---
base_model: yihongLiu/furina
tags:
- generated_from_trainer
model-index:
- name: furina_amh_corr_2e-05
  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_amh_corr_2e-05

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: 0.0255
- Spearman Corr: 0.7661

## 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 |
|:-------------:|:-----:|:----:|:---------------:|:-------------:|
| No log        | 0.9   | 200  | 0.0228          | 0.7682        |
| No log        | 1.81  | 400  | 0.0219          | 0.7622        |
| 0.0074        | 2.71  | 600  | 0.0265          | 0.7692        |
| 0.0074        | 3.62  | 800  | 0.0293          | 0.7731        |
| 0.0059        | 4.52  | 1000 | 0.0217          | 0.7782        |
| 0.0059        | 5.43  | 1200 | 0.0239          | 0.7679        |
| 0.005         | 6.33  | 1400 | 0.0227          | 0.7710        |
| 0.005         | 7.24  | 1600 | 0.0234          | 0.7666        |
| 0.0042        | 8.14  | 1800 | 0.0242          | 0.7729        |
| 0.0042        | 9.05  | 2000 | 0.0225          | 0.7674        |
| 0.0042        | 9.95  | 2200 | 0.0233          | 0.7682        |
| 0.0038        | 10.86 | 2400 | 0.0228          | 0.7659        |
| 0.0038        | 11.76 | 2600 | 0.0255          | 0.7661        |


### Framework versions

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