metadata
base_model: yihongLiu/furina
tags:
- generated_from_trainer
model-index:
- name: furina_kin_loss_2e-05
results: []
furina_kin_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: 0.0210
- Spearman Corr: 0.7681
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 | 0.89 | 200 | 0.0215 | 0.7741 |
| No log | 1.78 | 400 | 0.0206 | 0.7664 |
| 0.0006 | 2.67 | 600 | 0.0211 | 0.7701 |
| 0.0006 | 3.56 | 800 | 0.0205 | 0.7727 |
| 0.0006 | 4.45 | 1000 | 0.0207 | 0.7730 |
| 0.0006 | 5.35 | 1200 | 0.0207 | 0.7687 |
| 0.0007 | 6.24 | 1400 | 0.0209 | 0.7701 |
| 0.0007 | 7.13 | 1600 | 0.0212 | 0.7677 |
| 0.0007 | 8.02 | 1800 | 0.0210 | 0.7697 |
| 0.0007 | 8.91 | 2000 | 0.0210 | 0.7681 |
Framework versions
- Transformers 4.37.2
- Pytorch 2.2.0+cu121
- Datasets 2.17.0
- Tokenizers 0.15.2