|
--- |
|
license: apache-2.0 |
|
base_model: Qwen/Qwen2-0.5B |
|
tags: |
|
- generated_from_trainer |
|
metrics: |
|
- accuracy |
|
model-index: |
|
- name: llm2vec-Qwen2-0.5B-shopping-Quar-v2 |
|
results: [] |
|
--- |
|
|
|
<!-- 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. --> |
|
|
|
# llm2vec-Qwen2-0.5B-shopping-Quar-v2 |
|
|
|
This model is a fine-tuned version of [Qwen/Qwen2-0.5B](https://huggingface.co/Qwen/Qwen2-0.5B) on an unknown dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 3.1151 |
|
- Accuracy: 0.4539 |
|
|
|
## 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: 5e-05 |
|
- train_batch_size: 4 |
|
- eval_batch_size: 4 |
|
- seed: 42 |
|
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
|
- lr_scheduler_type: linear |
|
- num_epochs: 1 |
|
- mixed_precision_training: Native AMP |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | Accuracy | |
|
|:-------------:|:------:|:-----:|:---------------:|:--------:| |
|
| 3.4292 | 0.0510 | 1000 | 3.3647 | 0.4207 | |
|
| 3.3217 | 0.1019 | 2000 | 3.2997 | 0.4283 | |
|
| 3.274 | 0.1529 | 3000 | 3.2483 | 0.4345 | |
|
| 3.2467 | 0.2038 | 4000 | 3.1933 | 0.4407 | |
|
| 3.2093 | 0.2548 | 5000 | 3.1931 | 0.4439 | |
|
| 3.1807 | 0.3057 | 6000 | 3.1661 | 0.4476 | |
|
| 3.1978 | 0.3567 | 7000 | 3.1433 | 0.4486 | |
|
| 3.161 | 0.4076 | 8000 | 3.1091 | 0.4539 | |
|
| 3.1554 | 0.4586 | 9000 | 3.1044 | 0.4529 | |
|
| 3.1405 | 0.5095 | 10000 | 3.1151 | 0.4539 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.43.4 |
|
- Pytorch 1.12.0+cu102 |
|
- Datasets 2.20.0 |
|
- Tokenizers 0.19.1 |
|
|
