hBERTv2_new_pretrain_w_init_48_rte
This model is a fine-tuned version of gokuls/bert_12_layer_model_v2_complete_training_new_wt_init_48 on the GLUE RTE dataset. It achieves the following results on the evaluation set:
- Loss: 0.6971
- Accuracy: 0.4874
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 |
|---|---|---|---|---|
| 0.755 | 1.0 | 20 | 0.7426 | 0.5271 |
| 0.7127 | 2.0 | 40 | 0.6971 | 0.4874 |
| 0.7149 | 3.0 | 60 | 0.7048 | 0.5307 |
| 0.6699 | 4.0 | 80 | 0.7651 | 0.4946 |
| 0.6432 | 5.0 | 100 | 0.7025 | 0.4801 |
| 0.6008 | 6.0 | 120 | 0.7389 | 0.5379 |
| 0.5142 | 7.0 | 140 | 0.9628 | 0.5343 |
Framework versions
- Transformers 4.29.2
- Pytorch 1.14.0a0+410ce96
- Datasets 2.12.0
- Tokenizers 0.13.3
- Downloads last month
- 9
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.