Hugging Face's logo

Tommert25
/
multibert_dataaugmentation

Token Classification
Transformers
PyTorch
bert
Generated from Trainer
Inference Endpoints
Model card Files Community
Tommert25 commited on
Commit
4a36f31
·
1 Parent(s): 494032a

End of training

Browse files
Files changed (2) hide show
  1. README.md +19 -19
  2. pytorch_model.bin +1 -1
README.md CHANGED
@@ -18,11 +18,11 @@ should probably proofread and complete it, then remove this comment. -->
18
 
19
  This model is a fine-tuned version of [bert-base-multilingual-uncased](https://huggingface.co/bert-base-multilingual-uncased) on an unknown dataset.
20
  It achieves the following results on the evaluation set:
21
- - Loss: 0.7216
22
- - Precisions: 0.8745
23
- - Recall: 0.8029
24
- - F-measure: 0.8291
25
- - Accuracy: 0.9015
26
 
27
  ## Model description
28
 
@@ -53,20 +53,20 @@ The following hyperparameters were used during training:
53
 
54
  | Training Loss | Epoch | Step | Validation Loss | Precisions | Recall | F-measure | Accuracy |
55
  |:-------------:|:-----:|:----:|:---------------:|:----------:|:------:|:---------:|:--------:|
56
- | 0.5776 | 1.0 | 284 | 0.5209 | 0.7928 | 0.6866 | 0.7216 | 0.8385 |
57
- | 0.2774 | 2.0 | 568 | 0.4278 | 0.8274 | 0.7457 | 0.7626 | 0.8802 |
58
- | 0.1471 | 3.0 | 852 | 0.5814 | 0.8455 | 0.7114 | 0.7399 | 0.8627 |
59
- | 0.0933 | 4.0 | 1136 | 0.5386 | 0.8006 | 0.7300 | 0.7556 | 0.8835 |
60
- | 0.0631 | 5.0 | 1420 | 0.6197 | 0.8122 | 0.7445 | 0.7682 | 0.8846 |
61
- | 0.0437 | 6.0 | 1704 | 0.6973 | 0.8675 | 0.7423 | 0.7802 | 0.8815 |
62
- | 0.0274 | 7.0 | 1988 | 0.6409 | 0.7960 | 0.7586 | 0.7729 | 0.8895 |
63
- | 0.0202 | 8.0 | 2272 | 0.6477 | 0.8550 | 0.7712 | 0.8003 | 0.8922 |
64
- | 0.0136 | 9.0 | 2556 | 0.7231 | 0.8722 | 0.7765 | 0.8088 | 0.8919 |
65
- | 0.0094 | 10.0 | 2840 | 0.6787 | 0.8585 | 0.7916 | 0.8106 | 0.8955 |
66
- | 0.0064 | 11.0 | 3124 | 0.7215 | 0.8750 | 0.7819 | 0.8107 | 0.8974 |
67
- | 0.0052 | 12.0 | 3408 | 0.7295 | 0.8811 | 0.7840 | 0.8154 | 0.8985 |
68
- | 0.0038 | 13.0 | 3692 | 0.7216 | 0.8745 | 0.8029 | 0.8291 | 0.9015 |
69
- | 0.003 | 14.0 | 3976 | 0.7180 | 0.8745 | 0.8023 | 0.8289 | 0.9001 |
70
 
71
 
72
  ### Framework versions
 
18
 
19
  This model is a fine-tuned version of [bert-base-multilingual-uncased](https://huggingface.co/bert-base-multilingual-uncased) on an unknown dataset.
20
  It achieves the following results on the evaluation set:
21
+ - Loss: 0.6354
22
+ - Precisions: 0.8725
23
+ - Recall: 0.8025
24
+ - F-measure: 0.8295
25
+ - Accuracy: 0.8996
26
 
27
  ## Model description
28
 
 
53
 
54
  | Training Loss | Epoch | Step | Validation Loss | Precisions | Recall | F-measure | Accuracy |
55
  |:-------------:|:-----:|:----:|:---------------:|:----------:|:------:|:---------:|:--------:|
56
+ | 0.5999 | 1.0 | 284 | 0.4542 | 0.8507 | 0.7167 | 0.7422 | 0.8708 |
57
+ | 0.2808 | 2.0 | 568 | 0.3886 | 0.8552 | 0.7964 | 0.8192 | 0.8864 |
58
+ | 0.1596 | 3.0 | 852 | 0.4749 | 0.8786 | 0.7893 | 0.8208 | 0.8905 |
59
+ | 0.1035 | 4.0 | 1136 | 0.5060 | 0.8568 | 0.8034 | 0.8208 | 0.8954 |
60
+ | 0.0719 | 5.0 | 1420 | 0.5716 | 0.8498 | 0.8102 | 0.8255 | 0.8919 |
61
+ | 0.0456 | 6.0 | 1704 | 0.6255 | 0.8701 | 0.8060 | 0.8279 | 0.8960 |
62
+ | 0.0284 | 7.0 | 1988 | 0.6354 | 0.8725 | 0.8025 | 0.8295 | 0.8996 |
63
+ | 0.0205 | 8.0 | 2272 | 0.7146 | 0.8518 | 0.8105 | 0.8266 | 0.8988 |
64
+ | 0.011 | 9.0 | 2556 | 0.7307 | 0.8614 | 0.8045 | 0.8279 | 0.9004 |
65
+ | 0.0082 | 10.0 | 2840 | 0.7403 | 0.8785 | 0.7988 | 0.8255 | 0.9009 |
66
+ | 0.0064 | 11.0 | 3124 | 0.7756 | 0.8809 | 0.7913 | 0.8217 | 0.8989 |
67
+ | 0.0039 | 12.0 | 3408 | 0.8036 | 0.8650 | 0.7877 | 0.8130 | 0.8966 |
68
+ | 0.0038 | 13.0 | 3692 | 0.7660 | 0.8781 | 0.7950 | 0.8222 | 0.8997 |
69
+ | 0.0025 | 14.0 | 3976 | 0.7640 | 0.8829 | 0.7961 | 0.8249 | 0.9012 |
70
 
71
 
72
  ### Framework versions
pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0290d688618a632da2551d6c642619e172d35f1b2648aff0daee3de910a96515
3
  size 667152553
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f24f0be30881d2fb25a6759b3f0eff249e3324982362d87d074bbc48cc7a4335
3
  size 667152553