Hugging Face's logo

afaji
/
fresh-2-layer-medmcqa-distill-of-fresh-2-layer-gpqa_EVAL_gpqa

Multiple Choice
Transformers
PyTorch
bert
Generated from Trainer
Inference Endpoints
Model card Files Community
afaji commited on
Commit
1c9631c
•
1 Parent(s): 29fe8bb

fresh-2-layer-medmcqa-distill-of-fresh-2-layer-gpqa_EVAL_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: 9.4859
19
- - Accuracy: 0.6111
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 | 15.9159 | 0.2727 |
52
- | No log | 2.0 | 126 | 13.1758 | 0.3838 |
53
- | No log | 3.0 | 189 | 12.5917 | 0.4596 |
54
- | No log | 4.0 | 252 | 11.4595 | 0.4899 |
55
- | No log | 5.0 | 315 | 11.0792 | 0.5152 |
56
- | No log | 6.0 | 378 | 10.3175 | 0.5455 |
57
- | No log | 7.0 | 441 | 10.4051 | 0.5505 |
58
- | 2.9311 | 8.0 | 504 | 10.6829 | 0.5556 |
59
- | 2.9311 | 9.0 | 567 | 10.7602 | 0.5253 |
60
- | 2.9311 | 10.0 | 630 | 10.2955 | 0.5707 |
61
- | 2.9311 | 11.0 | 693 | 9.8900 | 0.5606 |
62
- | 2.9311 | 12.0 | 756 | 9.5430 | 0.5960 |
63
- | 2.9311 | 13.0 | 819 | 9.8694 | 0.5909 |
64
- | 2.9311 | 14.0 | 882 | 9.6516 | 0.5758 |
65
- | 2.9311 | 15.0 | 945 | 9.4962 | 0.6010 |
66
- | 0.3764 | 16.0 | 1008 | 9.8449 | 0.5960 |
67
- | 0.3764 | 17.0 | 1071 | 9.5987 | 0.6061 |
68
- | 0.3764 | 18.0 | 1134 | 9.6737 | 0.6061 |
69
- | 0.3764 | 19.0 | 1197 | 9.5190 | 0.6061 |
70
- | 0.3764 | 20.0 | 1260 | 9.4859 | 0.6111 |
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: 8.0989
19
+ - Accuracy: 0.6566
20
 
21
  ## Model description
22
 
 
48
 
49
  | Training Loss | Epoch | Step | Validation Loss | Accuracy |
50
  |:-------------:|:-----:|:----:|:---------------:|:--------:|
51
+ | No log | 1.0 | 125 | 13.0027 | 0.4747 |
52
+ | No log | 2.0 | 250 | 10.8183 | 0.5404 |
53
+ | No log | 3.0 | 375 | 11.0325 | 0.5909 |
54
+ | 3.3093 | 4.0 | 500 | 11.0605 | 0.5808 |
55
+ | 3.3093 | 5.0 | 625 | 9.5436 | 0.5758 |
56
+ | 3.3093 | 6.0 | 750 | 9.1106 | 0.6515 |
57
+ | 3.3093 | 7.0 | 875 | 8.4697 | 0.6212 |
58
+ | 0.675 | 8.0 | 1000 | 9.1724 | 0.6212 |
59
+ | 0.675 | 9.0 | 1125 | 8.4508 | 0.6515 |
60
+ | 0.675 | 10.0 | 1250 | 8.5147 | 0.6111 |
61
+ | 0.675 | 11.0 | 1375 | 8.4648 | 0.6414 |
62
+ | 0.2645 | 12.0 | 1500 | 8.2626 | 0.6515 |
63
+ | 0.2645 | 13.0 | 1625 | 8.2865 | 0.6515 |
64
+ | 0.2645 | 14.0 | 1750 | 8.1180 | 0.6465 |
65
+ | 0.2645 | 15.0 | 1875 | 8.5052 | 0.6414 |
66
+ | 0.1402 | 16.0 | 2000 | 7.9762 | 0.6515 |
67
+ | 0.1402 | 17.0 | 2125 | 8.1063 | 0.6515 |
68
+ | 0.1402 | 18.0 | 2250 | 8.0695 | 0.6515 |
69
+ | 0.1402 | 19.0 | 2375 | 8.0989 | 0.6566 |
70
+ | 0.07 | 20.0 | 2500 | 8.0972 | 0.6566 |
71
 
72
 
73
  ### Framework versions
pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:9cb5c8081057baddf84f58fa7348638213250f767f366525687cbb72fb6ccbe0
3
  size 98247916
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3a29010959713f4f8b6a1dc070fd1d493c25d89dc96e0e6d836f52563042b807
3
  size 98247916