Output_LayoutLMv3_v1

This model is a fine-tuned version of microsoft/layoutlmv3-large on an unknown dataset. It achieves the following results on the evaluation set:

  • Loss: 0.2030
  • Precision: 0.8
  • Recall: 0.8319
  • F1: 0.8156
  • Accuracy: 0.9743

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: 1e-06
  • train_batch_size: 2
  • eval_batch_size: 2
  • seed: 42
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: linear
  • training_steps: 3000

Training results

Training Loss Epoch Step Validation Loss Precision Recall F1 Accuracy
No log 2.27 100 0.3343 0.2051 0.0354 0.0604 0.8943
No log 4.55 200 0.1934 0.7143 0.6858 0.6998 0.9524
No log 6.82 300 0.1541 0.7344 0.7832 0.7580 0.9590
No log 9.09 400 0.1375 0.7542 0.8009 0.7768 0.9648
0.2233 11.36 500 0.1323 0.7915 0.8230 0.8069 0.9695
0.2233 13.64 600 0.1395 0.8 0.8142 0.8070 0.9695
0.2233 15.91 700 0.1495 0.7773 0.8186 0.7974 0.9686
0.2233 18.18 800 0.1444 0.8103 0.8319 0.8210 0.9752
0.2233 20.45 900 0.1732 0.7550 0.8319 0.7916 0.9676
0.0375 22.73 1000 0.1553 0.7966 0.8319 0.8139 0.9743
0.0375 25.0 1100 0.1639 0.7924 0.8274 0.8095 0.9724
0.0375 27.27 1200 0.1598 0.8034 0.8319 0.8174 0.9752
0.0375 29.55 1300 0.1723 0.8069 0.8319 0.8192 0.9743
0.0375 31.82 1400 0.1929 0.7810 0.8363 0.8077 0.9724
0.0188 34.09 1500 0.1940 0.7866 0.8319 0.8086 0.9714
0.0188 36.36 1600 0.1904 0.7932 0.8319 0.8121 0.9724
0.0188 38.64 1700 0.1910 0.7899 0.8319 0.8103 0.9724
0.0188 40.91 1800 0.2083 0.7801 0.8319 0.8051 0.9705
0.0188 43.18 1900 0.1880 0.8 0.8319 0.8156 0.9743
0.0123 45.45 2000 0.1902 0.8069 0.8319 0.8192 0.9752
0.0123 47.73 2100 0.1894 0.8095 0.8274 0.8184 0.9752
0.0123 50.0 2200 0.1833 0.8210 0.8319 0.8264 0.9771
0.0123 52.27 2300 0.1911 0.8069 0.8319 0.8192 0.9752
0.0123 54.55 2400 0.1972 0.8 0.8319 0.8156 0.9743
0.0086 56.82 2500 0.1924 0.8139 0.8319 0.8228 0.9762
0.0086 59.09 2600 0.1983 0.8 0.8319 0.8156 0.9743
0.0086 61.36 2700 0.2033 0.8 0.8319 0.8156 0.9743
0.0086 63.64 2800 0.2039 0.8 0.8319 0.8156 0.9743
0.0086 65.91 2900 0.2026 0.8 0.8319 0.8156 0.9743
0.0084 68.18 3000 0.2030 0.8 0.8319 0.8156 0.9743

Framework versions

  • Transformers 4.38.2
  • Pytorch 2.2.1+cu121
  • Datasets 2.18.0
  • Tokenizers 0.15.2
Downloads last month
24
Safetensors
Model size
356M params
Tensor type
F32
·
Inference Examples
This model does not have enough activity to be deployed to Inference API (serverless) yet. Increase its social visibility and check back later, or deploy to Inference Endpoints (dedicated) instead.

Model tree for Noureddinesa/Output_LayoutLMv3_v1

Finetuned
(6)
this model