Create README.md
Browse files
README.md
ADDED
|
@@ -0,0 +1,41 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: cc-by-sa-4.0
|
| 3 |
+
base_model: retrieva-jp/t5-large-long
|
| 4 |
+
tags:
|
| 5 |
+
- generated_from_trainer
|
| 6 |
+
model-index:
|
| 7 |
+
- name: checkpoints
|
| 8 |
+
results: []
|
| 9 |
+
---
|
| 10 |
+
|
| 11 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 12 |
+
should probably proofread and complete it, then remove this comment. -->
|
| 13 |
+
|
| 14 |
+
# checkpoints
|
| 15 |
+
|
| 16 |
+
This model is a fine-tuned version of [retrieva-jp/t5-large-long](https://huggingface.co/retrieva-jp/t5-large-long) on the [JMultiWOZ dataset](https://github.com/nu-dialogue/jmultiwoz).
|
| 17 |
+
|
| 18 |
+
The details of this model, the dataset, and the usage are described in JMultiWOZ repository: [nu-dialogue/jmultiwoz](https://github.com/nu-dialogue/jmultiwoz)
|
| 19 |
+
|
| 20 |
+
|
| 21 |
+
### Training hyperparameters
|
| 22 |
+
|
| 23 |
+
The following hyperparameters were used during training:
|
| 24 |
+
- learning_rate: 5e-05
|
| 25 |
+
- train_batch_size: 2
|
| 26 |
+
- eval_batch_size: 2
|
| 27 |
+
- seed: 42
|
| 28 |
+
- distributed_type: multi-GPU
|
| 29 |
+
- num_devices: 16
|
| 30 |
+
- total_train_batch_size: 32
|
| 31 |
+
- total_eval_batch_size: 32
|
| 32 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 33 |
+
- lr_scheduler_type: linear
|
| 34 |
+
- num_epochs: 5.0
|
| 35 |
+
|
| 36 |
+
### Framework versions
|
| 37 |
+
|
| 38 |
+
- Transformers 4.35.0.dev0
|
| 39 |
+
- Pytorch 1.13.1+cu116
|
| 40 |
+
- Datasets 2.14.5
|
| 41 |
+
- Tokenizers 0.14.1
|