paraphrase-mpnet-base-v2_mbti_full
This model is a fine-tuned version of sentence-transformers/paraphrase-mpnet-base-v2 on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.5933
- F1: 0.5931
- Roc Auc: 0.6834
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 | 0.5755 | 0.4804 | 0.6197 |
| 0.5774 | 2.0 | 651 | 0.5656 | 0.2262 | 0.5484 |
| 0.5774 | 3.0 | 976 | 0.5515 | 0.3992 | 0.6041 |
| 0.5594 | 4.0 | 1302 | 0.5487 | 0.4959 | 0.6344 |
| 0.5352 | 5.0 | 1627 | 0.5429 | 0.5776 | 0.6775 |
| 0.5352 | 6.0 | 1953 | 0.5557 | 0.5332 | 0.6560 |
| 0.4996 | 7.0 | 2278 | 0.5681 | 0.5895 | 0.6837 |
| 0.4531 | 8.0 | 2604 | 0.5793 | 0.5783 | 0.6783 |
| 0.4531 | 9.0 | 2929 | 0.5924 | 0.5982 | 0.6882 |
| 0.4204 | 9.98 | 3250 | 0.5970 | 0.5786 | 0.6778 |
Framework versions
- Transformers 4.39.1
- Pytorch 2.2.1+cu121
- Datasets 2.18.0
- Tokenizers 0.15.2