peft-finetune-flan-t5-mc-question-generation
Browse files- README.md +17 -17
- adapter_model.bin +1 -1
README.md
CHANGED
@@ -15,7 +15,7 @@ should probably proofread and complete it, then remove this comment. -->
|
|
15 |
|
16 |
This model is a fine-tuned version of [google/flan-t5-base](https://huggingface.co/google/flan-t5-base) on the None dataset.
|
17 |
It achieves the following results on the evaluation set:
|
18 |
-
- Loss: 1.
|
19 |
|
20 |
## Model description
|
21 |
|
@@ -48,26 +48,26 @@ The following hyperparameters were used during training:
|
|
48 |
|
49 |
| Training Loss | Epoch | Step | Validation Loss |
|
50 |
|:-------------:|:-----:|:----:|:---------------:|
|
51 |
-
| 2.
|
52 |
-
| 1.
|
53 |
-
| 1.
|
54 |
-
| 1.
|
55 |
-
| 1.
|
56 |
-
| 1.
|
57 |
-
| 1.
|
58 |
-
| 1.
|
59 |
-
| 1.
|
60 |
-
| 1.
|
61 |
-
| 1.
|
62 |
-
| 1.
|
63 |
-
| 1.
|
64 |
-
| 1.
|
65 |
-
| 1.
|
66 |
|
67 |
|
68 |
### Framework versions
|
69 |
|
70 |
-
- Transformers 4.
|
71 |
- Pytorch 2.0.0
|
72 |
- Datasets 2.1.0
|
73 |
- Tokenizers 0.13.3
|
|
|
15 |
|
16 |
This model is a fine-tuned version of [google/flan-t5-base](https://huggingface.co/google/flan-t5-base) on the None dataset.
|
17 |
It achieves the following results on the evaluation set:
|
18 |
+
- Loss: 1.1553
|
19 |
|
20 |
## Model description
|
21 |
|
|
|
48 |
|
49 |
| Training Loss | Epoch | Step | Validation Loss |
|
50 |
|:-------------:|:-----:|:----:|:---------------:|
|
51 |
+
| 2.2947 | 0.13 | 100 | 1.7430 |
|
52 |
+
| 1.8174 | 0.25 | 200 | 1.3561 |
|
53 |
+
| 1.5218 | 0.38 | 300 | 1.2409 |
|
54 |
+
| 1.4277 | 0.51 | 400 | 1.2068 |
|
55 |
+
| 1.3855 | 0.64 | 500 | 1.1918 |
|
56 |
+
| 1.3648 | 0.76 | 600 | 1.1808 |
|
57 |
+
| 1.3438 | 0.89 | 700 | 1.1744 |
|
58 |
+
| 1.3408 | 1.02 | 800 | 1.1685 |
|
59 |
+
| 1.3357 | 1.15 | 900 | 1.1658 |
|
60 |
+
| 1.3258 | 1.27 | 1000 | 1.1620 |
|
61 |
+
| 1.3187 | 1.4 | 1100 | 1.1597 |
|
62 |
+
| 1.3195 | 1.53 | 1200 | 1.1577 |
|
63 |
+
| 1.3168 | 1.65 | 1300 | 1.1572 |
|
64 |
+
| 1.3167 | 1.78 | 1400 | 1.1559 |
|
65 |
+
| 1.311 | 1.91 | 1500 | 1.1553 |
|
66 |
|
67 |
|
68 |
### Framework versions
|
69 |
|
70 |
+
- Transformers 4.32.0
|
71 |
- Pytorch 2.0.0
|
72 |
- Datasets 2.1.0
|
73 |
- Tokenizers 0.13.3
|
adapter_model.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 3591693
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:39fdf60e531abfa9fd2b5cb191ee9faf4db89b4744ee963231286d9e40b92d9c
|
3 |
size 3591693
|