CoolFace
Modelpublic

the-neural-networker/xlm-roberta-base-finetuned-panx-en

sourceHugging Facemitupdated 3y agoView on Hugging Face
0likes7downloads
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. -->

xlm-roberta-base-finetuned-panx-en

This model is a fine-tuned version of xlm-roberta-base on the xtreme dataset. It achieves the following results on the evaluation set:

  • —Loss: 0.5454
  • —F1: 0.7392

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: 5e-05
  • —trainbatchsize: 24
  • —evalbatchsize: 24
  • —seed: 42
  • —optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • —lrschedulertype: linear
  • —num_epochs: 10

Training results

Training LossEpochStepValidation LossF1
0.96711.0640.44690.5852
0.42382.01280.38290.6812
0.29913.01920.43790.6792
0.2284.02560.40820.7109
0.16645.03200.44200.7190
0.12026.03840.47360.7228
0.09187.04480.50680.7334
0.06818.05120.52040.7316
0.04959.05760.52730.7389
0.038310.06400.54540.7392

Framework versions

  • —Transformers 4.31.0
  • —Pytorch 2.0.1+cu117
  • —Datasets 2.14.4
  • —Tokenizers 0.13.3