Hugging Face's logo

saattrupdan
/
employment-contract-ner-da

Token Classification
Transformers
PyTorch
TensorBoard
Safetensors
Danish
xlm-roberta
Inference Endpoints
Model card Files Metrics Community
2
employment-contract-ner-da / README.md
saattrupdan's picture
saattrupdan
update model card README.md
4e03af4
preview code
|
raw
history blame
No virus
4.06 kB
metadata
license: cc-by-4.0
tags:
  - generated_from_trainer
model-index:
  - name: contract-ner-model-da
    results: []

contract-ner-model-da

This model is a fine-tuned version of NbAiLab/nb-bert-base on the None dataset. It achieves the following results on the evaluation set:

  • Loss: 0.0213
  • Micro F1: 0.9217

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: 2e-05
  • train_batch_size: 8
  • eval_batch_size: 8
  • seed: 42
  • 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
  • lr_scheduler_warmup_steps: 201
  • num_epochs: 500

Training results

Training Loss Epoch Step Validation Loss Micro F1
0.2722 4.44 200 0.0318 0.6422
0.0182 8.88 400 0.0176 0.8321
0.0081 13.33 600 0.0202 0.8530
0.0045 17.77 800 0.0168 0.8839
0.0029 22.22 1000 0.0230 0.8758
0.0016 26.66 1200 0.0234 0.8690
0.0013 31.11 1400 0.0219 0.8853
0.0012 35.55 1600 0.0248 0.8831
0.0008 39.99 1800 0.0223 0.8979
0.0006 44.44 2000 0.0257 0.8752
0.0004 48.88 2200 0.0191 0.9018
0.0004 53.33 2400 0.0244 0.9029
0.0004 57.77 2600 0.0227 0.8986
0.0007 62.22 2800 0.0242 0.9004
0.0004 66.66 3000 0.0218 0.8937
0.0003 71.11 3200 0.0214 0.9039
0.0003 75.55 3400 0.0251 0.8958
0.0003 79.99 3600 0.0210 0.8943
0.0004 84.44 3800 0.0227 0.8995
0.0002 88.88 4000 0.0226 0.9116
0.0002 93.33 4200 0.0209 0.9121
0.0001 97.77 4400 0.0225 0.9105
0.0003 102.22 4600 0.0278 0.9039
0.0003 106.66 4800 0.0223 0.9009
0.0002 111.11 5000 0.0274 0.9123
0.0003 115.55 5200 0.0236 0.9123
0.0001 119.99 5400 0.0235 0.9059
0.0001 124.44 5600 0.0220 0.9165
0.0002 128.88 5800 0.0265 0.9021
0.0001 133.33 6000 0.0225 0.9029
0.0002 137.77 6200 0.0249 0.9166
0.0004 142.22 6400 0.0192 0.9128
0.0002 146.66 6600 0.0181 0.9313
0.0001 151.11 6800 0.0191 0.9269
0.0001 155.55 7000 0.0224 0.9154
0.0002 159.99 7200 0.0192 0.9171
0.0002 164.44 7400 0.0202 0.9217
0.0001 168.88 7600 0.0185 0.9171
0.0001 173.33 7800 0.0207 0.9201
0.0001 177.77 8000 0.0226 0.9121
0.0001 182.22 8200 0.0208 0.9191
0.0002 186.66 8400 0.0248 0.9184
0.0002 191.11 8600 0.0213 0.9217

Framework versions

  • Transformers 4.11.3
  • Pytorch 1.9.0+cu111
  • Datasets 1.14.0
  • Tokenizers 0.10.3