furina_seed42_eng_esp_kin_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: 0.0243
- Spearman Corr: 0.6941
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 | 0.54 | 200 | 0.0533 | 0.0572 |
No log | 1.09 | 400 | 0.0304 | 0.5257 |
No log | 1.63 | 600 | 0.0287 | 0.5941 |
0.0719 | 2.18 | 800 | 0.0259 | 0.6188 |
0.0719 | 2.72 | 1000 | 0.0271 | 0.6295 |
0.0719 | 3.27 | 1200 | 0.0260 | 0.6321 |
0.0719 | 3.81 | 1400 | 0.0273 | 0.6451 |
0.0277 | 4.35 | 1600 | 0.0252 | 0.6539 |
0.0277 | 4.9 | 1800 | 0.0244 | 0.6544 |
0.0277 | 5.44 | 2000 | 0.0242 | 0.6640 |
0.0277 | 5.99 | 2200 | 0.0241 | 0.6676 |
0.0239 | 6.53 | 2400 | 0.0235 | 0.6710 |
0.0239 | 7.07 | 2600 | 0.0240 | 0.6761 |
0.0239 | 7.62 | 2800 | 0.0246 | 0.6809 |
0.0211 | 8.16 | 3000 | 0.0240 | 0.6802 |
0.0211 | 8.71 | 3200 | 0.0242 | 0.6862 |
0.0211 | 9.25 | 3400 | 0.0245 | 0.6863 |
0.0211 | 9.8 | 3600 | 0.0234 | 0.6897 |
0.019 | 10.34 | 3800 | 0.0235 | 0.6906 |
0.019 | 10.88 | 4000 | 0.0243 | 0.6941 |
Framework versions
- Transformers 4.37.2
- Pytorch 2.1.0+cu121
- Datasets 2.17.0
- Tokenizers 0.15.2
- Downloads last month
- 5
Inference API (serverless) is not available, repository is disabled.
Model tree for Shijia/furina_seed42_eng_esp_kin_cross_5e-06
Base model
yihongLiu/furina
Finetuned
this model