hBERTv1_new_pretrain_w_init_48_ver2_wnli
This model is a fine-tuned version of gokuls/bert_12_layer_model_v1_complete_training_new_wt_init_48 on the GLUE WNLI dataset. It achieves the following results on the evaluation set:
- Loss: 0.6880
- Accuracy: 0.5634
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: 64
- eval_batch_size: 64
- seed: 10
- distributed_type: multi-GPU
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 15
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 0.7455 | 1.0 | 10 | 0.7146 | 0.4366 |
| 0.7087 | 2.0 | 20 | 0.6880 | 0.5634 |
| 0.7086 | 3.0 | 30 | 0.7292 | 0.5634 |
| 0.7098 | 4.0 | 40 | 0.6897 | 0.5634 |
| 0.6995 | 5.0 | 50 | 0.7766 | 0.4366 |
| 0.7286 | 6.0 | 60 | 0.7309 | 0.4366 |
| 0.7537 | 7.0 | 70 | 0.7128 | 0.5634 |
Framework versions
- Transformers 4.34.0
- Pytorch 1.14.0a0+410ce96
- Datasets 2.14.5
- Tokenizers 0.14.1
- Downloads last month
- 5
This model does not have enough activity to be deployed to Inference API (serverless) yet. Increase its social
visibility and check back later, or deploy to Inference Endpoints (dedicated)
instead.
Model tree for gokuls/hBERTv1_new_pretrain_w_init_48_ver2_wnli
Dataset used to train gokuls/hBERTv1_new_pretrain_w_init_48_ver2_wnli
Evaluation results
- Accuracy on GLUE WNLIvalidation set self-reported0.563