Edit model card

tmp

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: 0.4127
  • Precision: 0.3197
  • Recall: 0.2438
  • F1: 0.2766

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: 1e-05
  • train_batch_size: 32
  • eval_batch_size: 32
  • seed: 42
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: constant
  • num_epochs: 3
  • mixed_precision_training: Native AMP

Training results

Training Loss Epoch Step Validation Loss Precision Recall F1
0.8182 0.35 500 0.5251 0.0 0.0 0.0
0.6835 0.7 1000 0.4857 0.0 0.0 0.0
0.6643 1.04 1500 0.4691 0.0 0.0 0.0
0.6403 1.39 2000 0.4580 0.4531 0.0349 0.0647
0.5617 1.74 2500 0.4528 0.3373 0.0673 0.1122
0.4896 2.09 3000 0.4265 0.3268 0.1611 0.2158
0.4451 2.43 3500 0.4087 0.3860 0.1791 0.2447
0.416 2.78 4000 0.4222 0.2937 0.2224 0.2531

Framework versions

  • Transformers 4.37.2
  • Pytorch 2.1.0+cu121
  • Datasets 2.17.0
  • Tokenizers 0.15.2
Downloads last month
1
Safetensors
Model size
278M params
Tensor type
F32
·

Finetuned from