Edit model card

distilbert-base-cased-finetuned-ner-geocorpus

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

  • Loss: 0.1175
  • Precision: 0.8176
  • Recall: 0.8651
  • F1: 0.8407
  • Accuracy: 0.9738

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: 16
  • eval_batch_size: 16
  • seed: 42
  • 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
No log 1.0 276 0.2104 0.6062 0.5413 0.5719 0.9489
0.2898 2.0 552 0.1456 0.7940 0.7310 0.7612 0.9648
0.2898 3.0 828 0.1225 0.7652 0.8021 0.7832 0.9671
0.1039 4.0 1104 0.1131 0.7590 0.8291 0.7925 0.9691
0.1039 5.0 1380 0.1086 0.8 0.8307 0.8151 0.9712
0.0585 6.0 1656 0.1188 0.7685 0.8741 0.8179 0.9689
0.0585 7.0 1932 0.1115 0.8009 0.8684 0.8333 0.9724
0.0349 8.0 2208 0.1196 0.8026 0.8708 0.8353 0.9728
0.0349 9.0 2484 0.1155 0.8317 0.8487 0.8401 0.9738
0.0235 10.0 2760 0.1175 0.8176 0.8651 0.8407 0.9738

Framework versions

  • Transformers 4.41.1
  • Pytorch 2.1.2
  • Datasets 2.19.1
  • Tokenizers 0.19.1
Downloads last month
8
Safetensors
Model size
65.2M params
Tensor type
F32
·
Inference API
Unable to determine this model's library. Check the docs .

Model tree for GuiTap/distilbert-base-cased-finetuned-ner-geocorpus

Finetuned
(213)
this model