guwenbert-large-CHED-Event Detection

This model is a fine-tuned version of ethanyt/guwenbert-large on the ched_ner dataset. It achieves the following results on the evaluation set:

  • Loss: 0.1905
  • Precision: 0.7443
  • Recall: 0.8069
  • F1: 0.7743
  • Accuracy: 0.9666

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 1.0 356 0.1420 0.6862 0.7573 0.72 0.9609
0.2304 2.0 712 0.1324 0.6907 0.7972 0.7401 0.9624
0.095 3.0 1068 0.1314 0.7268 0.7918 0.7579 0.9656
0.095 4.0 1424 0.1348 0.7248 0.7967 0.7590 0.9659
0.0613 5.0 1780 0.1525 0.7088 0.8147 0.7581 0.9635
0.0397 6.0 2136 0.1635 0.7224 0.8127 0.7649 0.9648
0.0397 7.0 2492 0.1693 0.7416 0.7986 0.7691 0.9662
0.0261 8.0 2848 0.1809 0.7338 0.8059 0.7682 0.9657
0.0164 9.0 3204 0.1904 0.7291 0.8127 0.7686 0.9655
0.0124 10.0 3560 0.1905 0.7443 0.8069 0.7743 0.9666

Framework versions

  • Transformers 4.43.4
  • Pytorch 2.3.1+cu121
  • Datasets 2.20.0
  • Tokenizers 0.19.1
Downloads last month
11
Safetensors
Model size
327M params
Tensor type
F32
·
Inference API
Unable to determine this model's library. Check the docs .

Model tree for Danielwei0214/guwenbert-large-CHED-Event_Detection

Finetuned
(2)
this model

Evaluation results