Downloads · 30 days
21
28% of all-time downloads
Nahuatl_Espanol_vn
Vichentito/Nahuatl_Espanol_vn
Nahuatl_Espanol_vn is a machine learning model from Vichentito. 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.
should probably proofread and complete it, then remove this comment. --
All-time downloads
74
Public
Parameters
248M
27.7 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors990 MB · 100%
At a glance
- Library
- transformers
- Model type
- t5
- Access
- Public
- Created
- May 14, 2024
- Updated
- May 28, 2024
- SHA
- c4f164b8
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. -->
Nahuatl_Espanol_vn
This model was trained from scratch on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 1.1464
- Bleu: 15.4218
- Gen Len: 45.5239
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: 0.0003
- train_batch_size: 32
- eval_batch_size: 32
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 3
Training results
| Training Loss | Epoch | Step | Validation Loss | Bleu | Gen Len |
|---|---|---|---|---|---|
| No log | 0.1064 | 100 | 1.1525 | 14.738 | 46.3599 |
| No log | 0.2128 | 200 | 1.1682 | 14.2823 | 45.9297 |
| No log | 0.3191 | 300 | 1.1739 | 14.2118 | 46.4243 |
| No log | 0.4255 | 400 | 1.1799 | 14.3198 | 45.9266 |
| 1.3984 | 0.5319 | 500 | 1.1771 | 14.0972 | 46.2179 |
| 1.3984 | 0.6383 | 600 | 1.1752 | 14.4083 | 45.8709 |
| 1.3984 | 0.7447 | 700 | 1.1756 | 14.1914 | 46.0949 |
| 1.3984 | 0.8511 | 800 | 1.1761 | 14.4131 | 46.0528 |
| 1.3984 | 0.9574 | 900 | 1.1727 | 14.1957 | 46.4856 |
| 1.3826 | 1.0638 | 1000 | 1.1768 | 14.7451 | 45.7873 |
| 1.3826 | 1.1702 | 1100 | 1.1727 | 14.6016 | 45.8654 |
| 1.3826 | 1.2766 | 1200 | 1.1726 | 14.6549 | 45.6857 |
| 1.3826 | 1.3830 | 1300 | 1.1693 | 14.586 | 45.6052 |
| 1.3826 | 1.4894 | 1400 | 1.1704 | 14.6483 | 45.6039 |
| 1.2932 | 1.5957 | 1500 | 1.1638 | 14.921 | 45.5508 |
| 1.2932 | 1.7021 | 1600 | 1.1649 | 14.7977 | 45.3693 |
| 1.2932 | 1.8085 | 1700 | 1.1580 | 14.9676 | 45.7072 |
| 1.2932 | 1.9149 | 1800 | 1.1567 | 14.794 | 45.5877 |
| 1.2932 | 2.0213 | 1900 | 1.1607 | 15.3066 | 45.677 |
| 1.2612 | 2.1277 | 2000 | 1.1569 | 15.1152 | 45.4122 |
| 1.2612 | 2.2340 | 2100 | 1.1553 | 15.2526 | 45.4026 |
| 1.2612 | 2.3404 | 2200 | 1.1521 | 15.2022 | 45.3518 |
| 1.2612 | 2.4468 | 2300 | 1.1505 | 15.3072 | 45.5873 |
| 1.2612 | 2.5532 | 2400 | 1.1500 | 15.417 | 45.5906 |
| 1.2095 | 2.6596 | 2500 | 1.1507 | 15.394 | 45.4383 |
| 1.2095 | 2.7660 | 2600 | 1.1501 | 15.4171 | 45.4846 |
| 1.2095 | 2.8723 | 2700 | 1.1472 | 15.4497 | 45.5049 |
| 1.2095 | 2.9787 | 2800 | 1.1464 | 15.4218 | 45.5239 |
Framework versions
- Transformers 4.41.0
- Pytorch 2.3.0+cu121
- Datasets 2.19.1
- Tokenizers 0.19.1
- Library
- transformers
- Type
- t5
- Created
- May 14, 2024
- Updated
- May 28, 2024