distilbert-allsides
This model is a fine-tuned version of distilbert-base-uncased on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.9138
- Acc: 0.7094
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: 32
- eval_batch_size: 32
- seed: 12345
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 16
- num_epochs: 20
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Acc |
|---|---|---|---|---|
| 0.7667 | 1.0 | 822 | 0.7003 | 0.6820 |
| 0.6893 | 2.0 | 1644 | 0.6619 | 0.6981 |
| 0.6177 | 3.0 | 2466 | 0.6736 | 0.7064 |
| 0.595 | 4.0 | 3288 | 0.6642 | 0.7091 |
| 0.5179 | 5.0 | 4110 | 0.6936 | 0.7121 |
| 0.4698 | 6.0 | 4932 | 0.7670 | 0.7106 |
| 0.463 | 7.0 | 5754 | 0.8537 | 0.7121 |
| 0.4345 | 8.0 | 6576 | 0.9138 | 0.7094 |
Framework versions
- Transformers 4.11.3
- Pytorch 1.10.1
- Datasets 1.17.0
- Tokenizers 0.10.3