Update README.md
Browse files
README.md
CHANGED
|
@@ -29,12 +29,12 @@ should probably proofread and complete it, then remove this comment. -->
|
|
| 29 |
|
| 30 |
This model is a fine-tuned version of [google/flan-t5-xl](https://huggingface.co/google/flan-t5-xl) on the pszemraj/fleece2instructions dataset.
|
| 31 |
It achieves the following results on the evaluation set:
|
| 32 |
-
- Loss: 0.
|
| 33 |
-
- Rouge1: 65.
|
| 34 |
-
- Rouge2: 48.
|
| 35 |
-
- Rougel: 63.
|
| 36 |
-
- Rougelsum: 63.
|
| 37 |
-
- Gen Len: 13.
|
| 38 |
|
| 39 |
## Model description
|
| 40 |
|
|
@@ -42,11 +42,11 @@ More information needed
|
|
| 42 |
|
| 43 |
## Intended uses & limitations
|
| 44 |
|
| 45 |
-
|
| 46 |
|
| 47 |
## Training and evaluation data
|
| 48 |
|
| 49 |
-
|
| 50 |
|
| 51 |
## Training procedure
|
| 52 |
|
|
|
|
| 29 |
|
| 30 |
This model is a fine-tuned version of [google/flan-t5-xl](https://huggingface.co/google/flan-t5-xl) on the pszemraj/fleece2instructions dataset.
|
| 31 |
It achieves the following results on the evaluation set:
|
| 32 |
+
- Loss: 0.8314
|
| 33 |
+
- Rouge1: 65.3297
|
| 34 |
+
- Rouge2: 48.8475
|
| 35 |
+
- Rougel: 63.4183
|
| 36 |
+
- Rougelsum: 63.5458
|
| 37 |
+
- Gen Len: 13.7474
|
| 38 |
|
| 39 |
## Model description
|
| 40 |
|
|
|
|
| 42 |
|
| 43 |
## Intended uses & limitations
|
| 44 |
|
| 45 |
+
Generate/recover **instructions** (assumes that there is just an instruction, not `inputs` as well) from arbitrary text.
|
| 46 |
|
| 47 |
## Training and evaluation data
|
| 48 |
|
| 49 |
+
Refer to `pszemraj/fleece2instructions`
|
| 50 |
|
| 51 |
## Training procedure
|
| 52 |
|