Edit model card

scenario-TCR-XLMV_data-cl-cardiff_cl_only_delta

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: 1.0448
  • Accuracy: 0.4838
  • F1: 0.4798

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: 11213
  • 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 1.09 250 1.0988 0.3333 0.1667
1.0959 2.17 500 1.0989 0.3333 0.1667
1.0959 3.26 750 1.1000 0.3333 0.1667
1.0996 4.35 1000 1.1023 0.3333 0.1667
1.0996 5.43 1250 1.0990 0.3333 0.1667
1.1001 6.52 1500 1.0997 0.3333 0.1667
1.1001 7.61 1750 1.0998 0.3333 0.1667
1.0992 8.7 2000 1.0988 0.3333 0.1667
1.0992 9.78 2250 1.0990 0.3333 0.1667
1.0998 10.87 2500 1.0992 0.3333 0.1667
1.0998 11.96 2750 1.0996 0.3333 0.1667
1.0994 13.04 3000 1.0987 0.3333 0.1667
1.0994 14.13 3250 1.0988 0.3333 0.1667
1.0993 15.22 3500 1.0993 0.3333 0.1667
1.0993 16.3 3750 1.0987 0.3333 0.1667
1.0995 17.39 4000 1.0986 0.3333 0.1667
1.0995 18.48 4250 1.0989 0.3333 0.1667
1.0991 19.57 4500 1.0989 0.3333 0.1667
1.0991 20.65 4750 1.0987 0.3333 0.1667
1.0994 21.74 5000 1.0987 0.3333 0.1667
1.0994 22.83 5250 1.0987 0.3333 0.1667
1.0991 23.91 5500 1.0987 0.3333 0.1667
1.0991 25.0 5750 1.0986 0.3333 0.1667
1.0991 26.09 6000 1.0987 0.3333 0.1667
1.0991 27.17 6250 1.0986 0.3333 0.1667
1.0946 28.26 6500 1.0796 0.4560 0.4220
1.0946 29.35 6750 1.0448 0.4838 0.4798

Framework versions

  • Transformers 4.33.3
  • Pytorch 2.1.1+cu121
  • Datasets 2.14.5
  • Tokenizers 0.13.3
Downloads last month
3

Finetuned from