch
deberta-v2
Generated from Trainer
Inference Endpoints
Model card Files Community
ABrinkmann commited on
Commit
04ff29c
•
1 Parent(s): 198cccc

update model card README.md

Browse files
Files changed (1) hide show
  1. README.md +17 -17
README.md CHANGED
@@ -19,11 +19,11 @@ should probably proofread and complete it, then remove this comment. -->
19
 
20
  This model is a fine-tuned version of [microsoft/deberta-v3-large](https://huggingface.co/microsoft/deberta-v3-large) on the None dataset.
21
  It achieves the following results on the evaluation set:
22
- - Loss: 0.1180
23
- - Precision: 0.9033
24
- - Recall: 0.9347
25
- - F1: 0.9187
26
- - Accuracy: 0.9813
27
 
28
  ## Model description
29
 
@@ -54,21 +54,21 @@ The following hyperparameters were used during training:
54
 
55
  | Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
56
  |:-------------:|:-----:|:-----:|:---------------:|:---------:|:------:|:------:|:--------:|
57
- | 0.0663 | 1.0 | 2261 | 0.0715 | 0.8709 | 0.9194 | 0.8945 | 0.9787 |
58
- | 0.0583 | 2.0 | 4522 | 0.0629 | 0.8845 | 0.9267 | 0.9051 | 0.9800 |
59
- | 0.0442 | 3.0 | 6783 | 0.0635 | 0.8841 | 0.9404 | 0.9114 | 0.9802 |
60
- | 0.0402 | 4.0 | 9044 | 0.0588 | 0.9011 | 0.9283 | 0.9145 | 0.9821 |
61
- | 0.0327 | 5.0 | 11305 | 0.0676 | 0.8919 | 0.9385 | 0.9146 | 0.9818 |
62
- | 0.0245 | 6.0 | 13566 | 0.0713 | 0.9037 | 0.9331 | 0.9182 | 0.9821 |
63
- | 0.0183 | 7.0 | 15827 | 0.0848 | 0.9049 | 0.9181 | 0.9114 | 0.9812 |
64
- | 0.0157 | 8.0 | 18088 | 0.0898 | 0.8957 | 0.9411 | 0.9178 | 0.9818 |
65
- | 0.009 | 9.0 | 20349 | 0.1027 | 0.8965 | 0.9385 | 0.9170 | 0.9817 |
66
- | 0.0068 | 10.0 | 22610 | 0.1180 | 0.9033 | 0.9347 | 0.9187 | 0.9813 |
67
 
68
 
69
  ### Framework versions
70
 
71
- - Transformers 4.30.1
72
  - Pytorch 2.0.1+cu117
73
- - Datasets 2.12.0
74
  - Tokenizers 0.13.3
 
19
 
20
  This model is a fine-tuned version of [microsoft/deberta-v3-large](https://huggingface.co/microsoft/deberta-v3-large) on the None dataset.
21
  It achieves the following results on the evaluation set:
22
+ - Loss: 0.0941
23
+ - Precision: 0.9139
24
+ - Recall: 0.9358
25
+ - F1: 0.9248
26
+ - Accuracy: 0.9856
27
 
28
  ## Model description
29
 
 
54
 
55
  | Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
56
  |:-------------:|:-----:|:-----:|:---------------:|:---------:|:------:|:------:|:--------:|
57
+ | 0.0539 | 1.0 | 2261 | 0.0571 | 0.8751 | 0.9304 | 0.9019 | 0.9822 |
58
+ | 0.0481 | 2.0 | 4522 | 0.0515 | 0.8794 | 0.9387 | 0.9081 | 0.9833 |
59
+ | 0.0362 | 3.0 | 6783 | 0.0502 | 0.8956 | 0.9336 | 0.9142 | 0.9841 |
60
+ | 0.0341 | 4.0 | 9044 | 0.0456 | 0.9097 | 0.9301 | 0.9198 | 0.9856 |
61
+ | 0.0272 | 5.0 | 11305 | 0.0520 | 0.9005 | 0.9451 | 0.9223 | 0.9860 |
62
+ | 0.0214 | 6.0 | 13566 | 0.0583 | 0.9069 | 0.9330 | 0.9197 | 0.9855 |
63
+ | 0.0162 | 7.0 | 15827 | 0.0684 | 0.9154 | 0.9259 | 0.9206 | 0.9854 |
64
+ | 0.0129 | 8.0 | 18088 | 0.0736 | 0.9158 | 0.9339 | 0.9248 | 0.9854 |
65
+ | 0.0074 | 9.0 | 20349 | 0.0869 | 0.9091 | 0.9355 | 0.9221 | 0.9854 |
66
+ | 0.0049 | 10.0 | 22610 | 0.0941 | 0.9139 | 0.9358 | 0.9248 | 0.9856 |
67
 
68
 
69
  ### Framework versions
70
 
71
+ - Transformers 4.30.2
72
  - Pytorch 2.0.1+cu117
73
+ - Datasets 2.13.0
74
  - Tokenizers 0.13.3