<!-- 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. -->
Task1a_class
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: 0.7193
- Accuracy: 0.6857
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: 5e-05
- train_batch_size: 8
- eval_batch_size: 8
- seed: 42
- 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 | Accuracy |
|---|---|---|---|---|
| No log | 1.0 | 18 | 0.7991 | 0.4857 |
| No log | 2.0 | 36 | 0.6316 | 0.7143 |
| No log | 3.0 | 54 | 0.7638 | 0.6 |
| No log | 4.0 | 72 | 0.7218 | 0.6571 |
| No log | 5.0 | 90 | 0.7193 | 0.6857 |
Framework versions
- Transformers 4.27.4
- Pytorch 1.13.1+cu116
- Datasets 2.11.0
- Tokenizers 0.13.2
