loha_fine_tuned_copa
This model is a fine-tuned version of google-bert/bert-base-uncased on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.7712
- Accuracy: 0.52
- F1: 0.5208
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: 0.003
- 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
- training_steps: 400
Training results
Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 |
---|---|---|---|---|---|
0.7031 | 1.0 | 50 | 0.6881 | 0.54 | 0.5411 |
0.692 | 2.0 | 100 | 0.6918 | 0.46 | 0.4613 |
0.6983 | 3.0 | 150 | 0.6993 | 0.48 | 0.4800 |
0.7013 | 4.0 | 200 | 0.6969 | 0.48 | 0.4771 |
0.6993 | 5.0 | 250 | 0.6922 | 0.53 | 0.5312 |
0.7012 | 6.0 | 300 | 0.6921 | 0.51 | 0.5110 |
0.6636 | 7.0 | 350 | 0.7049 | 0.53 | 0.5310 |
0.5915 | 8.0 | 400 | 0.7712 | 0.52 | 0.5208 |
Framework versions
- PEFT 0.10.1.dev0
- Transformers 4.40.1
- Pytorch 2.1.1+cu121
- Datasets 2.19.0
- Tokenizers 0.19.1
- Downloads last month
- 118
Unable to determine this model’s pipeline type. Check the
docs
.