Hugging Face's logo

afaji
/
fresh-2-layer-medmcqa20000-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
2fb8608
•
1 Parent(s): f378104

fresh-2-layer-medmcqa20000-distill-of-fresh-2-layer-gpqa_EVAL_gpqa

Browse files
Files changed (3) hide show
  1. README.md +29 -28
  2. pytorch_model.bin +1 -1
  3. tokenizer.json +2 -16
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: 6.0579
19
- - Accuracy: 0.7222
20
 
21
  ## Model description
22
 
@@ -48,32 +48,33 @@ The following hyperparameters were used during training:
48
 
49
  | Training Loss | Epoch | Step | Validation Loss | Accuracy |
50
  |:-------------:|:-----:|:----:|:---------------:|:--------:|
51
- | No log | 0.16 | 100 | 15.7756 | 0.3838 |
52
- | No log | 0.32 | 200 | 11.4980 | 0.5152 |
53
- | No log | 0.48 | 300 | 9.4964 | 0.5909 |
54
- | No log | 0.64 | 400 | 8.9627 | 0.6212 |
55
- | 3.5065 | 0.8 | 500 | 8.5232 | 0.6061 |
56
- | 3.5065 | 0.96 | 600 | 7.7951 | 0.6717 |
57
- | 3.5065 | 1.12 | 700 | 8.2685 | 0.6616 |
58
- | 3.5065 | 1.28 | 800 | 7.1380 | 0.6869 |
59
- | 3.5065 | 1.44 | 900 | 7.3768 | 0.6818 |
60
- | 0.9883 | 1.6 | 1000 | 6.9322 | 0.6970 |
61
- | 0.9883 | 1.76 | 1100 | 6.7062 | 0.6818 |
62
- | 0.9883 | 1.92 | 1200 | 6.6068 | 0.6919 |
63
- | 0.9883 | 2.08 | 1300 | 6.3543 | 0.6818 |
64
- | 0.9883 | 2.24 | 1400 | 6.0225 | 0.7020 |
65
- | 0.5892 | 2.4 | 1500 | 6.6609 | 0.6667 |
66
- | 0.5892 | 2.56 | 1600 | 6.3811 | 0.6919 |
67
- | 0.5892 | 2.72 | 1700 | 6.2649 | 0.6970 |
68
- | 0.5892 | 2.88 | 1800 | 6.8477 | 0.6919 |
69
- | 0.5892 | 3.04 | 1900 | 5.6575 | 0.7071 |
70
- | 0.4134 | 3.2 | 2000 | 5.8076 | 0.7071 |
71
- | 0.4134 | 3.36 | 2100 | 6.0579 | 0.7222 |
72
- | 0.4134 | 3.52 | 2200 | 5.7613 | 0.6970 |
73
- | 0.4134 | 3.68 | 2300 | 5.6748 | 0.7222 |
74
- | 0.4134 | 3.84 | 2400 | 5.8306 | 0.7121 |
75
- | 0.3115 | 4.0 | 2500 | 5.7578 | 0.7071 |
76
- | 0.3115 | 4.16 | 2600 | 5.5201 | 0.7172 |
 
77
 
78
 
79
  ### 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: 5.6554
19
+ - Accuracy: 0.7323
20
 
21
  ## Model description
22
 
 
48
 
49
  | Training Loss | Epoch | Step | Validation Loss | Accuracy |
50
  |:-------------:|:-----:|:----:|:---------------:|:--------:|
51
+ | No log | 0.16 | 100 | 15.6094 | 0.3384 |
52
+ | No log | 0.32 | 200 | 11.2486 | 0.4747 |
53
+ | No log | 0.48 | 300 | 9.7003 | 0.5556 |
54
+ | No log | 0.64 | 400 | 9.0128 | 0.6212 |
55
+ | 3.508 | 0.8 | 500 | 9.0146 | 0.6111 |
56
+ | 3.508 | 0.96 | 600 | 7.8672 | 0.6465 |
57
+ | 3.508 | 1.12 | 700 | 7.4123 | 0.6768 |
58
+ | 3.508 | 1.28 | 800 | 7.4161 | 0.6515 |
59
+ | 3.508 | 1.44 | 900 | 7.3679 | 0.6667 |
60
+ | 0.9934 | 1.6 | 1000 | 6.8781 | 0.6768 |
61
+ | 0.9934 | 1.76 | 1100 | 6.7447 | 0.6717 |
62
+ | 0.9934 | 1.92 | 1200 | 7.6242 | 0.6818 |
63
+ | 0.9934 | 2.08 | 1300 | 6.6278 | 0.6869 |
64
+ | 0.9934 | 2.24 | 1400 | 6.4569 | 0.6970 |
65
+ | 0.6102 | 2.4 | 1500 | 6.7556 | 0.7121 |
66
+ | 0.6102 | 2.56 | 1600 | 6.3065 | 0.7020 |
67
+ | 0.6102 | 2.72 | 1700 | 6.2906 | 0.7071 |
68
+ | 0.6102 | 2.88 | 1800 | 6.2230 | 0.7121 |
69
+ | 0.6102 | 3.04 | 1900 | 6.9069 | 0.7172 |
70
+ | 0.4278 | 3.2 | 2000 | 6.0706 | 0.7172 |
71
+ | 0.4278 | 3.36 | 2100 | 6.0340 | 0.7172 |
72
+ | 0.4278 | 3.52 | 2200 | 5.6554 | 0.7323 |
73
+ | 0.4278 | 3.68 | 2300 | 5.8829 | 0.7020 |
74
+ | 0.4278 | 3.84 | 2400 | 5.6822 | 0.7222 |
75
+ | 0.3174 | 4.0 | 2500 | 5.7620 | 0.7222 |
76
+ | 0.3174 | 4.16 | 2600 | 5.7952 | 0.7172 |
77
+ | 0.3174 | 4.32 | 2700 | 5.6193 | 0.7222 |
78
 
79
 
80
  ### Framework versions
pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b4040889cda02328f48cee1ea2cadf6be93111ca9a7ecc7800ec84fe1c320bff
3
  size 98247916
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7477d9b48bfc34973f667722f41df2741f5fd478902aeb205cfa1e1a917b45a3
3
  size 98247916
tokenizer.json CHANGED
@@ -1,21 +1,7 @@
1
  {
2
  "version": "1.0",
3
- "truncation": {
4
- "direction": "Right",
5
- "max_length": 512,
6
- "strategy": "LongestFirst",
7
- "stride": 0
8
- },
9
- "padding": {
10
- "strategy": {
11
- "Fixed": 512
12
- },
13
- "direction": "Right",
14
- "pad_to_multiple_of": null,
15
- "pad_id": 0,
16
- "pad_type_id": 0,
17
- "pad_token": "[PAD]"
18
- },
19
  "added_tokens": [
20
  {
21
  "id": 0,
 
1
  {
2
  "version": "1.0",
3
+ "truncation": null,
4
+ "padding": null,
 
 
 
 
 
 
 
 
 
 
 
 
 
 
5
  "added_tokens": [
6
  {
7
  "id": 0,