Downloads · 30 days
7
15% of all-time downloads
roBERTuito-Meta4Types-ft-ES
alecmontero/roBERTuito-Meta4Types-ft-ES
roBERTuito-Meta4Types-ft-ES is a machine learning model from alecmontero. 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
48
Public
Parameters
109M
435 MB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors435 MB · 100%
At a glance
- Library
- transformers
- Model type
- roberta
- Access
- Public
- Created
- Aug 1, 2024
- Updated
- Aug 1, 2024
- SHA
- f3e1f38e
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. -->
roBERTuito-Meta4Types-ft-ES
This model is a fine-tuned version of pysentimiento/robertuito-sentiment-analysis on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.8547
- Roc Auc: 0.6496
- Hamming Loss: 0.1830
- F1 Score: 0.5653
- Accuracy: 0.5931
- Precision: 0.6214
- Recall: 0.5298
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: 5e-05
- train_batch_size: 4
- eval_batch_size: 4
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 500
- num_epochs: 10
Training results
| Training Loss | Epoch | Step | Validation Loss | Roc Auc | Hamming Loss | F1 Score | Accuracy | Precision | Recall |
|---|---|---|---|---|---|---|---|---|---|
| No log | 1.0 | 204 | 0.5044 | 0.5 | 0.2026 | 0.2930 | 0.6176 | 0.9281 | 0.3333 |
| No log | 2.0 | 408 | 0.4634 | 0.5717 | 0.1961 | 0.4829 | 0.6225 | 0.5819 | 0.4651 |
| 0.4697 | 3.0 | 612 | 0.4784 | 0.6173 | 0.1748 | 0.4993 | 0.6275 | 0.8438 | 0.4596 |
| 0.4697 | 4.0 | 816 | 0.6585 | 0.6129 | 0.2124 | 0.5351 | 0.5539 | 0.5456 | 0.5279 |
| 0.1464 | 5.0 | 1020 | 0.8070 | 0.5891 | 0.2010 | 0.4963 | 0.6078 | 0.5732 | 0.4703 |
| 0.1464 | 6.0 | 1224 | 0.7848 | 0.6094 | 0.1912 | 0.5294 | 0.5735 | 0.5916 | 0.4989 |
| 0.1464 | 7.0 | 1428 | 0.8547 | 0.6496 | 0.1830 | 0.5653 | 0.5931 | 0.6214 | 0.5298 |
| 0.0278 | 8.0 | 1632 | 0.9068 | 0.6152 | 0.1846 | 0.5396 | 0.5784 | 0.6114 | 0.5064 |
| 0.0278 | 9.0 | 1836 | 0.9251 | 0.6110 | 0.1961 | 0.5258 | 0.5588 | 0.5674 | 0.5023 |
| 0.0029 | 10.0 | 2040 | 0.9343 | 0.6146 | 0.1944 | 0.5276 | 0.5686 | 0.5751 | 0.5002 |
Framework versions
- Transformers 4.43.3
- Pytorch 2.3.1+cu121
- Datasets 2.20.0
- Tokenizers 0.19.1
- Library
- transformers
- Type
- roberta
- Created
- Aug 1, 2024
- Updated
- Aug 1, 2024