furina_latin_amh-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: 0.0230
- Spearman Corr: 0.7629
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 | 0.52 | 200 | 0.0373 | 0.6019 |
No log | 1.04 | 400 | 0.0271 | 0.7049 |
No log | 1.55 | 600 | 0.0230 | 0.7352 |
0.049 | 2.07 | 800 | 0.0230 | 0.7520 |
0.049 | 2.59 | 1000 | 0.0217 | 0.7528 |
0.049 | 3.11 | 1200 | 0.0225 | 0.7703 |
0.049 | 3.63 | 1400 | 0.0229 | 0.7709 |
0.0252 | 4.15 | 1600 | 0.0210 | 0.7712 |
0.0252 | 4.66 | 1800 | 0.0237 | 0.7774 |
0.0252 | 5.18 | 2000 | 0.0210 | 0.7663 |
0.0252 | 5.7 | 2200 | 0.0201 | 0.7723 |
0.0189 | 6.22 | 2400 | 0.0210 | 0.7704 |
0.0189 | 6.74 | 2600 | 0.0215 | 0.7683 |
0.0189 | 7.25 | 2800 | 0.0210 | 0.7728 |
0.0189 | 7.77 | 3000 | 0.0210 | 0.7755 |
0.0144 | 8.29 | 3200 | 0.0242 | 0.7706 |
0.0144 | 8.81 | 3400 | 0.0230 | 0.7629 |
Framework versions
- Transformers 4.37.2
- Pytorch 2.2.0+cu121
- Datasets 2.17.0
- Tokenizers 0.15.2
- Downloads last month
- 7
Inference API (serverless) is not available, repository is disabled.
Model tree for shanhy/furina_latin_amh-hau-eng_train_spearman_corr
Base model
yihongLiu/furina
Finetuned
this model