metadata
license: mit
base_model: thenlper/gte-large
tags:
- generated_from_trainer
metrics:
- accuracy
model-index:
- name: checkpoint
results: []
checkpoint
This model is a fine-tuned version of thenlper/gte-large on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.1728
- Accuracy: 0.9545
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: 128
- eval_batch_size: 128
- 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 |
|---|---|---|---|---|
| 1.4496 | 1.0 | 11 | 0.8490 | 0.8 |
| 0.6028 | 2.0 | 22 | 0.3205 | 0.8909 |
| 0.183 | 3.0 | 33 | 0.2986 | 0.9273 |
| 0.0749 | 4.0 | 44 | 0.2600 | 0.9455 |
| 0.039 | 5.0 | 55 | 0.1932 | 0.9636 |
| 0.0208 | 6.0 | 66 | 0.1570 | 0.9636 |
| 0.0147 | 7.0 | 77 | 0.2016 | 0.9545 |
| 0.0119 | 8.0 | 88 | 0.1818 | 0.9545 |
| 0.0059 | 9.0 | 99 | 0.1700 | 0.9545 |
| 0.0048 | 10.0 | 110 | 0.1728 | 0.9545 |
Framework versions
- Transformers 4.39.3
- Pytorch 2.2.2+cu121
- Datasets 2.19.1
- Tokenizers 0.15.2