Downloads · 30 days
44
5% of all-time downloads
beto-sentiment-analysis-finetuned
stinoco/beto-sentiment-analysis-finetuned
beto-sentiment-analysis-finetuned is a text classification model from stinoco. Use it when you need a label for a piece of text. It is set up for transformers.
should probably proofread and complete it, then remove this comment. --
All-time downloads
808
Public
Repo size
13.2 GB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.bin440 MB · 100%
At a glance
- Task
- Text Classification
- Library
- transformers
- Model type
- bert
- Access
- Public
- Created
- Jan 2, 2023
- Updated
- Jan 26, 2023
- SHA
- 0736a354
Try a prompt
Spaces
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. -->
beto-sentiment-analysis-finetuned
This model is a fine-tuned version of finiteautomata/beto-sentiment-analysis on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 1.4406
- Accuracy: 0.7757
- F1: 0.7773
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: 1e-05
- train_batch_size: 32
- eval_batch_size: 32
- seed: 3380
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 35
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 |
|---|---|---|---|---|---|
| 2.5384 | 1.45 | 100 | 2.1387 | 0.2831 | 0.3049 |
| 2.1562 | 2.9 | 200 | 1.6375 | 0.4596 | 0.4873 |
| 1.5805 | 4.35 | 300 | 1.4332 | 0.5993 | 0.6377 |
| 1.4242 | 5.8 | 400 | 1.3355 | 0.6544 | 0.6565 |
| 1.1192 | 7.25 | 500 | 1.2845 | 0.6765 | 0.6854 |
| 0.9617 | 8.7 | 600 | 1.1512 | 0.6912 | 0.7167 |
| 0.829 | 10.14 | 700 | 1.0676 | 0.6801 | 0.7079 |
| 0.6889 | 11.59 | 800 | 1.0715 | 0.7022 | 0.7323 |
| 0.59 | 13.04 | 900 | 1.1065 | 0.7316 | 0.7392 |
| 0.5129 | 14.49 | 1000 | 1.1585 | 0.7059 | 0.7382 |
| 0.4278 | 15.94 | 1100 | 1.1106 | 0.75 | 0.7582 |
| 0.3728 | 17.39 | 1200 | 1.1561 | 0.7537 | 0.7679 |
| 0.3142 | 18.84 | 1300 | 1.1755 | 0.7537 | 0.7667 |
| 0.275 | 20.29 | 1400 | 1.2095 | 0.7574 | 0.7707 |
| 0.2251 | 21.74 | 1500 | 1.3647 | 0.7574 | 0.7674 |
| 0.2175 | 23.19 | 1600 | 1.3127 | 0.7537 | 0.7635 |
| 0.1923 | 24.64 | 1700 | 1.3494 | 0.7794 | 0.7760 |
| 0.1753 | 26.09 | 1800 | 1.4221 | 0.7684 | 0.7658 |
| 0.1484 | 27.54 | 1900 | 1.3572 | 0.7684 | 0.7727 |
| 0.1455 | 28.99 | 2000 | 1.4063 | 0.7757 | 0.7747 |
| 0.131 | 30.43 | 2100 | 1.3754 | 0.7721 | 0.7730 |
| 0.1125 | 31.88 | 2200 | 1.4302 | 0.7757 | 0.7740 |
| 0.1203 | 33.33 | 2300 | 1.4146 | 0.7684 | 0.7714 |
| 0.1083 | 34.78 | 2400 | 1.4406 | 0.7757 | 0.7773 |
Framework versions
- Transformers 4.26.0
- Pytorch 1.13.1+cu116
- Datasets 2.8.0
- Tokenizers 0.13.2
- Task
- Text Classification
- Library
- transformers
- Type
- bert
- Created
- Jan 2, 2023
- Updated
- Jan 26, 2023