Update README.md
Browse files
README.md
CHANGED
|
@@ -4,7 +4,7 @@ base_model: google/flan-t5-base
|
|
| 4 |
tags:
|
| 5 |
- generated_from_trainer
|
| 6 |
datasets:
|
| 7 |
-
- tldr
|
| 8 |
metrics:
|
| 9 |
- rouge
|
| 10 |
model-index:
|
|
@@ -30,7 +30,7 @@ should probably proofread and complete it, then remove this comment. -->
|
|
| 30 |
|
| 31 |
# BASH-Coder-Flan-T5-base
|
| 32 |
|
| 33 |
-
This model is a fine-tuned version of [google/flan-t5-base](https://huggingface.co/google/flan-t5-base) on the tldr dataset.
|
| 34 |
It achieves the following results on the evaluation set:
|
| 35 |
- Loss: 3.3608
|
| 36 |
- Rouge1: 27.0741
|
|
@@ -88,3 +88,8 @@ The following hyperparameters were used during training:
|
|
| 88 |
- Pytorch 2.1.0+cu121
|
| 89 |
- Datasets 2.15.0
|
| 90 |
- Tokenizers 0.15.0
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 4 |
tags:
|
| 5 |
- generated_from_trainer
|
| 6 |
datasets:
|
| 7 |
+
- neulab/tldr
|
| 8 |
metrics:
|
| 9 |
- rouge
|
| 10 |
model-index:
|
|
|
|
| 30 |
|
| 31 |
# BASH-Coder-Flan-T5-base
|
| 32 |
|
| 33 |
+
This model is a fine-tuned version of [google/flan-t5-base](https://huggingface.co/google/flan-t5-base) on the [neulab/tldr](https://huggingface.co/datasets/neulab/tldr) dataset.
|
| 34 |
It achieves the following results on the evaluation set:
|
| 35 |
- Loss: 3.3608
|
| 36 |
- Rouge1: 27.0741
|
|
|
|
| 88 |
- Pytorch 2.1.0+cu121
|
| 89 |
- Datasets 2.15.0
|
| 90 |
- Tokenizers 0.15.0
|
| 91 |
+
|
| 92 |
+
|
| 93 |
+
## Finr-tuning Script
|
| 94 |
+
|
| 95 |
+
[Google Colaboratory Notebook](https://colab.research.google.com/drive/1VMSVa49xn6O-P6CGNd5AOSoGkPV8D2F_?usp=sharing)
|