Hugging Face's logo

Tommert25
/
robbert_dataaugmentation

Token Classification
Transformers
PyTorch
roberta
Generated from Trainer
Inference Endpoints
Model card Files Community
Tommert25 commited on
Commit
6116e5e
·
1 Parent(s): 1f9bd5a

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 [pdelobelle/robbert-v2-dutch-base](https://huggingface.co/pdelobelle/robbert-v2-dutch-base) on an unknown dataset.
20
  It achieves the following results on the evaluation set:
21
- - Loss: 0.6833
22
- - Precisions: 0.8566
23
- - Recall: 0.8001
24
- - F-measure: 0.8200
25
- - Accuracy: 0.9051
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
- | 0.5974 | 1.0 | 284 | 0.4862 | 0.7056 | 0.7095 | 0.6861 | 0.8582 |
57
- | 0.2555 | 2.0 | 568 | 0.4399 | 0.7868 | 0.7784 | 0.7804 | 0.8856 |
58
- | 0.1306 | 3.0 | 852 | 0.4482 | 0.8741 | 0.7806 | 0.8057 | 0.9005 |
59
- | 0.0792 | 4.0 | 1136 | 0.5896 | 0.8170 | 0.7464 | 0.7440 | 0.8889 |
60
- | 0.0479 | 5.0 | 1420 | 0.5834 | 0.8550 | 0.7755 | 0.8004 | 0.9071 |
61
- | 0.0319 | 6.0 | 1704 | 0.6073 | 0.8253 | 0.7738 | 0.7866 | 0.8996 |
62
- | 0.0241 | 7.0 | 1988 | 0.6493 | 0.8488 | 0.7784 | 0.7987 | 0.9038 |
63
- | 0.017 | 8.0 | 2272 | 0.6967 | 0.8232 | 0.7900 | 0.8024 | 0.8978 |
64
- | 0.0179 | 9.0 | 2556 | 0.6627 | 0.8626 | 0.7983 | 0.8198 | 0.9055 |
65
- | 0.0097 | 10.0 | 2840 | 0.6833 | 0.8566 | 0.8001 | 0.8200 | 0.9051 |
66
- | 0.007 | 11.0 | 3124 | 0.6972 | 0.8574 | 0.7989 | 0.8196 | 0.9051 |
67
- | 0.0064 | 12.0 | 3408 | 0.7098 | 0.8524 | 0.7941 | 0.8141 | 0.9030 |
68
- | 0.0031 | 13.0 | 3692 | 0.7231 | 0.8612 | 0.7999 | 0.8194 | 0.9062 |
69
- | 0.0023 | 14.0 | 3976 | 0.7145 | 0.8629 | 0.7933 | 0.8149 | 0.9070 |
70
 
71
 
72
  ### Framework versions
 
18
 
19
  This model is a fine-tuned version of [pdelobelle/robbert-v2-dutch-base](https://huggingface.co/pdelobelle/robbert-v2-dutch-base) on an unknown dataset.
20
  It achieves the following results on the evaluation set:
21
+ - Loss: 0.7814
22
+ - Precisions: 0.8515
23
+ - Recall: 0.8094
24
+ - F-measure: 0.8265
25
+ - Accuracy: 0.9039
26
 
27
  ## Model description
28
 
 
53
 
54
  | Training Loss | Epoch | Step | Validation Loss | Precisions | Recall | F-measure | Accuracy |
55
  |:-------------:|:-----:|:----:|:---------------:|:----------:|:------:|:---------:|:--------:|
56
+ | 0.5813 | 1.0 | 285 | 0.4311 | 0.7695 | 0.7413 | 0.7537 | 0.8704 |
57
+ | 0.2533 | 2.0 | 570 | 0.4952 | 0.8339 | 0.7501 | 0.7745 | 0.8801 |
58
+ | 0.1216 | 3.0 | 855 | 0.5067 | 0.8403 | 0.7968 | 0.8148 | 0.8932 |
59
+ | 0.0685 | 4.0 | 1140 | 0.6121 | 0.8041 | 0.7972 | 0.7963 | 0.8886 |
60
+ | 0.0478 | 5.0 | 1425 | 0.6603 | 0.8239 | 0.7820 | 0.7983 | 0.8893 |
61
+ | 0.0294 | 6.0 | 1710 | 0.7029 | 0.8190 | 0.8029 | 0.8083 | 0.8954 |
62
+ | 0.0147 | 7.0 | 1995 | 0.7219 | 0.8332 | 0.8198 | 0.8227 | 0.8991 |
63
+ | 0.0142 | 8.0 | 2280 | 0.7702 | 0.8330 | 0.7953 | 0.8109 | 0.8961 |
64
+ | 0.0099 | 9.0 | 2565 | 0.7670 | 0.8340 | 0.7943 | 0.8086 | 0.8972 |
65
+ | 0.0044 | 10.0 | 2850 | 0.8132 | 0.8434 | 0.8026 | 0.8193 | 0.9025 |
66
+ | 0.0058 | 11.0 | 3135 | 0.7757 | 0.8468 | 0.8100 | 0.8253 | 0.9033 |
67
+ | 0.0046 | 12.0 | 3420 | 0.7814 | 0.8515 | 0.8094 | 0.8265 | 0.9039 |
68
+ | 0.0029 | 13.0 | 3705 | 0.8057 | 0.8494 | 0.8046 | 0.8229 | 0.9029 |
69
+ | 0.0012 | 14.0 | 3990 | 0.7994 | 0.8492 | 0.8047 | 0.8230 | 0.9031 |
70
 
71
 
72
  ### Framework versions
pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:284cea87c08f2cac8e0dc2137901e1d6bf15c5680c53925ec501d22085c0e845
3
  size 464775913
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:96f721e7bd193d53c58f1ce1a86df5f3a8a56c9f7869eeb62571c0e84b672f4f
3
  size 464775913