Downloads · 30 days
7
10% of all-time downloads
amh_to_en_model_finetuned
rosswong/amh_to_en_model_finetuned
amh_to_en_model_finetuned is a machine learning model from rosswong. 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
71
Public
Parameters
60.5M
5.6 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
- May 23, 2025
- Updated
- May 23, 2025
- SHA
- 0c1fb94a
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. -->
amh_to_en_model_finetuned
This model is a fine-tuned version of google-t5/t5-small on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 3.9481
- Bleu: 0.9829
- Gen Len: 18.4021
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: 2e-05
- train_batch_size: 16
- eval_batch_size: 16
- seed: 42
- optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: linear
- num_epochs: 30
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Bleu | Gen Len |
|---|---|---|---|---|---|
| No log | 1.0 | 97 | 4.2425 | 0.0 | 19.5232 |
| No log | 2.0 | 194 | 4.1644 | 0.0 | 19.4433 |
| No log | 3.0 | 291 | 4.1195 | 0.5019 | 19.232 |
| No log | 4.0 | 388 | 4.0928 | 0.6266 | 18.6237 |
| No log | 5.0 | 485 | 4.0720 | 0.6519 | 18.8737 |
| 4.3077 | 6.0 | 582 | 4.0554 | 0.7604 | 18.8273 |
| 4.3077 | 7.0 | 679 | 4.0409 | 0.8165 | 18.701 |
| 4.3077 | 8.0 | 776 | 4.0280 | 0.8108 | 18.7191 |
| 4.3077 | 9.0 | 873 | 4.0162 | 0.8278 | 18.6366 |
| 4.3077 | 10.0 | 970 | 4.0091 | 0.892 | 18.6392 |
| 4.1156 | 11.0 | 1067 | 4.0007 | 0.9591 | 18.6031 |
| 4.1156 | 12.0 | 1164 | 3.9937 | 0.9774 | 18.7062 |
| 4.1156 | 13.0 | 1261 | 3.9876 | 0.9587 | 18.7036 |
| 4.1156 | 14.0 | 1358 | 3.9812 | 0.9192 | 18.6881 |
| 4.1156 | 15.0 | 1455 | 3.9767 | 0.9736 | 18.7036 |
| 4.0333 | 16.0 | 1552 | 3.9717 | 0.9359 | 18.732 |
| 4.0333 | 17.0 | 1649 | 3.9704 | 0.9184 | 18.7371 |
| 4.0333 | 18.0 | 1746 | 3.9656 | 0.9619 | 18.7062 |
| 4.0333 | 19.0 | 1843 | 3.9632 | 0.9558 | 18.7706 |
| 4.0333 | 20.0 | 1940 | 3.9602 | 0.9774 | 18.701 |
| 3.9874 | 21.0 | 2037 | 3.9588 | 0.9746 | 18.7191 |
| 3.9874 | 22.0 | 2134 | 3.9566 | 0.971 | 18.7216 |
| 3.9874 | 23.0 | 2231 | 3.9544 | 1.0137 | 18.7268 |
| 3.9874 | 24.0 | 2328 | 3.9525 | 1.0202 | 18.567 |
| 3.9874 | 25.0 | 2425 | 3.9507 | 1.0161 | 18.5129 |
| 3.9628 | 26.0 | 2522 | 3.9494 | 1.0158 | 18.3557 |
| 3.9628 | 27.0 | 2619 | 3.9487 | 1.0253 | 18.4381 |
| 3.9628 | 28.0 | 2716 | 3.9485 | 1.0209 | 18.2938 |
| 3.9628 | 29.0 | 2813 | 3.9482 | 1.0123 | 18.2938 |
| 3.9628 | 30.0 | 2910 | 3.9481 | 0.9829 | 18.4021 |
Framework versions
- Transformers 4.51.3
- Pytorch 2.6.0+cu124
- Datasets 3.6.0
- Tokenizers 0.21.1
- Library
- transformers
- Type
- t5
- License
- apache-2.0
- Created
- May 23, 2025
- Updated
- May 23, 2025