Update README.md
Browse files
README.md
CHANGED
|
@@ -16,13 +16,6 @@ should probably proofread and complete it, then remove this comment. -->
|
|
| 16 |
# oop-de-qag-flan-t5-base
|
| 17 |
|
| 18 |
This model is a fine-tuned version of [google/flan-t5-base](https://huggingface.co/google/flan-t5-base) on an unknown dataset.
|
| 19 |
-
It achieves the following results on the evaluation set:
|
| 20 |
-
- Loss: nan
|
| 21 |
-
- Rouge1: 1.6667
|
| 22 |
-
- Rouge2: 0.0
|
| 23 |
-
- Rougel: 1.6111
|
| 24 |
-
- Rougelsum: 1.6389
|
| 25 |
-
- Gen Len: 13.4062
|
| 26 |
|
| 27 |
## Model description
|
| 28 |
|
|
@@ -50,20 +43,6 @@ The following hyperparameters were used during training:
|
|
| 50 |
- num_epochs: 8
|
| 51 |
- mixed_precision_training: Native AMP
|
| 52 |
|
| 53 |
-
### Training results
|
| 54 |
-
|
| 55 |
-
| Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum | Gen Len |
|
| 56 |
-
|:-------------:|:-----:|:----:|:---------------:|:------:|:------:|:------:|:---------:|:-------:|
|
| 57 |
-
| No log | 1.0 | 127 | nan | 1.6667 | 0.0 | 1.6111 | 1.6389 | 13.4062 |
|
| 58 |
-
| No log | 2.0 | 254 | nan | 1.6667 | 0.0 | 1.6111 | 1.6389 | 13.4062 |
|
| 59 |
-
| No log | 3.0 | 381 | nan | 1.6667 | 0.0 | 1.6111 | 1.6389 | 13.4062 |
|
| 60 |
-
| 0.0 | 4.0 | 508 | nan | 1.6667 | 0.0 | 1.6111 | 1.6389 | 13.4062 |
|
| 61 |
-
| 0.0 | 5.0 | 635 | nan | 1.6667 | 0.0 | 1.6111 | 1.6389 | 13.4062 |
|
| 62 |
-
| 0.0 | 6.0 | 762 | nan | 1.6667 | 0.0 | 1.6111 | 1.6389 | 13.4062 |
|
| 63 |
-
| 0.0 | 7.0 | 889 | nan | 1.6667 | 0.0 | 1.6111 | 1.6389 | 13.4062 |
|
| 64 |
-
| 0.0 | 8.0 | 1016 | nan | 1.6667 | 0.0 | 1.6111 | 1.6389 | 13.4062 |
|
| 65 |
-
|
| 66 |
-
|
| 67 |
### Framework versions
|
| 68 |
|
| 69 |
- Transformers 4.35.2
|
|
|
|
| 16 |
# oop-de-qag-flan-t5-base
|
| 17 |
|
| 18 |
This model is a fine-tuned version of [google/flan-t5-base](https://huggingface.co/google/flan-t5-base) on an unknown dataset.
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 19 |
|
| 20 |
## Model description
|
| 21 |
|
|
|
|
| 43 |
- num_epochs: 8
|
| 44 |
- mixed_precision_training: Native AMP
|
| 45 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 46 |
### Framework versions
|
| 47 |
|
| 48 |
- Transformers 4.35.2
|