|
--- |
|
base_model: yihongLiu/furina |
|
tags: |
|
- generated_from_trainer |
|
model-index: |
|
- name: furina_seed42_eng_esp_hau_cross_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_seed42_eng_esp_hau_cross_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: 0.0260 |
|
- Spearman Corr: 0.7338 |
|
|
|
## 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 | 0.48 | 200 | 0.0504 | 0.1104 | |
|
| No log | 0.97 | 400 | 0.0316 | 0.6024 | |
|
| No log | 1.45 | 600 | 0.0338 | 0.6583 | |
|
| No log | 1.94 | 800 | 0.0294 | 0.6741 | |
|
| 0.0692 | 2.42 | 1000 | 0.0294 | 0.6849 | |
|
| 0.0692 | 2.91 | 1200 | 0.0312 | 0.6991 | |
|
| 0.0692 | 3.39 | 1400 | 0.0312 | 0.7002 | |
|
| 0.0692 | 3.88 | 1600 | 0.0231 | 0.7199 | |
|
| 0.0291 | 4.36 | 1800 | 0.0243 | 0.7215 | |
|
| 0.0291 | 4.85 | 2000 | 0.0286 | 0.7169 | |
|
| 0.0291 | 5.33 | 2200 | 0.0274 | 0.7279 | |
|
| 0.0291 | 5.82 | 2400 | 0.0248 | 0.7313 | |
|
| 0.0248 | 6.3 | 2600 | 0.0266 | 0.7305 | |
|
| 0.0248 | 6.79 | 2800 | 0.0238 | 0.7325 | |
|
| 0.0248 | 7.27 | 3000 | 0.0262 | 0.7311 | |
|
| 0.0248 | 7.76 | 3200 | 0.0260 | 0.7338 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.37.2 |
|
- Pytorch 2.1.0+cu121 |
|
- Datasets 2.17.0 |
|
- Tokenizers 0.15.2 |
|
|
