winobias_trainer_roberta-large_finetuned
This model is a fine-tuned version of roberta-large on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.6932
- Accuracy: 0.5
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: 32
- eval_batch_size: 32
- 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 | 0.4 | 20 | 0.6966 | 0.5 |
| No log | 0.8 | 40 | 0.7068 | 0.5 |
| No log | 1.2 | 60 | 0.7124 | 0.5 |
| No log | 1.6 | 80 | 0.6931 | 0.5 |
| No log | 2.0 | 100 | 0.7072 | 0.5 |
| No log | 2.4 | 120 | 0.6989 | 0.5 |
| No log | 2.8 | 140 | 0.6956 | 0.5 |
| No log | 3.2 | 160 | 0.6967 | 0.5 |
| No log | 3.6 | 180 | 0.6939 | 0.5 |
| No log | 4.0 | 200 | 0.6933 | 0.5 |
| No log | 4.4 | 220 | 0.6934 | 0.5 |
| No log | 4.8 | 240 | 0.6932 | 0.5 |
Framework versions
- Transformers 4.23.1
- Pytorch 1.12.1
- Datasets 2.6.1
- Tokenizers 0.13.1