Downloads · 30 days
6
3% of all-time downloads
esp-to-lsm-barto-model
vania2911/esp-to-lsm-barto-model
esp-to-lsm-barto-model is a machine learning model from vania2911. Use it for the machine learning task on the model card, and read the license before you ship it in a product. The card lists the license as apache-2.0.
should probably proofread and complete it, then remove this comment. --
All-time downloads
198
Public
Repo size
15.6 GB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.bin558 MB · 99%
At a glance
- License
- apache-2.0
- Model type
- bart
- Access
- Public
- Created
- Oct 24, 2024
- Updated
- Jun 25, 2025
- SHA
- 38084bd5
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. -->
esp-to-lsm-barto-model
This model is a fine-tuned version of vgaraujov/bart-base-spanish on Spanish to Mexican Sign Language glosses. It achieves the following results on the evaluation set:
- Loss: 0.0119
- Bleu: 83.6834
- Rouge: {'rouge1': 0.9460428088566635, 'rouge2': 0.882022510713687, 'rougeL': 0.943717327148829, 'rougeLsum': 0.9444284172999342}
- Ter: 9.1078
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: 1.5e-05
- 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: 20
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Bleu | Rouge | Ter |
|---|---|---|---|---|---|---|
| 0.1801 | 1.0 | 75 | 0.0539 | 29.7114 | {'rouge1': 0.7345039307098129, 'rouge2': 0.5117211122211125, 'rougeL': 0.6920450246920837, 'rougeLsum': 0.6917017405252704} | 48.6989 |
| 0.0371 | 2.0 | 150 | 0.0243 | 68.6531 | {'rouge1': 0.8650428833149424, 'rouge2': 0.7422672235172237, 'rougeL': 0.8558077203297794, 'rougeLsum': 0.8557997277776692} | 18.8662 |
| 0.0238 | 3.0 | 225 | 0.0181 | 73.9024 | {'rouge1': 0.9076046423619955, 'rouge2': 0.8112917314167318, 'rougeL': 0.9029955371425962, 'rougeLsum': 0.9032938360658951} | 13.9405 |
| 0.0179 | 4.0 | 300 | 0.0160 | 76.6146 | {'rouge1': 0.9205966876260996, 'rouge2': 0.8325669053169056, 'rougeL': 0.9148529626691393, 'rougeLsum': 0.9153342229665762} | 13.3829 |
| 0.0129 | 5.0 | 375 | 0.0156 | 78.3396 | {'rouge1': 0.929181029210441, 'rouge2': 0.8567184667184671, 'rougeL': 0.9250333914451565, 'rougeLsum': 0.9248940386955096} | 11.7100 |
| 0.0123 | 6.0 | 450 | 0.0137 | 79.0461 | {'rouge1': 0.9284243662111307, 'rouge2': 0.8598646446146447, 'rougeL': 0.9243404177521828, 'rougeLsum': 0.9244574099647634} | 11.6171 |
| 0.0111 | 7.0 | 525 | 0.0132 | 82.3284 | {'rouge1': 0.9416226110490817, 'rouge2': 0.8737761220261224, 'rougeL': 0.9374446528417115, 'rougeLsum': 0.9382127507568687} | 10.1301 |
| 0.0095 | 8.0 | 600 | 0.0133 | 81.2724 | {'rouge1': 0.9374726357520476, 'rouge2': 0.8655512543012546, 'rougeL': 0.9330040732687792, 'rougeLsum': 0.9330111326581916} | 10.4089 |
| 0.0083 | 9.0 | 675 | 0.0125 | 80.9377 | {'rouge1': 0.9409313461592872, 'rouge2': 0.8717704980204982, 'rougeL': 0.9359087377763852, 'rougeLsum': 0.9363485895912368} | 10.1301 |
| 0.0083 | 10.0 | 750 | 0.0125 | 81.2165 | {'rouge1': 0.9380090622884738, 'rouge2': 0.866998140748141, 'rougeL': 0.9336646751940871, 'rougeLsum': 0.9341928028398617} | 10.3160 |
| 0.007 | 11.0 | 825 | 0.0123 | 82.2914 | {'rouge1': 0.9462954802049229, 'rouge2': 0.8791352737676269, 'rougeL': 0.9424912837706958, 'rougeLsum': 0.9428021973439931} | 9.4796 |
| 0.0073 | 12.0 | 900 | 0.0125 | 82.1390 | {'rouge1': 0.9430502719817737, 'rouge2': 0.873168741933448, 'rougeL': 0.9384727836090067, 'rougeLsum': 0.9391153484744819} | 9.7584 |
| 0.0077 | 13.0 | 975 | 0.0121 | 81.5111 | {'rouge1': 0.9433854187751248, 'rouge2': 0.8734352591852592, 'rougeL': 0.9382403832550894, 'rougeLsum': 0.9391199941126414} | 9.8513 |
| 0.0069 | 14.0 | 1050 | 0.0120 | 81.7991 | {'rouge1': 0.9413324633313025, 'rouge2': 0.8663211804535336, 'rougeL': 0.9377540444734718, 'rougeLsum': 0.9381450086291419} | 9.9442 |
| 0.0061 | 15.0 | 1125 | 0.0117 | 83.2649 | {'rouge1': 0.9455139253448078, 'rouge2': 0.8779724719724722, 'rougeL': 0.9423062373356493, 'rougeLsum': 0.9430993151728446} | 9.1078 |
| 0.0059 | 16.0 | 1200 | 0.0121 | 82.6313 | {'rouge1': 0.9444912304900699, 'rouge2': 0.874740174313704, 'rougeL': 0.9399545093565994, 'rougeLsum': 0.9407451758910739} | 9.6654 |
| 0.0054 | 17.0 | 1275 | 0.0118 | 83.1501 | {'rouge1': 0.9443079410126627, 'rouge2': 0.8739764657999955, 'rougeL': 0.9406166388937288, 'rougeLsum': 0.941211772561231} | 9.4796 |
| 0.006 | 18.0 | 1350 | 0.0119 | 83.5599 | {'rouge1': 0.9444137594431712, 'rouge2': 0.8779277574277575, 'rougeL': 0.9421305419296906, 'rougeLsum': 0.9425740897103128} | 9.2937 |
| 0.0057 | 19.0 | 1425 | 0.0118 | 83.4843 | {'rouge1': 0.9465982741315557, 'rouge2': 0.8811424501424505, 'rougeL': 0.9436887519228851, 'rougeLsum': 0.9443445977540404} | 9.1078 |
| 0.0069 | 20.0 | 1500 | 0.0119 | 83.6834 | {'rouge1': 0.9460428088566635, 'rouge2': 0.882022510713687, 'rougeL': 0.943717327148829, 'rougeLsum': 0.9444284172999342} | 9.1078 |
Framework versions
- Transformers 4.26.1
- Pytorch 2.5.0+cu121
- Datasets 3.0.2
- Tokenizers 0.13.3
- Type
- bart
- License
- apache-2.0
- Created
- Oct 24, 2024
- Updated
- Jun 25, 2025