haturusinghe's picture
End of training
f452204 verified
metadata
license: mit
base_model: xlm-roberta-base
tags:
  - generated_from_trainer
metrics:
  - accuracy
model-index:
  - name: XLM-R-BASE-VanillaFT-5E-spring-feather-1-D-08-03-T-08-15
    results: []

XLM-R-BASE-VanillaFT-5E-spring-feather-1-D-08-03-T-08-15

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: 0.4196
  • Precision 0: 0.8318
  • Precision 1: 0.7503
  • Recall 0: 0.8119
  • Recall 1: 0.7767
  • F1 0: 0.8217
  • F1 1: 0.7633
  • Precision Weighted: 0.7987
  • Recall Weighted: 0.7976
  • F1 Weighted: 0.7980
  • Accuracy: 0.7976
  • F1 Macro: 0.7925

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: 402
  • 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 Accuracy F1 Macro
0.5481 1.0 469 0.4437 0.7838 0.7441 0.8226 0.6900 0.8028 0.7161 0.7677 0.7688 0.7676 0.7688 0.7594
0.4178 2.0 938 0.4403 0.8529 0.6988 0.7519 0.8211 0.7994 0.7553 0.7904 0.7800 0.7815 0.7800 0.7773
0.3416 3.0 1407 0.4196 0.8318 0.7503 0.8119 0.7767 0.8217 0.7633 0.7987 0.7976 0.7980 0.7976 0.7925
0.2757 4.0 1876 0.4393 0.8430 0.7153 0.7735 0.8024 0.8068 0.7565 0.7912 0.7852 0.7864 0.7852 0.7816
0.2231 5.0 2345 0.4908 0.8343 0.7418 0.8031 0.7827 0.8184 0.7617 0.7968 0.7948 0.7954 0.7948 0.7901

Framework versions

  • Transformers 4.43.3
  • Pytorch 2.3.1+cu121
  • Datasets 2.20.0
  • Tokenizers 0.19.1