scenario-kd-scr-ner-full-xlmr-halfen_data-univner_en66

This model is a fine-tuned version of haryoaw/scenario-TCR-NER_data-univner_half on the None dataset. It achieves the following results on the evaluation set:

  • Loss: 250.6721
  • Precision: 0.4368
  • Recall: 0.2754
  • F1: 0.3378
  • Accuracy: 0.9532

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: 3e-05
  • train_batch_size: 8
  • eval_batch_size: 32
  • seed: 66
  • gradient_accumulation_steps: 4
  • total_train_batch_size: 32
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: linear
  • num_epochs: 10

Training results

Training Loss Epoch Step Validation Loss Precision Recall F1 Accuracy
426.5331 1.28 500 343.1131 0.4717 0.0259 0.0491 0.9413
317.8317 2.55 1000 306.4857 0.3815 0.1066 0.1667 0.9449
288.4479 3.83 1500 285.8158 0.4429 0.1284 0.1990 0.9461
270.6268 5.1 2000 271.5317 0.3921 0.2050 0.2692 0.9494
257.3109 6.38 2500 260.7265 0.3853 0.2381 0.2943 0.9517
248.4864 7.65 3000 253.9278 0.3950 0.2940 0.3371 0.9527
242.8456 8.93 3500 250.6721 0.4368 0.2754 0.3378 0.9532

Framework versions

  • Transformers 4.33.3
  • Pytorch 2.1.1+cu121
  • Datasets 2.14.5
  • Tokenizers 0.13.3
Downloads last month
10
Inference API
Unable to determine this model's library. Check the docs .

Model tree for haryoaw/scenario-kd-scr-ner-full-xlmr-halfen_data-univner_en66