furina_original_esp-hau-eng_train_spearman_corr
This model is a fine-tuned version of yihongLiu/furina on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.0223
- Spearman Corr: 0.7531
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 | 1.45 | 200 | 0.0258 | 0.6734 |
0.0716 | 2.91 | 400 | 0.0230 | 0.7066 |
0.0257 | 4.36 | 600 | 0.0221 | 0.7471 |
0.0257 | 5.82 | 800 | 0.0242 | 0.7494 |
0.0197 | 7.27 | 1000 | 0.0224 | 0.7514 |
0.0156 | 8.73 | 1200 | 0.0222 | 0.7504 |
0.013 | 10.18 | 1400 | 0.0221 | 0.7507 |
0.013 | 11.64 | 1600 | 0.0213 | 0.7606 |
0.0107 | 13.09 | 1800 | 0.0218 | 0.7568 |
0.0091 | 14.55 | 2000 | 0.0223 | 0.7588 |
0.0081 | 16.0 | 2200 | 0.0230 | 0.7582 |
0.0081 | 17.45 | 2400 | 0.0230 | 0.7548 |
0.0071 | 18.91 | 2600 | 0.0221 | 0.7561 |
0.0063 | 20.36 | 2800 | 0.0216 | 0.7591 |
0.0063 | 21.82 | 3000 | 0.0217 | 0.7578 |
0.0059 | 23.27 | 3200 | 0.0223 | 0.7531 |
Framework versions
- Transformers 4.37.2
- Pytorch 2.2.0+cu121
- Datasets 2.17.0
- Tokenizers 0.15.2
- Downloads last month
- 3
Inference API (serverless) is not available, repository is disabled.
Model tree for shanhy/furina_original_esp-hau-eng_train_spearman_corr
Base model
yihongLiu/furina
Finetuned
this model