all-MiniLM-L12-v2_mbti_full
This model is a fine-tuned version of sentence-transformers/all-MiniLM-L12-v2 on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.6163
- F1: 0.6302
- Roc Auc: 0.7108
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: 3e-05
- train_batch_size: 8
- eval_batch_size: 8
- seed: 42
- gradient_accumulation_steps: 2
- total_train_batch_size: 16
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 10
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | F1 | Roc Auc |
|---|---|---|---|---|---|
| No log | 1.0 | 325 | 0.5453 | 0.4591 | 0.6226 |
| 0.5606 | 2.0 | 651 | 0.5234 | 0.6248 | 0.7090 |
| 0.5606 | 3.0 | 976 | 0.5217 | 0.6148 | 0.7054 |
| 0.4918 | 4.0 | 1302 | 0.5307 | 0.5912 | 0.6932 |
| 0.4152 | 5.0 | 1627 | 0.5459 | 0.6262 | 0.7116 |
| 0.4152 | 6.0 | 1953 | 0.5793 | 0.6234 | 0.7087 |
| 0.3484 | 7.0 | 2278 | 0.5958 | 0.6378 | 0.7161 |
| 0.293 | 8.0 | 2604 | 0.6076 | 0.6405 | 0.7177 |
| 0.293 | 9.0 | 2929 | 0.6186 | 0.6362 | 0.7143 |
| 0.2592 | 9.98 | 3250 | 0.6262 | 0.6365 | 0.7149 |
Framework versions
- Transformers 4.39.1
- Pytorch 2.2.1+cu121
- Datasets 2.18.0
- Tokenizers 0.15.2