furina_eng_loss_2e-05
This model is a fine-tuned version of yihongLiu/furina on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.0202
- Spearman Corr: 0.7777
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: 2e-05
- 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 | 1.33 | 200 | 0.0211 | 0.7732 |
0.0009 | 2.66 | 400 | 0.0215 | 0.7773 |
0.0008 | 3.99 | 600 | 0.0209 | 0.7752 |
0.0008 | 5.32 | 800 | 0.0197 | 0.7734 |
0.0007 | 6.64 | 1000 | 0.0211 | 0.7735 |
0.0006 | 7.97 | 1200 | 0.0208 | 0.7751 |
0.0006 | 9.3 | 1400 | 0.0203 | 0.7789 |
0.0008 | 10.63 | 1600 | 0.0200 | 0.7797 |
0.001 | 11.96 | 1800 | 0.0207 | 0.7734 |
0.001 | 13.29 | 2000 | 0.0203 | 0.7756 |
0.0009 | 14.62 | 2200 | 0.0202 | 0.7745 |
0.0009 | 15.95 | 2400 | 0.0202 | 0.7777 |
Framework versions
- Transformers 4.37.2
- Pytorch 2.2.0+cu121
- Datasets 2.17.0
- Tokenizers 0.15.2
- Downloads last month
- 6
Inference API (serverless) is not available, repository is disabled.
Model tree for Shijia/furina_eng_loss_2e-05
Base model
yihongLiu/furina
Finetuned
this model