py39-pylingual-v1-segmenter
This model is a fine-tuned version of syssec-utd/py39-pylingual-v1-mlm on the syssec-utd/segmentation-py39-pylingual-v1-tokenized dataset. It achieves the following results on the evaluation set:
- Loss: 0.0087
- Precision: 0.9912
- Recall: 0.9828
- F1: 0.9869
- Accuracy: 0.9952
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: 2e-05
- train_batch_size: 48
- eval_batch_size: 8
- seed: 42
- distributed_type: multi-GPU
- optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: linear
- num_epochs: 2
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
|---|---|---|---|---|---|---|---|
| 0.0057 | 1.0 | 102151 | 0.0097 | 0.9899 | 0.9831 | 0.9865 | 0.9953 |
| 0.0033 | 2.0 | 204302 | 0.0087 | 0.9912 | 0.9828 | 0.9869 | 0.9952 |
Framework versions
- Transformers 4.48.2
- Pytorch 2.4.1+cu121
- Datasets 3.0.1
- Tokenizers 0.21.0