scenario-kd-po-ner-full-xlmr_data-univner_half66

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: 53.5934
  • Precision: 0.7914
  • Recall: 0.7922
  • F1: 0.7918
  • Accuracy: 0.9789

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
93.9811 0.5828 500 77.1719 0.7802 0.7262 0.7522 0.9755
69.0206 1.1655 1000 70.2429 0.7554 0.7718 0.7635 0.9766
62.467 1.7483 1500 66.3316 0.7886 0.7455 0.7664 0.9767
58.5858 2.3310 2000 63.5450 0.7970 0.7396 0.7672 0.9768
55.7072 2.9138 2500 61.1857 0.7871 0.7772 0.7821 0.9783
53.5041 3.4965 3000 59.5353 0.7816 0.7843 0.7829 0.9783
51.8153 4.0793 3500 58.3157 0.7938 0.7863 0.7900 0.9786
50.327 4.6620 4000 57.1124 0.7914 0.7905 0.7910 0.9788
49.2402 5.2448 4500 56.3184 0.7844 0.7986 0.7914 0.9789
48.2334 5.8275 5000 55.7867 0.7922 0.7862 0.7892 0.9787
47.4646 6.4103 5500 55.2770 0.7955 0.7818 0.7886 0.9785
46.8764 6.9930 6000 54.6109 0.7958 0.7826 0.7891 0.9788
46.3099 7.5758 6500 54.2702 0.8051 0.7830 0.7939 0.9792
45.8877 8.1585 7000 53.9679 0.7953 0.7917 0.7935 0.9792
45.5735 8.7413 7500 53.7160 0.7935 0.7907 0.7921 0.9787
45.3573 9.3240 8000 53.6114 0.7886 0.7919 0.7903 0.9791
45.2644 9.9068 8500 53.5934 0.7914 0.7922 0.7918 0.9789

Framework versions

  • Transformers 4.44.2
  • Pytorch 2.1.1+cu121
  • Datasets 2.14.5
  • Tokenizers 0.19.1
Downloads last month
10
Safetensors
Model size
235M params
Tensor type
F32
·
Inference API
Unable to determine this model’s pipeline type. Check the docs .

Model tree for haryoaw/scenario-kd-po-ner-full-xlmr_data-univner_half66