Edit model card

scenario-TCR-XLMV_data-en-cardiff_eng_only_alpha

This model is a fine-tuned version of facebook/xlm-v-base on the None dataset. It achieves the following results on the evaluation set:

  • Loss: 1.0987
  • Accuracy: 0.3333
  • F1: 0.1667

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: 32
  • eval_batch_size: 32
  • seed: 1123
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: linear
  • num_epochs: 30

Training results

Training Loss Epoch Step Validation Loss Accuracy F1
No log 1.03 60 1.0986 0.3333 0.1667
No log 2.07 120 1.0986 0.3333 0.1667
No log 3.1 180 1.0991 0.3329 0.1665
No log 4.14 240 1.0987 0.3333 0.1667
No log 5.17 300 1.0988 0.3333 0.1667
No log 6.21 360 1.0990 0.3333 0.1667
No log 7.24 420 1.0993 0.3333 0.1667
No log 8.28 480 1.0987 0.3333 0.1667
1.0995 9.31 540 1.0988 0.3333 0.1667
1.0995 10.34 600 1.0987 0.3333 0.1667
1.0995 11.38 660 1.0988 0.3333 0.1667
1.0995 12.41 720 1.0988 0.3333 0.1667
1.0995 13.45 780 1.0999 0.3333 0.1667
1.0995 14.48 840 1.1007 0.3333 0.1667
1.0995 15.52 900 1.0988 0.3338 0.1685
1.0995 16.55 960 1.0987 0.3333 0.1667
1.1001 17.59 1020 1.0990 0.3333 0.1667
1.1001 18.62 1080 1.0989 0.3333 0.1667
1.1001 19.66 1140 1.0986 0.3333 0.1667
1.1001 20.69 1200 1.0987 0.3333 0.1667
1.1001 21.72 1260 1.0989 0.3333 0.1667
1.1001 22.76 1320 1.0988 0.3333 0.1667
1.1001 23.79 1380 1.0986 0.3333 0.1667
1.1001 24.83 1440 1.0986 0.3333 0.1667
1.0992 25.86 1500 1.0986 0.3333 0.1667
1.0992 26.9 1560 1.0986 0.3333 0.1667
1.0992 27.93 1620 1.0987 0.3333 0.1667
1.0992 28.97 1680 1.0987 0.3333 0.1667
1.0992 30.0 1740 1.0987 0.3333 0.1667

Framework versions

  • Transformers 4.33.3
  • Pytorch 2.1.1+cu121
  • Datasets 2.14.5
  • Tokenizers 0.13.3
Downloads last month
4

Finetuned from