Hugging Face's logo

mpalaval
/
assignment2_attempt11

Token Classification
Transformers
PyTorch
bert
Generated from Trainer
Model card Files
xet
Community
mpalaval commited on
Commit
e9345b2
·
1 Parent(s): 25359f3

End of training

Browse files
Files changed (2) hide show
  1. README.md +20 -20
  2. pytorch_model.bin +1 -1
README.md CHANGED
@@ -20,11 +20,11 @@ should probably proofread and complete it, then remove this comment. -->
20
 
21
  This model is a fine-tuned version of [bert-base-cased](https://huggingface.co/bert-base-cased) on the None dataset.
22
  It achieves the following results on the evaluation set:
23
- - Loss: 0.5801
24
- - Precision: 0.25
25
- - Recall: 0.1271
26
- - F1: 0.1685
27
- - Accuracy: 0.9361
28
 
29
  ## Model description
30
 
@@ -55,21 +55,21 @@ The following hyperparameters were used during training:
55
 
56
  | Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
57
  |:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
58
- | No log | 1.0 | 128 | 0.3153 | 0.0 | 0.0 | 0.0 | 0.9388 |
59
- | No log | 2.0 | 256 | 0.2743 | 0.1452 | 0.0763 | 0.1000 | 0.9362 |
60
- | No log | 3.0 | 384 | 0.3585 | 0.1636 | 0.0763 | 0.1040 | 0.9331 |
61
- | 0.2077 | 4.0 | 512 | 0.4103 | 0.2973 | 0.0932 | 0.1419 | 0.9391 |
62
- | 0.2077 | 5.0 | 640 | 0.4270 | 0.3111 | 0.1186 | 0.1718 | 0.9404 |
63
- | 0.2077 | 6.0 | 768 | 0.4653 | 0.2414 | 0.1186 | 0.1591 | 0.9371 |
64
- | 0.2077 | 7.0 | 896 | 0.4569 | 0.14 | 0.1186 | 0.1284 | 0.9316 |
65
- | 0.023 | 8.0 | 1024 | 0.4619 | 0.1647 | 0.1186 | 0.1379 | 0.9333 |
66
- | 0.023 | 9.0 | 1152 | 0.5165 | 0.2456 | 0.1186 | 0.16 | 0.9372 |
67
- | 0.023 | 10.0 | 1280 | 0.5495 | 0.2459 | 0.1271 | 0.1676 | 0.9361 |
68
- | 0.023 | 11.0 | 1408 | 0.5714 | 0.2778 | 0.1271 | 0.1744 | 0.9378 |
69
- | 0.0047 | 12.0 | 1536 | 0.5712 | 0.2586 | 0.1271 | 0.1705 | 0.9368 |
70
- | 0.0047 | 13.0 | 1664 | 0.5776 | 0.2542 | 0.1271 | 0.1695 | 0.9363 |
71
- | 0.0047 | 14.0 | 1792 | 0.5785 | 0.2632 | 0.1271 | 0.1714 | 0.9365 |
72
- | 0.0047 | 15.0 | 1920 | 0.5801 | 0.25 | 0.1271 | 0.1685 | 0.9361 |
73
 
74
 
75
  ### Framework versions
 
20
 
21
  This model is a fine-tuned version of [bert-base-cased](https://huggingface.co/bert-base-cased) on the None dataset.
22
  It achieves the following results on the evaluation set:
23
+ - Loss: 0.6058
24
+ - Precision: 0.2642
25
+ - Recall: 0.1186
26
+ - F1: 0.1637
27
+ - Accuracy: 0.9370
28
 
29
  ## Model description
30
 
 
55
 
56
  | Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
57
  |:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
58
+ | No log | 1.0 | 128 | 0.3124 | 0.2308 | 0.0254 | 0.0458 | 0.9401 |
59
+ | No log | 2.0 | 256 | 0.2862 | 0.1636 | 0.0763 | 0.1040 | 0.9353 |
60
+ | No log | 3.0 | 384 | 0.3899 | 0.2093 | 0.0763 | 0.1118 | 0.9359 |
61
+ | 0.1996 | 4.0 | 512 | 0.4161 | 0.3095 | 0.1102 | 0.1625 | 0.9382 |
62
+ | 0.1996 | 5.0 | 640 | 0.4845 | 0.3077 | 0.1017 | 0.1529 | 0.9392 |
63
+ | 0.1996 | 6.0 | 768 | 0.4841 | 0.2692 | 0.1186 | 0.1647 | 0.9365 |
64
+ | 0.1996 | 7.0 | 896 | 0.4987 | 0.2258 | 0.1186 | 0.1556 | 0.9349 |
65
+ | 0.0254 | 8.0 | 1024 | 0.5512 | 0.2766 | 0.1102 | 0.1576 | 0.9370 |
66
+ | 0.0254 | 9.0 | 1152 | 0.5772 | 0.3171 | 0.1102 | 0.1635 | 0.9379 |
67
+ | 0.0254 | 10.0 | 1280 | 0.5764 | 0.2586 | 0.1271 | 0.1705 | 0.9342 |
68
+ | 0.0254 | 11.0 | 1408 | 0.5964 | 0.2917 | 0.1186 | 0.1687 | 0.9380 |
69
+ | 0.005 | 12.0 | 1536 | 0.5952 | 0.2642 | 0.1186 | 0.1637 | 0.9368 |
70
+ | 0.005 | 13.0 | 1664 | 0.5980 | 0.2593 | 0.1186 | 0.1628 | 0.9367 |
71
+ | 0.005 | 14.0 | 1792 | 0.6033 | 0.2642 | 0.1186 | 0.1637 | 0.9370 |
72
+ | 0.005 | 15.0 | 1920 | 0.6058 | 0.2642 | 0.1186 | 0.1637 | 0.9370 |
73
 
74
 
75
  ### Framework versions
pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:6a56da538751ce20a0b4471eb21576605a5e4001ca1c72c57a2b42b566f048da
3
  size 430993062
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e84bd73f6f7eccbbf1fecae162607f5da68766be42e3f22d476f4ac452329032
3
  size 430993062