Ariffiq99's picture
End of training
d0283fe verified
metadata
license: mit
base_model: Ariffiq99/CRAB_COPA_xlm_roberta_base_finetuned
tags:
  - generated_from_trainer
metrics:
  - f1
model-index:
  - name: e_care_CRAB_COPA_xlm_roberta_base_finetuned
    results: []

e_care_CRAB_COPA_xlm_roberta_base_finetuned

This model is a fine-tuned version of Ariffiq99/CRAB_COPA_xlm_roberta_base_finetuned on an unknown dataset. It achieves the following results on the evaluation set:

  • Loss: 0.5909
  • F1: 0.6956

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: 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: 7

Training results

Training Loss Epoch Step Validation Loss F1
0.6982 1.0 933 0.6295 0.6084
0.6346 2.0 1866 0.5949 0.6329
0.5924 3.0 2799 0.5665 0.6753
0.5466 4.0 3732 0.5624 0.6871
0.5054 5.0 4665 0.5662 0.6861
0.4716 6.0 5598 0.5790 0.6989
0.4426 7.0 6531 0.5909 0.6956

Framework versions

  • Transformers 4.41.1
  • Pytorch 2.3.0+cu121
  • Datasets 2.19.2
  • Tokenizers 0.19.1