bert-base-uncased-finetuned-wls-manual-5ep-lower
This model is a fine-tuned version of bert-base-uncased on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 1.4858
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: 0.0001
- train_batch_size: 32
- eval_batch_size: 32
- seed: 42
- gradient_accumulation_steps: 2
- total_train_batch_size: 64
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 5
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 2.1142 | 0.93 | 7 | 1.9585 |
| 1.6082 | 2.0 | 15 | 1.5910 |
| 1.4973 | 2.93 | 22 | 1.4644 |
| 1.4145 | 4.0 | 30 | 1.4717 |
| 1.335 | 4.67 | 35 | 1.4035 |
Framework versions
- Transformers 4.31.0
- Pytorch 1.11.0+cu113
- Datasets 2.14.4
- Tokenizers 0.13.3
- Downloads last month
- 1
Model tree for btamm12/bert-base-uncased-finetuned-wls-manual-5ep-lower
Base model
google-bert/bert-base-uncased