Hugging Face's logo

haturusinghe
/
XLM-R-BASE-Finetune-step2-finetune-and-eval-may31-volcanic-moon-1-D-05-31-T-03-38

Text Classification
Transformers
Safetensors
xlm-roberta
Generated from Trainer
Inference Endpoints
Model card Files Community
XLM-R-BASE-Finetune-step2-finetune-and-eval-may31-volcanic-moon-1-D-05-31-T-03-38 / README.md
haturusinghe's picture
haturusinghe
End of training
5a12498 verified
preview code
|
raw
history blame
2.77 kB
metadata
license: mit
base_model: xlm-roberta-base
tags:
  - generated_from_trainer
model-index:
  - name: >-
      XLM-R-BASE-Finetune-step2-finetune-and-eval-may31-volcanic-moon-1-D-05-31-T-03-38
    results: []

XLM-R-BASE-Finetune-step2-finetune-and-eval-may31-volcanic-moon-1-D-05-31-T-03-38

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

  • Loss: 0.3977
  • Precision 0: 0.8721
  • Precision 1: 0.8029
  • Recall 0: 0.8633
  • Recall 1: 0.8148
  • F1 0: 0.8677
  • F1 1: 0.8088
  • Precision Weighted: 0.8440
  • Recall Weighted: 0.8436
  • F1 Weighted: 0.8438
  • F1 Macro: 0.8382

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: 2e-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
  • lr_scheduler_warmup_ratio: 0.1
  • num_epochs: 5

Training results

Training Loss Epoch Step Validation Loss Precision 0 Precision 1 Recall 0 Recall 1 F1 0 F1 1 Precision Weighted Recall Weighted F1 Weighted F1 Macro
0.5501 1.0 469 0.4524 0.7699 0.8995 0.9556 0.5823 0.8528 0.7069 0.8226 0.804 0.7936 0.7799
0.3869 2.0 938 0.4545 0.8995 0.7229 0.7710 0.8739 0.8303 0.7913 0.8278 0.8128 0.8145 0.8108
0.3825 3.0 1407 0.3678 0.8429 0.8191 0.8855 0.7586 0.8637 0.7877 0.8333 0.834 0.8329 0.8257
0.2683 4.0 1876 0.3977 0.8721 0.8029 0.8633 0.8148 0.8677 0.8088 0.8440 0.8436 0.8438 0.8382
0.2297 5.0 2345 0.5155 0.8711 0.7937 0.8552 0.8148 0.8631 0.8041 0.8396 0.8388 0.8391 0.8336

Framework versions

  • Transformers 4.41.2
  • Pytorch 2.3.0+cu121
  • Datasets 2.19.1
  • Tokenizers 0.19.1