furina_seed42_eng_esp_hau_cross_0.0001
This model is a fine-tuned version of yihongLiu/furina on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.0279
- Spearman Corr: 0.6968
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: 0.0001
- 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 | 0.48 | 200 | 0.0361 | 0.5376 |
No log | 0.97 | 400 | 0.0267 | 0.6376 |
No log | 1.45 | 600 | 0.0314 | 0.6433 |
No log | 1.94 | 800 | 0.0275 | 0.6611 |
0.0438 | 2.42 | 1000 | 0.0256 | 0.6919 |
0.0438 | 2.91 | 1200 | 0.0347 | 0.6921 |
0.0438 | 3.39 | 1400 | 0.0309 | 0.6727 |
0.0438 | 3.88 | 1600 | 0.0366 | 0.6935 |
0.0231 | 4.36 | 1800 | 0.0281 | 0.6924 |
0.0231 | 4.85 | 2000 | 0.0285 | 0.6941 |
0.0231 | 5.33 | 2200 | 0.0268 | 0.6985 |
0.0231 | 5.82 | 2400 | 0.0306 | 0.6896 |
0.0148 | 6.3 | 2600 | 0.0279 | 0.6968 |
Framework versions
- Transformers 4.37.2
- Pytorch 2.1.0+cu121
- Datasets 2.17.0
- Tokenizers 0.15.2
- Downloads last month
- 92
Inference Providers
NEW
This model is not currently available via any of the supported Inference Providers.
Model tree for Shijia/furina_seed42_eng_esp_hau_cross_0.0001
Base model
yihongLiu/furina