Edit model card

robbert-twitter-sentiment-tokenized

This model is a fine-tuned version of pdelobelle/robbert-v2-dutch-base on the dutch_social dataset. It achieves the following results on the evaluation set:

  • Loss: 0.5473
  • Accuracy: 0.814
  • F1: 0.8133
  • Precision: 0.8131
  • Recall: 0.814

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
  • 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: 3

Training results

Training Loss Epoch Step Validation Loss Accuracy F1 Precision Recall
0.6895 1.0 282 0.6307 0.7433 0.7442 0.7500 0.7433
0.4948 2.0 564 0.5189 0.8053 0.8062 0.8081 0.8053
0.2642 3.0 846 0.5473 0.814 0.8133 0.8131 0.814

Framework versions

  • Transformers 4.17.0
  • Pytorch 1.11.0+cpu
  • Datasets 2.0.0
  • Tokenizers 0.11.6
Downloads last month
30
Hosted inference API
Text Classification
Examples
Examples
This model can be loaded on the Inference API on-demand.

Dataset used to train btjiong/robbert-twitter-sentiment-tokenized

Evaluation results