bert-large-cased-lora-1.58M-snli-model3
This model is a fine-tuned version of bert-large-cased on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.8051
- Accuracy: 0.6975
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: 2e-05
- train_batch_size: 256
- eval_batch_size: 256
- seed: 74
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 3
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 0.5037 | 1.0 | 2146 | 0.4157 | 0.8407 |
| 0.4587 | 2.0 | 4292 | 0.3823 | 0.8574 |
| 0.446 | 3.0 | 6438 | 0.3734 | 0.8612 |
Framework versions
- Transformers 4.35.2
- Pytorch 2.1.1+cu121
- Datasets 2.15.0
- Tokenizers 0.15.0
- Downloads last month
- 92
Inference Providers
NEW
This model is not currently available via any of the supported Inference Providers.
Model tree for varun-v-rao/bert-large-cased-lora-1.58M-snli-model3
Base model
google-bert/bert-large-cased