py310 pylingual v1 segmenter This model is a fine tuned version of syssec utd/py310 pylingual v1 mlm on the syssec utd/segmentation py310 pylingual v1 tokenized dataset. It achieves the following results on the evaluation set: Loss: 0.0069 Precision: 0.9931 Recall: 0.9901 F1: 0.9916 Accuracy: 0.9977 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 : : : : : : : : : : : : : : : : 0.0052 1.0 192889 0.0072 0.9923 0.9885 0.9904 0.9973 0.0032 2.0 385778 0.0069 0.9931 0.9901 0.9916 0.9977 Framework versions Transformers 4.48.2 Pytorch 2.2.1+cu121 Datasets 2.18.0 Tokenizers 0.21.0
We use cookies for essential functionality and analytics. You can accept or reject analytics cookies.Cookie policy