metadata
license: apache-2.0
base_model: distilbert-base-cased
tags:
- generated_from_trainer
metrics:
- precision
- recall
- f1
- accuracy
model-index:
- name: distilbert-finetuned-gesture-prediction-21-classes
results: []
distilbert-finetuned-gesture-prediction-21-classes
This model is a fine-tuned version of distilbert-base-cased on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 1.0324
- Precision: 0.8139
- Recall: 0.8139
- F1: 0.8139
- 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: 9.96098704459956e-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 |
|---|---|---|---|---|---|---|---|
| 2.1035 | 1.0 | 26 | 1.2829 | 0.7042 | 0.7042 | 0.7042 | 0.6806 |
| 0.9959 | 2.0 | 52 | 0.9482 | 0.7756 | 0.7756 | 0.7756 | 0.7621 |
| 0.6164 | 3.0 | 78 | 0.8716 | 0.7849 | 0.7849 | 0.7849 | 0.7685 |
| 0.3812 | 4.0 | 104 | 0.8710 | 0.8004 | 0.8004 | 0.8004 | 0.7867 |
| 0.2325 | 5.0 | 130 | 0.9558 | 0.7916 | 0.7916 | 0.7916 | 0.7788 |
| 0.1558 | 6.0 | 156 | 0.9310 | 0.8077 | 0.8077 | 0.8077 | 0.7949 |
| 0.0983 | 7.0 | 182 | 0.9989 | 0.8121 | 0.8121 | 0.8121 | 0.7992 |
| 0.0697 | 8.0 | 208 | 1.0241 | 0.8083 | 0.8083 | 0.8083 | 0.7963 |
| 0.05 | 9.0 | 234 | 1.0352 | 0.8110 | 0.8110 | 0.8110 | 0.7991 |
| 0.0403 | 10.0 | 260 | 1.0324 | 0.8139 | 0.8139 | 0.8139 | 0.8022 |
Framework versions
- Transformers 4.40.1
- Pytorch 2.2.1+cu121
- Datasets 2.19.1
- Tokenizers 0.19.1