|
--- |
|
base_model: yihongLiu/furina |
|
tags: |
|
- generated_from_trainer |
|
model-index: |
|
- name: furina_seed42_eng_amh_hau_basic_0.0001 |
|
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_seed42_eng_amh_hau_basic_0.0001 |
|
|
|
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: 0.0338 |
|
- Spearman Corr: 0.7400 |
|
|
|
## 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: 0.0001 |
|
- 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 | 1.55 | 200 | 0.0268 | 0.6751 | |
|
| 0.0634 | 3.1 | 400 | 0.0365 | 0.7191 | |
|
| 0.0233 | 4.65 | 600 | 0.0237 | 0.7350 | |
|
| 0.0152 | 6.2 | 800 | 0.0311 | 0.7443 | |
|
| 0.0152 | 7.75 | 1000 | 0.0321 | 0.7341 | |
|
| 0.0108 | 9.3 | 1200 | 0.0303 | 0.7293 | |
|
| 0.0078 | 10.85 | 1400 | 0.0301 | 0.7334 | |
|
| 0.0062 | 12.4 | 1600 | 0.0368 | 0.7249 | |
|
| 0.005 | 13.95 | 1800 | 0.0377 | 0.7439 | |
|
| 0.005 | 15.5 | 2000 | 0.0327 | 0.7443 | |
|
| 0.0044 | 17.05 | 2200 | 0.0338 | 0.7400 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.37.2 |
|
- Pytorch 2.1.0+cu121 |
|
- Datasets 2.17.0 |
|
- Tokenizers 0.15.2 |
|
|
