fresh-2-layer-medmcqa20000-distill-of-fresh-2-layer-gpqa_EVAL_gpqa
Browse files- README.md +29 -28
- pytorch_model.bin +1 -1
- 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:
|
19 |
-
- Accuracy: 0.
|
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.
|
52 |
-
| No log | 0.32 | 200 | 11.
|
53 |
-
| No log | 0.48 | 300 | 9.
|
54 |
-
| No log | 0.64 | 400 |
|
55 |
-
| 3.
|
56 |
-
| 3.
|
57 |
-
| 3.
|
58 |
-
| 3.
|
59 |
-
| 3.
|
60 |
-
| 0.
|
61 |
-
| 0.
|
62 |
-
| 0.
|
63 |
-
| 0.
|
64 |
-
| 0.
|
65 |
-
| 0.
|
66 |
-
| 0.
|
67 |
-
| 0.
|
68 |
-
| 0.
|
69 |
-
| 0.
|
70 |
-
| 0.
|
71 |
-
| 0.
|
72 |
-
| 0.
|
73 |
-
| 0.
|
74 |
-
| 0.
|
75 |
-
| 0.
|
76 |
-
| 0.
|
|
|
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:
|
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 |
-
|
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,
|