distilbert-fa-zwnj-base-MLM-pquad_2
This model is a fine-tuned version of HooshvareLab/distilbert-fa-zwnj-base on the generator dataset. It achieves the following results on the evaluation set:
- Loss: 5.1748
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: 0.0005
- train_batch_size: 32
- eval_batch_size: 32
- seed: 42
- gradient_accumulation_steps: 8
- total_train_batch_size: 256
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: cosine
- lr_scheduler_warmup_steps: 100
- num_epochs: 20
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 6.714 | 3.22 | 100 | 6.4352 |
| 6.4216 | 6.44 | 200 | 6.1348 |
| 6.1667 | 9.67 | 300 | 5.9233 |
| 5.9502 | 12.89 | 400 | 5.6905 |
| 5.6578 | 16.13 | 500 | 5.2831 |
| 5.379 | 19.35 | 600 | 5.1748 |
Framework versions
- Transformers 4.26.1
- Pytorch 1.13.1+cu116
- Datasets 2.9.0
- Tokenizers 0.13.2