bert_base_train_book_ent_15p_s_qnli
This model is a fine-tuned version of gokulsrinivasagan/bert_base_train_book_ent_15p_s on the GLUE QNLI dataset. It achieves the following results on the evaluation set:
- Loss: 0.6915
- Accuracy: 0.4946
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: 5e-05
- train_batch_size: 256
- eval_batch_size: 256
- seed: 10
- optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: linear
- num_epochs: 50
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 0.698 | 1.0 | 410 | 0.6946 | 0.4946 |
| 0.6975 | 2.0 | 820 | 0.6915 | 0.4946 |
| 0.6966 | 3.0 | 1230 | 0.6980 | 0.5054 |
| 0.6964 | 4.0 | 1640 | 0.6938 | 0.4946 |
| 0.6958 | 5.0 | 2050 | 0.6931 | 0.5054 |
| 0.6955 | 6.0 | 2460 | 0.6929 | 0.5054 |
| 0.6956 | 7.0 | 2870 | 0.6938 | 0.4946 |
Framework versions
- Transformers 4.51.2
- Pytorch 2.6.0+cu126
- Datasets 3.5.0
- Tokenizers 0.21.1