add_BERT_no_pretrain_qnli
This model is a fine-tuned version of on the GLUE QNLI dataset. It achieves the following results on the evaluation set:
- Loss: 0.6899
- Accuracy: 0.5288
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: 4e-05
- train_batch_size: 128
- eval_batch_size: 128
- seed: 10
- distributed_type: multi-GPU
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 50
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 0.7079 | 1.0 | 819 | 0.7210 | 0.5054 |
| 0.6952 | 2.0 | 1638 | 0.6912 | 0.4946 |
| 0.6922 | 3.0 | 2457 | 0.6905 | 0.5279 |
| 0.6918 | 4.0 | 3276 | 0.6899 | 0.5288 |
| 0.6922 | 5.0 | 4095 | 0.6922 | 0.5153 |
| 0.6933 | 6.0 | 4914 | 0.6926 | 0.5127 |
| 0.6931 | 7.0 | 5733 | 0.6952 | 0.4946 |
| 0.6933 | 8.0 | 6552 | 0.6928 | 0.5113 |
| 0.693 | 9.0 | 7371 | 0.6922 | 0.5215 |
Framework versions
- Transformers 4.30.2
- Pytorch 1.14.0a0+410ce96
- Datasets 2.12.0
- Tokenizers 0.13.3