bert-base-uncased-pandas-github-issues
This model is a fine-tuned version of distilbert-base-uncased on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.0324
- F1 Micro: 0.5528
- Precision Micro: 0.6494
- Recall Micro: 0.4813
- Accuracy: 0.2932
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: 0.0001
- train_batch_size: 64
- eval_batch_size: 64
- seed: 42
- optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 500
- num_epochs: 8
Training results
| Training Loss | Epoch | Step | Validation Loss | F1 Micro | Precision Micro | Recall Micro | Accuracy |
|---|---|---|---|---|---|---|---|
| No log | 1.0 | 123 | 0.2308 | 0.0320 | 0.0164 | 0.5905 | 0.0 |
| No log | 2.0 | 246 | 0.0527 | 0.1882 | 0.5469 | 0.1136 | 0.1233 |
| No log | 3.0 | 369 | 0.0476 | 0.2757 | 0.3968 | 0.2113 | 0.1459 |
| No log | 4.0 | 492 | 0.0409 | 0.4130 | 0.6102 | 0.3121 | 0.2533 |
| 0.1778 | 5.0 | 615 | 0.0365 | 0.4977 | 0.6169 | 0.4170 | 0.2671 |
| 0.1778 | 6.0 | 738 | 0.0346 | 0.5304 | 0.6461 | 0.4499 | 0.2820 |
| 0.1778 | 7.0 | 861 | 0.0328 | 0.5450 | 0.6405 | 0.4743 | 0.2815 |
| 0.1778 | 8.0 | 984 | 0.0324 | 0.5528 | 0.6494 | 0.4813 | 0.2932 |
Framework versions
- Transformers 4.53.3
- Pytorch 2.6.0+cu124
- Datasets 4.4.1
- Tokenizers 0.21.2