metadata
base_model: yihongLiu/furina
tags:
- generated_from_trainer
model-index:
- name: furina_seed42_eng_kin_hau_cross_5e-06
results: []
furina_seed42_eng_kin_hau_cross_5e-06
This model is a fine-tuned version of yihongLiu/furina on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.0271
- Spearman Corr: 0.7253
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 | 0.53 | 200 | 0.0620 | 0.0297 |
No log | 1.06 | 400 | 0.0452 | 0.4298 |
No log | 1.6 | 600 | 0.0368 | 0.5777 |
0.0775 | 2.13 | 800 | 0.0330 | 0.6272 |
0.0775 | 2.66 | 1000 | 0.0368 | 0.6536 |
0.0775 | 3.19 | 1200 | 0.0303 | 0.6597 |
0.0775 | 3.72 | 1400 | 0.0300 | 0.6759 |
0.0336 | 4.26 | 1600 | 0.0282 | 0.6848 |
0.0336 | 4.79 | 1800 | 0.0277 | 0.6941 |
0.0336 | 5.32 | 2000 | 0.0269 | 0.7028 |
0.0336 | 5.85 | 2200 | 0.0283 | 0.7096 |
0.0286 | 6.38 | 2400 | 0.0271 | 0.7074 |
0.0286 | 6.91 | 2600 | 0.0271 | 0.7052 |
0.0286 | 7.45 | 2800 | 0.0276 | 0.7198 |
0.0286 | 7.98 | 3000 | 0.0270 | 0.7159 |
0.0252 | 8.51 | 3200 | 0.0277 | 0.7255 |
0.0252 | 9.04 | 3400 | 0.0268 | 0.7229 |
0.0252 | 9.57 | 3600 | 0.0271 | 0.7253 |
Framework versions
- Transformers 4.37.2
- Pytorch 2.1.0+cu121
- Datasets 2.17.0
- Tokenizers 0.15.2