metadata
license: mit
base_model: BAAI/bge-small-zh-v1.5
tags:
- generated_from_trainer
metrics:
- accuracy
model-index:
- name: sft-bge-bert24m-to-sentiment
results: []
sft-bge-bert24m-to-sentiment
This model is a fine-tuned version of BAAI/bge-small-zh-v1.5 on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.5564
- Accuracy: 0.7853
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: 2e-05
- train_batch_size: 32
- eval_batch_size: 32
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 5
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 0.5355 | 1.0 | 3750 | 0.5576 | 0.7633 |
| 0.4901 | 2.0 | 7500 | 0.5481 | 0.779 |
| 0.4494 | 3.0 | 11250 | 0.5340 | 0.7793 |
| 0.4305 | 4.0 | 15000 | 0.5467 | 0.7797 |
| 0.3995 | 5.0 | 18750 | 0.5564 | 0.7853 |
Framework versions
- Transformers 4.37.2
- Pytorch 2.2.0+cu121
- Datasets 2.17.1
- Tokenizers 0.15.2