cs605-nlp-assignment-2-bert-base-uncased
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: 1.9930
- Accuracy: 0.7452
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: 16
- eval_batch_size: 16
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 10
Training results
Training Loss | Epoch | Step | Validation Loss | Accuracy |
---|---|---|---|---|
0.5642 | 1.0 | 746 | 0.5072 | 0.7389 |
0.3952 | 2.0 | 1492 | 0.6096 | 0.7459 |
0.1079 | 3.0 | 2238 | 1.1929 | 0.7523 |
0.0792 | 4.0 | 2984 | 1.4899 | 0.7566 |
0.0268 | 5.0 | 3730 | 1.6392 | 0.7382 |
0.0203 | 6.0 | 4476 | 1.8555 | 0.7311 |
0.0104 | 7.0 | 5222 | 1.9696 | 0.7459 |
0.0049 | 8.0 | 5968 | 1.9695 | 0.7389 |
0.0036 | 9.0 | 6714 | 1.9248 | 0.7476 |
0.0019 | 10.0 | 7460 | 1.9930 | 0.7452 |
Framework versions
- Transformers 4.40.1
- Pytorch 2.3.0
- Datasets 2.18.0
- Tokenizers 0.19.1
- Downloads last month
- 2
Inference API (serverless) does not yet support transformers models for this pipeline type.
Model tree for inflaton/cs605-nlp-assignment-2-bert-base-uncased
Base model
google-bert/bert-base-uncased
Finetuned
this model