py313 pylingual v1.3 segmenter This model is a fine tuned version of syssec utd/py313 pylingual v1.3 mlm on the syssec utd/segmentation py313 pylingual v2 tokenized dataset. It achieves the following results on the evaluation set: Loss: 0.0007 Precision: 0.9985 Recall: 0.9980 F1: 0.9982 Accuracy: 0.9996 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 num devices: 3 total train batch size: 144 total eval batch size: 24 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 num epochs: 2 mixed precision training: Native AMP Training results Training Loss Epoch Step Validation Loss Precision Recall F1 Accuracy : : : : : : : : : : : : : : : : 0.0079 1.0 32225 0.0008 0.9988 0.9985 0.9987 0.9997 0.0043 2.0 64450 0.0007 0.9985 0.9980 0.9982 0.9996 Framework versions Transformers 4.55.4…
We use cookies for essential functionality and analytics. You can accept or reject analytics cookies.Cookie policy