|
--- |
|
base_model: yihongLiu/furina |
|
tags: |
|
- generated_from_trainer |
|
model-index: |
|
- name: furina_seed42_eng_kin_amh_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_kin_amh_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: 0.0235 |
|
- Spearman Corr: 0.7429 |
|
|
|
## 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 | 0.59 | 200 | 0.0574 | 0.0907 | |
|
| No log | 1.17 | 400 | 0.0433 | 0.3618 | |
|
| No log | 1.76 | 600 | 0.0302 | 0.5602 | |
|
| 0.0806 | 2.35 | 800 | 0.0310 | 0.6452 | |
|
| 0.0806 | 2.93 | 1000 | 0.0311 | 0.6667 | |
|
| 0.0806 | 3.52 | 1200 | 0.0341 | 0.6832 | |
|
| 0.0313 | 4.11 | 1400 | 0.0263 | 0.6957 | |
|
| 0.0313 | 4.69 | 1600 | 0.0366 | 0.7020 | |
|
| 0.0313 | 5.28 | 1800 | 0.0311 | 0.7107 | |
|
| 0.0313 | 5.87 | 2000 | 0.0340 | 0.7112 | |
|
| 0.0257 | 6.45 | 2200 | 0.0251 | 0.7188 | |
|
| 0.0257 | 7.04 | 2400 | 0.0229 | 0.7220 | |
|
| 0.0257 | 7.62 | 2600 | 0.0243 | 0.7361 | |
|
| 0.0226 | 8.21 | 2800 | 0.0217 | 0.7414 | |
|
| 0.0226 | 8.8 | 3000 | 0.0231 | 0.7376 | |
|
| 0.0226 | 9.38 | 3200 | 0.0233 | 0.7431 | |
|
| 0.0226 | 9.97 | 3400 | 0.0257 | 0.7369 | |
|
| 0.0199 | 10.56 | 3600 | 0.0241 | 0.7474 | |
|
| 0.0199 | 11.14 | 3800 | 0.0253 | 0.7411 | |
|
| 0.0199 | 11.73 | 4000 | 0.0257 | 0.7478 | |
|
| 0.0178 | 12.32 | 4200 | 0.0267 | 0.7471 | |
|
| 0.0178 | 12.9 | 4400 | 0.0235 | 0.7429 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.37.2 |
|
- Pytorch 2.1.0+cu121 |
|
- Datasets 2.17.0 |
|
- Tokenizers 0.15.2 |
|
|
