Downloads · 30 days
8
20% of all-time downloads
t5-small-finetuned-de-en-batch8
rossanez/t5-small-finetuned-de-en-batch8
t5-small-finetuned-de-en-batch8 is a machine learning model from rossanez. Use it for the machine learning task on the model card, and read the license before you ship it in a product. 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
40
Public
Repo size
727 MB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.bin242 MB · 99%
At a glance
- Library
- transformers
- License
- apache-2.0
- Model type
- t5
- Access
- Public
- Created
- Mar 2, 2022
- Updated
- Dec 4, 2021
- SHA
- 799dc17f
Datasets
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. -->
t5-small-finetuned-de-en-batch8
This model is a fine-tuned version of t5-small on the wmt14 dataset. It achieves the following results on the evaluation set:
- Loss: 2.1282
- Bleu: 10.039
- Gen Len: 17.3839
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: 0.0002
- train_batch_size: 8
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 5
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Bleu | Gen Len |
|---|---|---|---|---|---|
| No log | 1.0 | 375 | 2.0912 | 9.9147 | 17.3084 |
| 1.5593 | 2.0 | 750 | 2.0858 | 9.9386 | 17.4299 |
| 1.4383 | 3.0 | 1125 | 2.1137 | 9.9804 | 17.34 |
| 1.3562 | 4.0 | 1500 | 2.1198 | 9.9685 | 17.367 |
| 1.3562 | 5.0 | 1875 | 2.1282 | 10.039 | 17.3839 |
Framework versions
- Transformers 4.12.5
- Pytorch 1.10.0+cu111
- Datasets 1.16.1
- Tokenizers 0.10.3
- Library
- transformers
- Type
- t5
- License
- apache-2.0
- Created
- Mar 2, 2022
- Updated
- Dec 4, 2021