Hugging Face's logo

afaji
/
fresh-4-layer-swag-distill-of-fresh-4-layer-gpqa

Multiple Choice
Transformers
PyTorch
bert
Generated from Trainer
Inference Endpoints
Model card Files Community
afaji commited on
Commit
7e17e06
•
1 Parent(s): 8abb356

fresh-4-layer-swag-distill-of-fresh-4-layer-gpqa

Browse files
Files changed (2) hide show
  1. README.md +22 -22
  2. pytorch_model.bin +1 -1
README.md CHANGED
@@ -15,8 +15,8 @@ should probably proofread and complete it, then remove this comment. -->
15
 
16
  This model is a fine-tuned version of [](https://huggingface.co/) on an unknown dataset.
17
  It achieves the following results on the evaluation set:
18
- - Loss: 13.7243
19
- - Accuracy: 0.4141
20
 
21
  ## Model description
22
 
@@ -48,26 +48,26 @@ The following hyperparameters were used during training:
48
 
49
  | Training Loss | Epoch | Step | Validation Loss | Accuracy |
50
  |:-------------:|:-----:|:----:|:---------------:|:--------:|
51
- | No log | 1.0 | 63 | 12.7754 | 0.2879 |
52
- | No log | 2.0 | 126 | 15.8531 | 0.3333 |
53
- | No log | 3.0 | 189 | 14.6240 | 0.3636 |
54
- | No log | 4.0 | 252 | 14.4419 | 0.3737 |
55
- | No log | 5.0 | 315 | 14.0280 | 0.4091 |
56
- | No log | 6.0 | 378 | 13.7243 | 0.4141 |
57
- | No log | 7.0 | 441 | 13.9530 | 0.3838 |
58
- | 1.7783 | 8.0 | 504 | 12.1750 | 0.3737 |
59
- | 1.7783 | 9.0 | 567 | 13.5994 | 0.3889 |
60
- | 1.7783 | 10.0 | 630 | 12.8507 | 0.3586 |
61
- | 1.7783 | 11.0 | 693 | 13.4322 | 0.3838 |
62
- | 1.7783 | 12.0 | 756 | 11.9978 | 0.3990 |
63
- | 1.7783 | 13.0 | 819 | 13.3436 | 0.3939 |
64
- | 1.7783 | 14.0 | 882 | 12.3388 | 0.4040 |
65
- | 1.7783 | 15.0 | 945 | 12.5646 | 0.4141 |
66
- | 0.2705 | 16.0 | 1008 | 13.2618 | 0.3838 |
67
- | 0.2705 | 17.0 | 1071 | 12.4800 | 0.3990 |
68
- | 0.2705 | 18.0 | 1134 | 12.5251 | 0.3838 |
69
- | 0.2705 | 19.0 | 1197 | 12.8962 | 0.3990 |
70
- | 0.2705 | 20.0 | 1260 | 12.5932 | 0.3990 |
71
 
72
 
73
  ### Framework versions
 
15
 
16
  This model is a fine-tuned version of [](https://huggingface.co/) on an unknown dataset.
17
  It achieves the following results on the evaluation set:
18
+ - Loss: 11.8632
19
+ - Accuracy: 0.4293
20
 
21
  ## Model description
22
 
 
48
 
49
  | Training Loss | Epoch | Step | Validation Loss | Accuracy |
50
  |:-------------:|:-----:|:----:|:---------------:|:--------:|
51
+ | No log | 1.0 | 125 | 13.8015 | 0.2778 |
52
+ | No log | 2.0 | 250 | 14.0268 | 0.3535 |
53
+ | No log | 3.0 | 375 | 13.0123 | 0.3838 |
54
+ | 1.8616 | 4.0 | 500 | 12.3288 | 0.3535 |
55
+ | 1.8616 | 5.0 | 625 | 12.1718 | 0.3737 |
56
+ | 1.8616 | 6.0 | 750 | 12.7654 | 0.3889 |
57
+ | 1.8616 | 7.0 | 875 | 12.6711 | 0.3838 |
58
+ | 0.4769 | 8.0 | 1000 | 12.0719 | 0.4141 |
59
+ | 0.4769 | 9.0 | 1125 | 11.8960 | 0.4091 |
60
+ | 0.4769 | 10.0 | 1250 | 12.0726 | 0.4192 |
61
+ | 0.4769 | 11.0 | 1375 | 11.8632 | 0.4293 |
62
+ | 0.1853 | 12.0 | 1500 | 11.6135 | 0.4141 |
63
+ | 0.1853 | 13.0 | 1625 | 12.2307 | 0.4141 |
64
+ | 0.1853 | 14.0 | 1750 | 11.7646 | 0.4040 |
65
+ | 0.1853 | 15.0 | 1875 | 11.6897 | 0.4141 |
66
+ | 0.0913 | 16.0 | 2000 | 12.0394 | 0.4091 |
67
+ | 0.0913 | 17.0 | 2125 | 11.7915 | 0.4040 |
68
+ | 0.0913 | 18.0 | 2250 | 12.0047 | 0.3990 |
69
+ | 0.0913 | 19.0 | 2375 | 11.9798 | 0.3939 |
70
+ | 0.0436 | 20.0 | 2500 | 12.0208 | 0.4040 |
71
 
72
 
73
  ### Framework versions
pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ec45730f4e3d600d59780ec63b782636bf369550460ccc8f06422977acce2c6c
3
  size 131874700
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9a8ab7d6e277e9b186371314a6e2ed5dfb5c52ab6cf923ff59f2cc3744233b3a
3
  size 131874700