cs605-nlp-assignment-2-roberta-base
This model is a fine-tuned version of roberta-base on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 1.1088
- Accuracy: 0.7023
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: 3.2723062543456794e-05
- train_batch_size: 64
- 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 |
---|---|---|---|---|
No log | 1.0 | 187 | 0.5811 | 0.6614 |
No log | 2.0 | 374 | 0.5568 | 0.6889 |
0.5401 | 3.0 | 561 | 0.5805 | 0.6933 |
0.5401 | 4.0 | 748 | 0.6222 | 0.6996 |
0.5401 | 5.0 | 935 | 0.7495 | 0.7026 |
0.3002 | 6.0 | 1122 | 0.8180 | 0.7047 |
0.3002 | 7.0 | 1309 | 0.9720 | 0.6976 |
0.3002 | 8.0 | 1496 | 0.9912 | 0.6986 |
0.1454 | 9.0 | 1683 | 1.0774 | 0.6983 |
0.1454 | 10.0 | 1870 | 1.1088 | 0.7023 |
Framework versions
- Transformers 4.41.2
- Pytorch 2.1.0+cu121
- Datasets 2.19.1
- Tokenizers 0.19.1
- Downloads last month
- 4
Inference API (serverless) does not yet support transformers models for this pipeline type.
Model tree for inflaton/cs605-nlp-assignment-2-roberta-base
Base model
FacebookAI/roberta-base