metadata
license: mit
base_model: Supabase/gte-small
tags:
- generated_from_trainer
metrics:
- accuracy
model-index:
- name: v_best_model
results: []
v_best_model
This model is a fine-tuned version of Supabase/gte-small on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.2700
- Accuracy: 0.9437
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: 0.0001
- 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 | Accuracy |
|---|---|---|---|---|
| 1.639 | 1.0 | 21 | 1.3351 | 0.7606 |
| 1.065 | 2.0 | 42 | 0.7793 | 0.8592 |
| 0.6055 | 3.0 | 63 | 0.5200 | 0.8873 |
| 0.3519 | 4.0 | 84 | 0.3832 | 0.9014 |
| 0.2186 | 5.0 | 105 | 0.3277 | 0.9155 |
| 0.1573 | 6.0 | 126 | 0.2844 | 0.9296 |
| 0.118 | 7.0 | 147 | 0.3185 | 0.9014 |
| 0.0948 | 8.0 | 168 | 0.2744 | 0.9437 |
| 0.0831 | 9.0 | 189 | 0.2746 | 0.9437 |
| 0.0778 | 10.0 | 210 | 0.2700 | 0.9437 |
Framework versions
- Transformers 4.36.2
- Pytorch 2.0.1+cu117
- Datasets 2.16.1
- Tokenizers 0.15.0