<!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. -->
bert-base-uncased-qnli
This model is a fine-tuned version of bert-base-uncased on the GLUE QNLI dataset. It achieves the following results on the evaluation set:
- Loss: 0.2297
- Accuracy: 0.9105
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: 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 |
---|---|---|---|---|
0.3436 | 1.0 | 819 | 0.2489 | 0.9035 |
0.1962 | 2.0 | 1638 | 0.2297 | 0.9105 |
0.1049 | 3.0 | 2457 | 0.2620 | 0.9121 |
0.0662 | 4.0 | 3276 | 0.3534 | 0.9088 |
0.0487 | 5.0 | 4095 | 0.3688 | 0.9046 |
0.0368 | 6.0 | 4914 | 0.3943 | 0.9074 |
0.0329 | 7.0 | 5733 | 0.4250 | 0.9092 |
0.0272 | 8.0 | 6552 | 0.4012 | 0.9054 |
0.0243 | 9.0 | 7371 | 0.4497 | 0.9041 |
Framework versions
- Transformers 4.26.0
- Pytorch 1.14.0a0+410ce96
- Datasets 2.9.0
- Tokenizers 0.13.2