CoolFace
Modelpublic

Arunavaonly/Bangla-twoclass-Sentiment-Analyzer

sourceHugging Facemitupdated 3y agoView on Hugging Face
1likes421kdownloads
Model Card

<!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. -->

Bangla-Twoclass-Sentiment-Analyzer

This model is a fine-tuned version of xlm-roberta-base on the None dataset. It achieves the following results on the evaluation set:

  • —Loss: 2.7755
  • —F1: 0.6113

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: 3e-05
  • —trainbatchsize: 16
  • —evalbatchsize: 16
  • —seed: 42
  • —optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • —lrschedulertype: linear
  • —training_steps: 1800
  • —mixedprecisiontraining: Native AMP

Training results

Training LossEpochStepValidation LossF1
No log2.532000.98690.4635
No log5.064000.89780.5858
0.86927.596001.19780.6149
0.869210.138001.51450.6112
0.313812.6610002.03530.6041
0.313815.1912002.43160.6203
0.313817.7214002.60250.6002
0.076920.2516002.62470.6082
0.076922.7818002.77550.6113

Framework versions

  • —Transformers 4.37.2
  • —Pytorch 2.1.0+cu121
  • —Datasets 2.17.1
  • —Tokenizers 0.15.2