hBERTv2_new_pretrain_48_qnli
This model is a fine-tuned version of gokuls/bert_12_layer_model_v2_complete_training_new_48 on the GLUE QNLI dataset. It achieves the following results on the evaluation set:
- Loss: 0.6635
- Accuracy: 0.5967
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 |
|---|---|---|---|---|
| 0.6834 | 1.0 | 819 | 0.6635 | 0.5967 |
| 0.6634 | 2.0 | 1638 | 0.6696 | 0.5931 |
| 0.6597 | 3.0 | 2457 | 0.6701 | 0.6013 |
| 0.6607 | 4.0 | 3276 | 0.6780 | 0.5876 |
| 0.6602 | 5.0 | 4095 | 0.6903 | 0.5858 |
| 0.6577 | 6.0 | 4914 | 0.6712 | 0.5892 |
Framework versions
- Transformers 4.29.2
- Pytorch 1.14.0a0+410ce96
- Datasets 2.12.0
- Tokenizers 0.13.3
- Downloads last month
- 45
Inference Providers
NEW
This model is not currently available via any of the supported third-party Inference Providers, and
the model is not deployed on the HF Inference API.
Dataset used to train gokuls/hBERTv2_new_pretrain_48_qnli
Evaluation results
- Accuracy on GLUE QNLIvalidation set self-reported0.597