---
base_model: yihongLiu/furina
tags:
- generated_from_trainer
model-index:
- name: furina_eng_train_spearman_corr
  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. -->

# furina_eng_train_spearman_corr

This model is a fine-tuned version of [yihongLiu/furina](https://huggingface.co/yihongLiu/furina) on the None dataset.
It achieves the following results on the evaluation set:
- Loss: 0.0236
- Spearman Corr: 0.7826

## 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: 128
- seed: 42
- gradient_accumulation_steps: 2
- total_train_batch_size: 64
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 30
- mixed_precision_training: Native AMP

### Training results

| Training Loss | Epoch | Step | Validation Loss | Spearman Corr |
|:-------------:|:-----:|:----:|:---------------:|:-------------:|
| 0.0998        | 2.33  | 200  | 0.0146          | 0.7469        |
| 0.025         | 4.65  | 400  | 0.0226          | 0.7908        |
| 0.0171        | 6.98  | 600  | 0.0186          | 0.7648        |
| 0.0136        | 9.3   | 800  | 0.0169          | 0.7634        |
| 0.0114        | 11.63 | 1000 | 0.0214          | 0.7722        |
| 0.0081        | 13.95 | 1200 | 0.0221          | 0.7833        |
| 0.0072        | 16.28 | 1400 | 0.0228          | 0.7853        |
| 0.0065        | 18.6  | 1600 | 0.0245          | 0.7759        |
| 0.006         | 20.93 | 1800 | 0.0286          | 0.7788        |
| 0.0056        | 23.26 | 2000 | 0.0236          | 0.7826        |


### Framework versions

- Transformers 4.37.2
- Pytorch 2.2.0+cu121
- Datasets 2.17.0
- Tokenizers 0.15.2