Hugging Face's logo

afaji
/
fresh-2-layer-medmcqa10000-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
a5ea010
•
1 Parent(s): b7d6bd1

fresh-2-layer-medmcqa10000-distill-of-fresh-2-layer-gpqa_EVAL_gpqa

Browse files
Files changed (2) hide show
  1. README.md +32 -19
  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: 7.4163
19
- - Accuracy: 0.7071
20
 
21
  ## Model description
22
 
@@ -48,23 +48,36 @@ The following hyperparameters were used during training:
48
 
49
  | Training Loss | Epoch | Step | Validation Loss | Accuracy |
50
  |:-------------:|:-----:|:----:|:---------------:|:--------:|
51
- | No log | 0.32 | 100 | 13.4249 | 0.3788 |
52
- | No log | 0.64 | 200 | 11.8598 | 0.5 |
53
- | No log | 0.96 | 300 | 9.9228 | 0.5707 |
54
- | No log | 1.28 | 400 | 9.1023 | 0.5909 |
55
- | 3.2199 | 1.6 | 500 | 8.7143 | 0.6263 |
56
- | 3.2199 | 1.92 | 600 | 8.6075 | 0.6515 |
57
- | 3.2199 | 2.24 | 700 | 8.8026 | 0.6212 |
58
- | 3.2199 | 2.56 | 800 | 8.8548 | 0.6111 |
59
- | 3.2199 | 2.88 | 900 | 8.1953 | 0.6465 |
60
- | 0.909 | 3.19 | 1000 | 7.6411 | 0.6465 |
61
- | 0.909 | 3.51 | 1100 | 8.8796 | 0.6616 |
62
- | 0.909 | 3.83 | 1200 | 7.4163 | 0.7071 |
63
- | 0.909 | 4.15 | 1300 | 7.6117 | 0.6414 |
64
- | 0.909 | 4.47 | 1400 | 7.7245 | 0.6717 |
65
- | 0.4831 | 4.79 | 1500 | 7.2824 | 0.6869 |
66
- | 0.4831 | 5.11 | 1600 | 7.3471 | 0.6970 |
67
- | 0.4831 | 5.43 | 1700 | 7.5603 | 0.6818 |
 
 
 
 
 
 
 
 
 
 
 
 
 
68
 
69
 
70
  ### 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: 7.2371
19
+ - Accuracy: 0.7222
20
 
21
  ## Model description
22
 
 
48
 
49
  | Training Loss | Epoch | Step | Validation Loss | Accuracy |
50
  |:-------------:|:-----:|:----:|:---------------:|:--------:|
51
+ | No log | 0.32 | 100 | 13.8640 | 0.4495 |
52
+ | No log | 0.64 | 200 | 11.8895 | 0.5152 |
53
+ | No log | 0.96 | 300 | 10.3828 | 0.5303 |
54
+ | No log | 1.28 | 400 | 9.0300 | 0.5657 |
55
+ | 3.3496 | 1.6 | 500 | 8.6264 | 0.5808 |
56
+ | 3.3496 | 1.92 | 600 | 8.8207 | 0.6061 |
57
+ | 3.3496 | 2.24 | 700 | 8.8302 | 0.5960 |
58
+ | 3.3496 | 2.56 | 800 | 8.8428 | 0.6566 |
59
+ | 3.3496 | 2.88 | 900 | 7.9552 | 0.6364 |
60
+ | 0.8968 | 3.19 | 1000 | 8.4617 | 0.6263 |
61
+ | 0.8968 | 3.51 | 1100 | 8.8555 | 0.6616 |
62
+ | 0.8968 | 3.83 | 1200 | 7.5445 | 0.6566 |
63
+ | 0.8968 | 4.15 | 1300 | 7.6791 | 0.6717 |
64
+ | 0.8968 | 4.47 | 1400 | 7.8363 | 0.6616 |
65
+ | 0.4853 | 4.79 | 1500 | 7.6269 | 0.6515 |
66
+ | 0.4853 | 5.11 | 1600 | 7.5024 | 0.6919 |
67
+ | 0.4853 | 5.43 | 1700 | 7.4191 | 0.6717 |
68
+ | 0.4853 | 5.75 | 1800 | 7.6877 | 0.6768 |
69
+ | 0.4853 | 6.07 | 1900 | 7.4651 | 0.6818 |
70
+ | 0.3197 | 6.39 | 2000 | 7.4452 | 0.6970 |
71
+ | 0.3197 | 6.71 | 2100 | 7.2401 | 0.7121 |
72
+ | 0.3197 | 7.03 | 2200 | 7.4038 | 0.7121 |
73
+ | 0.3197 | 7.35 | 2300 | 7.1982 | 0.7071 |
74
+ | 0.3197 | 7.67 | 2400 | 7.2287 | 0.7071 |
75
+ | 0.2394 | 7.99 | 2500 | 7.2371 | 0.7222 |
76
+ | 0.2394 | 8.31 | 2600 | 7.2513 | 0.7071 |
77
+ | 0.2394 | 8.63 | 2700 | 7.3788 | 0.6919 |
78
+ | 0.2394 | 8.95 | 2800 | 7.1303 | 0.7071 |
79
+ | 0.2394 | 9.27 | 2900 | 7.1608 | 0.7121 |
80
+ | 0.1744 | 9.58 | 3000 | 7.1039 | 0.7222 |
81
 
82
 
83
  ### Framework versions
pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c52fb7a8a49aecfb2316f035e3c279dcbad98517a8fb44c83b2ba5562c7d9082
3
  size 98247916
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:170794066e4b694be635820f11ee58e1f5bf4e525064ab40ee504439aaddee3d
3
  size 98247916