Newton Kimathi commited on
Commit
089bc72
1 Parent(s): 164b448

End of training

Browse files
Files changed (2) hide show
  1. README.md +26 -12
  2. pytorch_model.bin +1 -1
README.md CHANGED
@@ -15,7 +15,7 @@ should probably proofread and complete it, then remove this comment. -->
15
 
16
  This model is a fine-tuned version of [bert-base-cased](https://huggingface.co/bert-base-cased) on an unknown dataset.
17
  It achieves the following results on the evaluation set:
18
- - Loss: 1.0370
19
 
20
  ## Model description
21
 
@@ -40,23 +40,37 @@ The following hyperparameters were used during training:
40
  - seed: 42
41
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
42
  - lr_scheduler_type: linear
43
- - num_epochs: 3
44
 
45
  ### Training results
46
 
47
- | Training Loss | Epoch | Step | Validation Loss |
48
- |:-------------:|:-----:|:----:|:---------------:|
49
- | 0.7418 | 0.5 | 500 | 0.6955 |
50
- | 0.6729 | 1.0 | 1000 | 0.5980 |
51
- | 0.5229 | 1.5 | 1500 | 0.6831 |
52
- | 0.5016 | 2.0 | 2000 | 0.6205 |
53
- | 0.327 | 2.5 | 2500 | 0.9250 |
54
- | 0.2762 | 3.0 | 3000 | 1.0370 |
 
 
 
 
 
 
 
 
 
 
 
 
 
 
55
 
56
 
57
  ### Framework versions
58
 
59
- - Transformers 4.32.1
60
  - Pytorch 2.0.1+cu118
61
- - Datasets 2.14.4
62
  - Tokenizers 0.13.3
 
15
 
16
  This model is a fine-tuned version of [bert-base-cased](https://huggingface.co/bert-base-cased) on an unknown dataset.
17
  It achieves the following results on the evaluation set:
18
+ - Loss: 2.0254
19
 
20
  ## Model description
21
 
 
40
  - seed: 42
41
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
42
  - lr_scheduler_type: linear
43
+ - num_epochs: 10
44
 
45
  ### Training results
46
 
47
+ | Training Loss | Epoch | Step | Validation Loss |
48
+ |:-------------:|:-----:|:-----:|:---------------:|
49
+ | 0.7571 | 0.5 | 500 | 0.7201 |
50
+ | 0.7109 | 1.0 | 1000 | 0.7818 |
51
+ | 0.6315 | 1.5 | 1500 | 0.6852 |
52
+ | 0.6027 | 2.0 | 2000 | 0.6426 |
53
+ | 0.4843 | 2.5 | 2500 | 0.7306 |
54
+ | 0.4498 | 3.0 | 3000 | 0.6962 |
55
+ | 0.3384 | 3.5 | 3500 | 1.0376 |
56
+ | 0.3462 | 4.0 | 4000 | 1.1839 |
57
+ | 0.2456 | 4.5 | 4500 | 1.2843 |
58
+ | 0.2445 | 5.0 | 5000 | 1.3436 |
59
+ | 0.1542 | 5.5 | 5500 | 1.5233 |
60
+ | 0.1698 | 6.0 | 6000 | 1.5252 |
61
+ | 0.1042 | 6.5 | 6500 | 1.4930 |
62
+ | 0.11 | 7.0 | 7000 | 1.5485 |
63
+ | 0.0646 | 7.5 | 7500 | 1.7473 |
64
+ | 0.0711 | 8.0 | 8000 | 1.7637 |
65
+ | 0.0456 | 8.5 | 8500 | 1.8249 |
66
+ | 0.0379 | 9.0 | 9000 | 1.9362 |
67
+ | 0.0305 | 9.5 | 9500 | 2.0290 |
68
+ | 0.025 | 10.0 | 10000 | 2.0254 |
69
 
70
 
71
  ### Framework versions
72
 
73
+ - Transformers 4.33.1
74
  - Pytorch 2.0.1+cu118
75
+ - Datasets 2.14.5
76
  - Tokenizers 0.13.3
pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f4fbd2fd037bd6f618ea366cf2af2befc11bae824750e23eea6565472a87ac0d
3
  size 433318705
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ef1312703bf9e594b88960b5474b3ca3f63949ea73bbf174f6b1239f082dd5eb
3
  size 433318705