fresh-2-layer-medmcqa50000-distill-of-fresh-2-layer-gpqa_EVAL_gpqa
Browse files- README.md +24 -38
- 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 |
|
|
@@ -48,42 +48,28 @@ The following hyperparameters were used during training:
|
|
| 48 |
|
| 49 |
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|
| 50 |
|:-------------:|:-----:|:----:|:---------------:|:--------:|
|
| 51 |
-
| No log | 0.06 | 100 | 14.
|
| 52 |
-
| No log | 0.13 | 200 |
|
| 53 |
-
| No log | 0.19 | 300 |
|
| 54 |
-
| No log | 0.26 | 400 | 9.
|
| 55 |
-
| 3.
|
| 56 |
-
| 3.
|
| 57 |
-
| 3.
|
| 58 |
-
| 3.
|
| 59 |
-
| 3.
|
| 60 |
-
| 1.
|
| 61 |
-
| 1.
|
| 62 |
-
| 1.
|
| 63 |
-
| 1.
|
| 64 |
-
| 1.
|
| 65 |
-
| 0.
|
| 66 |
-
| 0.
|
| 67 |
-
| 0.
|
| 68 |
-
| 0.
|
| 69 |
-
| 0.
|
| 70 |
-
| 0.
|
| 71 |
-
| 0.
|
| 72 |
-
| 0.
|
| 73 |
-
| 0.4805 | 1.47 | 2300 | 5.6583 | 0.7374 |
|
| 74 |
-
| 0.4805 | 1.54 | 2400 | 5.1442 | 0.7475 |
|
| 75 |
-
| 0.3914 | 1.6 | 2500 | 5.0866 | 0.7677 |
|
| 76 |
-
| 0.3914 | 1.66 | 2600 | 5.0077 | 0.7626 |
|
| 77 |
-
| 0.3914 | 1.73 | 2700 | 4.6813 | 0.7778 |
|
| 78 |
-
| 0.3914 | 1.79 | 2800 | 4.8810 | 0.7677 |
|
| 79 |
-
| 0.3914 | 1.86 | 2900 | 4.6941 | 0.7626 |
|
| 80 |
-
| 0.3368 | 1.92 | 3000 | 4.8332 | 0.7727 |
|
| 81 |
-
| 0.3368 | 1.98 | 3100 | 4.6855 | 0.7828 |
|
| 82 |
-
| 0.3368 | 2.05 | 3200 | 4.7359 | 0.7778 |
|
| 83 |
-
| 0.3368 | 2.11 | 3300 | 4.5992 | 0.7778 |
|
| 84 |
-
| 0.3368 | 2.18 | 3400 | 4.5406 | 0.7677 |
|
| 85 |
-
| 0.2459 | 2.24 | 3500 | 4.8480 | 0.7828 |
|
| 86 |
-
| 0.2459 | 2.3 | 3600 | 4.6215 | 0.7677 |
|
| 87 |
|
| 88 |
|
| 89 |
### 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: 6.3481
|
| 19 |
+
- Accuracy: 0.7677
|
| 20 |
|
| 21 |
## Model description
|
| 22 |
|
|
|
|
| 48 |
|
| 49 |
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|
| 50 |
|:-------------:|:-----:|:----:|:---------------:|:--------:|
|
| 51 |
+
| No log | 0.06 | 100 | 14.8949 | 0.4141 |
|
| 52 |
+
| No log | 0.13 | 200 | 11.8675 | 0.4697 |
|
| 53 |
+
| No log | 0.19 | 300 | 10.6894 | 0.5556 |
|
| 54 |
+
| No log | 0.26 | 400 | 9.8194 | 0.5404 |
|
| 55 |
+
| 3.5537 | 0.32 | 500 | 9.0542 | 0.5556 |
|
| 56 |
+
| 3.5537 | 0.38 | 600 | 9.0155 | 0.6061 |
|
| 57 |
+
| 3.5537 | 0.45 | 700 | 8.1758 | 0.6768 |
|
| 58 |
+
| 3.5537 | 0.51 | 800 | 7.6983 | 0.6970 |
|
| 59 |
+
| 3.5537 | 0.58 | 900 | 7.6211 | 0.6818 |
|
| 60 |
+
| 1.0971 | 0.64 | 1000 | 7.1361 | 0.6919 |
|
| 61 |
+
| 1.0971 | 0.7 | 1100 | 7.1059 | 0.6717 |
|
| 62 |
+
| 1.0971 | 0.77 | 1200 | 6.9443 | 0.6919 |
|
| 63 |
+
| 1.0971 | 0.83 | 1300 | 6.7089 | 0.7273 |
|
| 64 |
+
| 1.0971 | 0.9 | 1400 | 6.5064 | 0.7172 |
|
| 65 |
+
| 0.699 | 0.96 | 1500 | 5.9161 | 0.7273 |
|
| 66 |
+
| 0.699 | 1.02 | 1600 | 6.6374 | 0.7525 |
|
| 67 |
+
| 0.699 | 1.09 | 1700 | 6.3481 | 0.7677 |
|
| 68 |
+
| 0.699 | 1.15 | 1800 | 5.9385 | 0.7323 |
|
| 69 |
+
| 0.699 | 1.22 | 1900 | 6.2063 | 0.7374 |
|
| 70 |
+
| 0.4733 | 1.28 | 2000 | 5.9173 | 0.7273 |
|
| 71 |
+
| 0.4733 | 1.34 | 2100 | 5.8466 | 0.7626 |
|
| 72 |
+
| 0.4733 | 1.41 | 2200 | 5.6702 | 0.7374 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 73 |
|
| 74 |
|
| 75 |
### 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 sha256:7e0aef65b647dc4c499530b1a8ae8171fac88507448aa818f7a26334a1fd967b
|
| 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,
|