50b872b03be8ea1de2b56990675689b8

This model is a fine-tuned version of FacebookAI/xlm-roberta-large-finetuned-conll02-dutch on the contemmcm/hate-speech-and-offensive-language dataset. It achieves the following results on the evaluation set:

  • Loss: 0.6782
  • Data Size: 0.25
  • Epoch Runtime: 34.1089
  • Accuracy: 0.7672
  • F1 Macro: 0.2894

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: 8
  • eval_batch_size: 8
  • seed: 42
  • distributed_type: multi-GPU
  • num_devices: 4
  • total_train_batch_size: 32
  • total_eval_batch_size: 32
  • optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
  • lr_scheduler_type: constant
  • num_epochs: 50

Training results

Training Loss Epoch Step Validation Loss Data Size Epoch Runtime Accuracy F1 Macro
No log 0 0 0.9577 0 7.8524 0.7646 0.2914
No log 1 619 0.6718 0.0078 8.7690 0.7672 0.2894
No log 2 1238 0.6317 0.0156 10.2849 0.7672 0.2894
0.0159 3 1857 0.6548 0.0312 12.7261 0.7672 0.2894
0.0159 4 2476 0.6813 0.0625 15.8751 0.7672 0.2894
0.665 5 3095 0.6862 0.125 22.1784 0.7672 0.2894
0.0642 6 3714 0.6782 0.25 34.1089 0.7672 0.2894

Framework versions

  • Transformers 4.57.0
  • Pytorch 2.8.0+cu128
  • Datasets 4.3.0
  • Tokenizers 0.22.1
Downloads last month
15
Safetensors
Model size
0.6B params
Tensor type
F32
ยท
Inference Providers NEW
This model isn't deployed by any Inference Provider. ๐Ÿ™‹ Ask for provider support

Model tree for contemmcm/50b872b03be8ea1de2b56990675689b8

Finetuned
(20)
this model

Evaluation results