Update README.md
Browse files
README.md
CHANGED
|
@@ -13,7 +13,7 @@ should probably proofread and complete it, then remove this comment. -->
|
|
| 13 |
|
| 14 |
# results
|
| 15 |
|
| 16 |
-
This model is a fine-tuned version of [google/flan-t5-base](https://huggingface.co/google/flan-t5-base) on
|
| 17 |
It achieves the following results on the evaluation set:
|
| 18 |
- Loss: 2.9379
|
| 19 |
|
|
@@ -23,14 +23,16 @@ More information needed
|
|
| 23 |
|
| 24 |
## Intended uses & limitations
|
| 25 |
|
| 26 |
-
|
| 27 |
|
| 28 |
## Training and evaluation data
|
| 29 |
|
| 30 |
-
|
| 31 |
|
| 32 |
## Training procedure
|
| 33 |
|
|
|
|
|
|
|
| 34 |
### Training hyperparameters
|
| 35 |
|
| 36 |
The following hyperparameters were used during training:
|
|
|
|
| 13 |
|
| 14 |
# results
|
| 15 |
|
| 16 |
+
This model is a fine-tuned version of [google/flan-t5-base](https://huggingface.co/google/flan-t5-base) on question/answer pairs scraped from Quora.
|
| 17 |
It achieves the following results on the evaluation set:
|
| 18 |
- Loss: 2.9379
|
| 19 |
|
|
|
|
| 23 |
|
| 24 |
## Intended uses & limitations
|
| 25 |
|
| 26 |
+
Closed book question answering
|
| 27 |
|
| 28 |
## Training and evaluation data
|
| 29 |
|
| 30 |
+
50,000 question/answer pairs scraped from Quora
|
| 31 |
|
| 32 |
## Training procedure
|
| 33 |
|
| 34 |
+
Seq2Seq training described here: https://huggingface.co/docs/evaluate/transformers_integrations
|
| 35 |
+
|
| 36 |
### Training hyperparameters
|
| 37 |
|
| 38 |
The following hyperparameters were used during training:
|