furina_hau_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: 0.0213
- Spearman Corr: 0.7683
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 | 0.95 | 200 | 0.0215 | 0.7652 |
No log | 1.91 | 400 | 0.0209 | 0.7689 |
0.0007 | 2.86 | 600 | 0.0213 | 0.7713 |
0.0007 | 3.82 | 800 | 0.0208 | 0.7714 |
0.0006 | 4.77 | 1000 | 0.0205 | 0.7709 |
0.0006 | 5.73 | 1200 | 0.0205 | 0.7725 |
0.0006 | 6.68 | 1400 | 0.0212 | 0.7675 |
0.0006 | 7.64 | 1600 | 0.0213 | 0.7675 |
0.0005 | 8.59 | 1800 | 0.0210 | 0.7672 |
0.0005 | 9.55 | 2000 | 0.0211 | 0.7664 |
0.0005 | 10.5 | 2200 | 0.0216 | 0.7675 |
0.0005 | 11.46 | 2400 | 0.0212 | 0.7666 |
0.0005 | 12.41 | 2600 | 0.0213 | 0.7683 |
Framework versions
- Transformers 4.37.2
- Pytorch 2.2.0+cu121
- Datasets 2.17.0
- Tokenizers 0.15.2
- Downloads last month
- 5
Inference Providers
NEW
This model is not currently available via any of the supported Inference Providers.
Model tree for Shijia/furina_hau_loss_2e-05
Base model
yihongLiu/furina