Downloads · 30 days
26
2% of all-time downloads
bert-finetuned-gesture-prediction-21-classes
qfrodicio/bert-finetuned-gesture-prediction-21-classes
bert-finetuned-gesture-prediction-21-classes is a token classification model from qfrodicio. Use it when you need labels on individual words, such as names. 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
1.4K
Public
Parameters
108M
9.1 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.bin431 MB · 50%
At a glance
- Task
- Token Classification
- Library
- transformers
- License
- apache-2.0
- Model type
- bert
- Access
- Public
- Created
- Mar 7, 2023
- Updated
- May 7, 2024
- SHA
- 35071ad8
Try a prompt
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. -->
bert-finetuned-gesture-prediction-21-classes
This model is a fine-tuned version of bert-base-cased on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 1.0260
- Precision: 0.8125
- Recall: 0.8125
- F1: 0.8125
- Accuracy: 0.8022
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: 6.042200829392303e-05
- train_batch_size: 64
- eval_batch_size: 64
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 10
Training results
| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
|---|---|---|---|---|---|---|---|
| 2.2133 | 1.0 | 26 | 1.4161 | 0.7074 | 0.7074 | 0.7074 | 0.6642 |
| 1.1038 | 2.0 | 52 | 0.9797 | 0.7678 | 0.7678 | 0.7678 | 0.7521 |
| 0.6732 | 3.0 | 78 | 0.9139 | 0.7908 | 0.7908 | 0.7908 | 0.7738 |
| 0.4167 | 4.0 | 104 | 0.9106 | 0.7978 | 0.7978 | 0.7978 | 0.7826 |
| 0.2739 | 5.0 | 130 | 0.9295 | 0.8017 | 0.8017 | 0.8017 | 0.7883 |
| 0.1772 | 6.0 | 156 | 0.9294 | 0.8116 | 0.8116 | 0.8116 | 0.7989 |
| 0.1223 | 7.0 | 182 | 0.9899 | 0.8085 | 0.8085 | 0.8085 | 0.7964 |
| 0.0916 | 8.0 | 208 | 1.0156 | 0.8130 | 0.8130 | 0.8130 | 0.8012 |
| 0.0656 | 9.0 | 234 | 1.0234 | 0.8136 | 0.8136 | 0.8136 | 0.8025 |
| 0.0563 | 10.0 | 260 | 1.0260 | 0.8125 | 0.8125 | 0.8125 | 0.8022 |
Framework versions
- Transformers 4.40.1
- Pytorch 2.2.1+cu121
- Datasets 2.19.1
- Tokenizers 0.19.1
- Task
- Token Classification
- Library
- transformers
- Type
- bert
- License
- apache-2.0
- Created
- Mar 7, 2023
- Updated
- May 7, 2024