test_twowayloss_implementation
This model is a fine-tuned version of bert-base-uncased on the None dataset. It achieves the following results on the evaluation set:
- Loss: 8.9001
- Accuracy: 0.5659
- Precision: 0.0114
- Recall: 0.5082
- F1: 0.0223
- Hamming: 0.4341
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: 8
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_ratio: 0.1
- training_steps: 10
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | Precision | Recall | F1 | Hamming |
|---|---|---|---|---|---|---|---|---|
| 8.8818 | 0.0 | 5 | 8.9210 | 0.5632 | 0.0110 | 0.4947 | 0.0216 | 0.4368 |
| 8.124 | 0.0 | 10 | 8.9001 | 0.5659 | 0.0114 | 0.5082 | 0.0223 | 0.4341 |
Framework versions
- Transformers 4.35.0.dev0
- Pytorch 2.0.1+cu118
- Datasets 2.7.1
- Tokenizers 0.14.1