hBERTv1_new_pretrain_w_init_48_ver2_rte
This model is a fine-tuned version of gokuls/bert_12_layer_model_v1_complete_training_new_wt_init_48 on the GLUE RTE dataset. It achieves the following results on the evaluation set:
- Loss: 0.6919
- Accuracy: 0.5271
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 |
|---|---|---|---|---|
| 0.7175 | 1.0 | 39 | 0.6919 | 0.5271 |
| 0.7099 | 2.0 | 78 | 0.7006 | 0.4729 |
| 0.7111 | 3.0 | 117 | 0.6927 | 0.5271 |
| 0.7011 | 4.0 | 156 | 0.6976 | 0.4729 |
| 0.7021 | 5.0 | 195 | 0.6955 | 0.4729 |
| 0.6986 | 6.0 | 234 | 0.7078 | 0.4729 |
Framework versions
- Transformers 4.34.0
- Pytorch 1.14.0a0+410ce96
- Datasets 2.14.5
- Tokenizers 0.14.1
- Downloads last month
- 4
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.