Downloads · 30 days
7
9% of all-time downloads
my_translator
jsphelps12/my_translator
my_translator is a machine learning model from jsphelps12. 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
79
Public
Parameters
60.5M
13.8 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors242 MB · 99%
At a glance
- Library
- transformers
- License
- apache-2.0
- Model type
- t5
- Access
- Public
- Created
- Apr 15, 2024
- Updated
- Apr 16, 2024
- SHA
- 00b04d37
Base models
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. -->
my_translator
This model is a fine-tuned version of google-t5/t5-small on the generator dataset. It achieves the following results on the evaluation set:
- Loss: 1.3036
- Bleu: 20.6458
- Gen Len: 18.52
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: 16
- eval_batch_size: 16
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 15
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Bleu | Gen Len |
|---|---|---|---|---|---|
| 1.5155 | 1.0 | 1556 | 1.3228 | 17.8685 | 18.5208 |
| 1.2945 | 2.0 | 3112 | 1.2303 | 18.5903 | 18.5401 |
| 1.1669 | 3.0 | 4668 | 1.2021 | 19.0779 | 18.5258 |
| 1.0522 | 4.0 | 6224 | 1.1794 | 19.41 | 18.5329 |
| 0.9606 | 5.0 | 7780 | 1.1635 | 19.6192 | 18.5289 |
| 0.8903 | 6.0 | 9336 | 1.1702 | 19.894 | 18.515 |
| 0.8152 | 7.0 | 10892 | 1.1734 | 19.9585 | 18.5129 |
| 0.7499 | 8.0 | 12448 | 1.1959 | 20.1959 | 18.5369 |
| 0.7078 | 9.0 | 14004 | 1.2016 | 20.1621 | 18.5272 |
| 0.6623 | 10.0 | 15560 | 1.2251 | 20.2858 | 18.515 |
| 0.6114 | 11.0 | 17116 | 1.2415 | 20.4039 | 18.5227 |
| 0.5742 | 12.0 | 18672 | 1.2607 | 20.5759 | 18.5248 |
| 0.5333 | 13.0 | 20228 | 1.2762 | 20.5848 | 18.5142 |
| 0.5134 | 14.0 | 21784 | 1.2900 | 20.5416 | 18.517 |
| 0.4932 | 15.0 | 23340 | 1.3036 | 20.6458 | 18.52 |
Framework versions
- Transformers 4.38.2
- Pytorch 2.2.1+cu121
- Datasets 2.18.0
- Tokenizers 0.15.2
- Library
- transformers
- Type
- t5
- License
- apache-2.0
- Created
- Apr 15, 2024
- Updated
- Apr 16, 2024