|
--- |
|
base_model: yihongLiu/furina |
|
tags: |
|
- generated_from_trainer |
|
model-index: |
|
- name: furina_ary_loss_5e-06 |
|
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_ary_loss_5e-06 |
|
|
|
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: 0.0226 |
|
- Spearman Corr: 0.7565 |
|
|
|
## 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-06 |
|
- 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 | 0.7563 | |
|
| No log | 1.8 | 400 | 0.0235 | 0.7560 | |
|
| 0.0036 | 2.7 | 600 | 0.0225 | 0.7529 | |
|
| 0.0036 | 3.6 | 800 | 0.0230 | 0.7605 | |
|
| 0.0035 | 4.5 | 1000 | 0.0219 | 0.7584 | |
|
| 0.0035 | 5.41 | 1200 | 0.0227 | 0.7586 | |
|
| 0.0034 | 6.31 | 1400 | 0.0221 | 0.7607 | |
|
| 0.0034 | 7.21 | 1600 | 0.0225 | 0.7612 | |
|
| 0.0038 | 8.11 | 1800 | 0.0219 | 0.7575 | |
|
| 0.0038 | 9.01 | 2000 | 0.0224 | 0.7576 | |
|
| 0.0038 | 9.91 | 2200 | 0.0220 | 0.7598 | |
|
| 0.0043 | 10.81 | 2400 | 0.0224 | 0.7601 | |
|
| 0.0043 | 11.71 | 2600 | 0.0226 | 0.7565 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.37.2 |
|
- Pytorch 2.2.0+cu121 |
|
- Datasets 2.17.0 |
|
- Tokenizers 0.15.2 |
|
|
