Edit model card

uzroberta-sentiment-analysis

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: 1.0473
  • Accuracy: 0.8257
  • F1: 0.8287

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: 16
  • eval_batch_size: 16
  • seed: 42
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: linear
  • num_epochs: 6

Training results

Training Loss Epoch Step Validation Loss Accuracy F1
0.3411 1.0 1156 0.4061 0.8276 0.8303
0.2319 2.0 2312 0.4074 0.8336 0.8359
0.1629 3.0 3468 0.5250 0.8394 0.8416
0.1082 4.0 4624 0.8780 0.8180 0.8219
0.0712 5.0 5780 0.9741 0.8321 0.8349
0.0537 6.0 6936 1.0473 0.8257 0.8287

Framework versions

  • Transformers 4.27.3
  • Pytorch 2.0.0+cu117
  • Datasets 2.11.0
  • Tokenizers 0.12.1
Downloads last month
34
Safetensors
Model size
83.5M params
Tensor type
I64
·
F32
·

Space using murodbek/uzroberta-sentiment-analysis 1