<!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. -->
fine-tuning-binary_bert-cola-glue-steps47-bs128-0.0003-8-8-512-0.1
This model was trained from scratch on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.0003
- Accuracy: 1.0
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: 0.0003
- train_batch_size: 128
- eval_batch_size: 128
- seed: 42
- distributed_type: multi-GPU
- num_devices: 2
- total_train_batch_size: 256
- total_eval_batch_size: 256
- optimizer: Adam with betas=(0.9,0.98) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 1
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 0.3086 | 0.21 | 5 | 0.0410 | 1.0 |
| 0.02 | 0.42 | 10 | 0.0019 | 1.0 |
| 0.0016 | 0.62 | 15 | 0.0005 | 1.0 |
| 0.0006 | 0.83 | 20 | 0.0003 | 1.0 |
Framework versions
- Transformers 4.34.1
- Pytorch 2.1.0+cu121
- Datasets 2.14.6
- Tokenizers 0.14.1
