---
base_model: yihongLiu/furina
tags:
- generated_from_trainer
model-index:
- name: furina_latin_amh-esp-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_latin_amh-esp-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: 0.0189
- Spearman Corr: 0.7428

## 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        | 0.53  | 200  | 0.0170          | 0.6821        |
| No log        | 1.06  | 400  | 0.0189          | 0.7085        |
| No log        | 1.59  | 600  | 0.0171          | 0.7217        |
| 0.0448        | 2.12  | 800  | 0.0218          | 0.7303        |
| 0.0448        | 2.65  | 1000 | 0.0172          | 0.7281        |
| 0.0448        | 3.17  | 1200 | 0.0182          | 0.7356        |
| 0.0448        | 3.7   | 1400 | 0.0164          | 0.7388        |
| 0.0206        | 4.23  | 1600 | 0.0179          | 0.7414        |
| 0.0206        | 4.76  | 1800 | 0.0188          | 0.7419        |
| 0.0206        | 5.29  | 2000 | 0.0175          | 0.7453        |
| 0.0206        | 5.82  | 2200 | 0.0187          | 0.7493        |
| 0.0155        | 6.35  | 2400 | 0.0203          | 0.7403        |
| 0.0155        | 6.88  | 2600 | 0.0180          | 0.7443        |
| 0.0155        | 7.41  | 2800 | 0.0189          | 0.7415        |
| 0.0155        | 7.94  | 3000 | 0.0178          | 0.7476        |
| 0.0116        | 8.47  | 3200 | 0.0189          | 0.7396        |
| 0.0116        | 8.99  | 3400 | 0.0203          | 0.7367        |
| 0.0116        | 9.52  | 3600 | 0.0195          | 0.7434        |
| 0.0089        | 10.05 | 3800 | 0.0189          | 0.7428        |


### Framework versions

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