|
--- |
|
base_model: yihongLiu/furina |
|
tags: |
|
- generated_from_trainer |
|
model-index: |
|
- name: furina_seed42_eng_esp_kin_cross_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_esp_kin_cross_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: 0.0323 |
|
- Spearman Corr: 0.6759 |
|
|
|
## 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 | 0.54 | 200 | 0.0358 | 0.5989 | |
|
| No log | 1.09 | 400 | 0.0285 | 0.6016 | |
|
| No log | 1.63 | 600 | 0.0403 | -0.0786 | |
|
| 0.046 | 2.18 | 800 | 0.0386 | nan | |
|
| 0.046 | 2.72 | 1000 | 0.0383 | nan | |
|
| 0.046 | 3.27 | 1200 | 0.0392 | 0.4628 | |
|
| 0.046 | 3.81 | 1400 | 0.0601 | 0.5371 | |
|
| 0.0469 | 4.35 | 1600 | 0.0260 | 0.6378 | |
|
| 0.0469 | 4.9 | 1800 | 0.0273 | 0.6483 | |
|
| 0.0469 | 5.44 | 2000 | 0.0278 | 0.6641 | |
|
| 0.0469 | 5.99 | 2200 | 0.0336 | 0.6578 | |
|
| 0.0219 | 6.53 | 2400 | 0.0314 | 0.6684 | |
|
| 0.0219 | 7.07 | 2600 | 0.0335 | 0.6719 | |
|
| 0.0219 | 7.62 | 2800 | 0.0277 | 0.6742 | |
|
| 0.0128 | 8.16 | 3000 | 0.0377 | 0.6741 | |
|
| 0.0128 | 8.71 | 3200 | 0.0323 | 0.6759 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.37.2 |
|
- Pytorch 2.1.0+cu121 |
|
- Datasets 2.17.0 |
|
- Tokenizers 0.15.2 |
|
|
