py311 pylingual v1 segmenter This model is a fine tuned version of syssec utd/py311 pylingual v1 mlm on the syssec utd/segmentation py311 pylingual v1 tokenized dataset. It achieves the following results on the evaluation set: Loss: 0.0046 Precision: 0.9958 Recall: 0.9937 F1: 0.9948 Accuracy: 0.9983 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 : : : : : : : : : : : : : : : : 0.0049 1.0 163974 0.0038 0.9964 0.9951 0.9958 0.9986 0.0029 2.0 327948 0.0046 0.9958 0.9937 0.9948 0.9983 Framework versions Transformers 4.48.2 Pytorch 2.4.1+cu121 Datasets 3.0.1 Tokenizers 0.21.0
We use cookies for essential functionality and analytics. You can accept or reject analytics cookies.Cookie policy