Downloads · 30 days
7
0% of all-time downloads
long-ke-t5-base-translation-aihub-bidirection_e1
KETI-AIR-Downstream/long-ke-t5-base-translation-aihub-bidirection_e1
long-ke-t5-base-translation-aihub-bidirection_e1 is a translation model from KETI-AIR-Downstream. Use it when you need text moved from one language to another. It is set up for transformers. The card lists the license as apache-2.0.
should probably proofread and complete it, then remove this comment. --
All-time downloads
2.7K
Public
Parameters
297M
2.4 GB on disk
Likes
1
Public
Repo makeup
Click a slice to open those files.
.bin1.2 GB · 50%
At a glance
- Task
- Translation
- Library
- transformers
- License
- apache-2.0
- Model type
- longt5
- Access
- Public
- Created
- Jul 3, 2023
- Updated
- Sep 18, 2023
- SHA
- 8f6ad791
Try a prompt
Base models
Model card
From the Hugging Face model README
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->
ko2en_bidirection
This model is a fine-tuned version of KETI-AIR/long-ke-t5-base on the csv_dataset.py dataset. It achieves the following results on the evaluation set:
- Loss: 0.6808
- Bleu: 52.2152
- Gen Len: 396.0215
Model description
More information needed
Intended uses & limitations
More information needed
Training and evaluation data
More information needed
Training procedure
Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 0.001
- train_batch_size: 8
- eval_batch_size: 4
- seed: 42
- distributed_type: multi-GPU
- num_devices: 8
- total_train_batch_size: 64
- total_eval_batch_size: 32
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 1.0
Training results
| Training Loss | Epoch | Step | Validation Loss | Bleu | Gen Len |
|---|---|---|---|---|---|
| 0.5962 | 1.0 | 750093 | 0.6808 | 0.0 | 18.369 |
Framework versions
- Transformers 4.28.1
- Pytorch 1.13.0
- Datasets 2.9.0
- Tokenizers 0.13.2
- Task
- Translation
- Library
- transformers
- Type
- longt5
- License
- apache-2.0
- Languages
- ko, en
- Created
- Jul 3, 2023
- Updated
- Sep 18, 2023