Update README.md
Browse files
README.md
CHANGED
|
@@ -1,3 +1,23 @@
|
|
| 1 |
-
|
| 2 |
-
|
| 3 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
# gpt2-medium-nlg-tm1_tm2_tm3
|
| 2 |
+
|
| 3 |
+
This model is a fine-tuned version of [GPT2-medium](https://huggingface.co/gpt2-medium) on [TaskMaster1](https://huggingface.co/datasets/ConvLab/tm1), [TaskMaster2](https://huggingface.co/datasets/ConvLab/tm2) and [TaskMaster3](https://huggingface.co/datasets/ConvLab/tm3)
|
| 4 |
+
|
| 5 |
+
Refer to [ConvLab-3](https://github.com/ConvLab/ConvLab-3) for model description and usage.
|
| 6 |
+
|
| 7 |
+
## Training procedure
|
| 8 |
+
|
| 9 |
+
### Training hyperparameters
|
| 10 |
+
|
| 11 |
+
The following hyperparameters were used during training:
|
| 12 |
+
- learning_rate: 5e-5
|
| 13 |
+
- train_batch_size: 64
|
| 14 |
+
- gradient_accumulation_steps: 2
|
| 15 |
+
- total_train_batch_size: 128
|
| 16 |
+
- optimizer: AdamW
|
| 17 |
+
- lr_scheduler_type: linear
|
| 18 |
+
- num_epochs: 20
|
| 19 |
+
|
| 20 |
+
### Framework versions
|
| 21 |
+
|
| 22 |
+
- Transformers 4.23.1
|
| 23 |
+
- Pytorch 1.10.1+cu111
|