murodbek

This model is a fine-tuned version of rifkat/uztext-3Gb-BPE-Roberta on the None dataset. It achieves the following results on the evaluation set: - Loss: 0.1626 - F1: 0.9175 The following hyperparameters were used during training: - learningrate: 5e-05 - trainbatchsize: 16 - evalbatchsize: 16 - seed: 42 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lrschedulertype: linear - numepochs: 5 | Training Loss | Epoch | Step | Validation Loss | F1 | |:-------------:|:-----:|:----:|:---------------:|:------:| | 0.0515 | 1.0 | 150 | 0.1373 | 0.9141 | | 0.0415 | 2.0 | 300 | 0.1268 | 0.9194 | | 0.0101 | 3.0 | 450 | 0.1225 | 0.9416 | | 0.0038 | 4.0 | 600 | 0.1426 | 0.9353 | | 0.0004 | 5.0 | 750 | 0.1458 | 0.9320 | - Transformers 4.27.3 - Pytorch 2.0.0+cu117 - Datasets 2.11.0 - Tokenizers 0.12.1