layoutlmv3-finetuned-language-levels-v4

This model is a fine-tuned version of microsoft/layoutlmv3-base on the None dataset. It achieves the following results on the evaluation set:

  • Loss: 0.0013
  • Precision: 1.0
  • Recall: 1.0
  • F1: 1.0
  • Accuracy: 1.0

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-05
  • 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: 1000

Training results

Training Loss Epoch Step Validation Loss Precision Recall F1 Accuracy
No log 0.0290 100 0.0100 1.0 1.0 1.0 1.0
No log 0.0579 200 0.0036 1.0 1.0 1.0 1.0
No log 0.0869 300 0.0022 1.0 1.0 1.0 1.0
No log 0.1158 400 0.0016 1.0 1.0 1.0 1.0
0.0123 0.1448 500 0.0013 1.0 1.0 1.0 1.0
0.0123 0.1738 600 0.0011 1.0 1.0 1.0 1.0
0.0123 0.2027 700 0.0010 1.0 1.0 1.0 1.0
0.0123 0.2317 800 0.0009 1.0 1.0 1.0 1.0
0.0123 0.2606 900 0.0008 1.0 1.0 1.0 1.0
0.0018 0.2896 1000 0.0008 1.0 1.0 1.0 1.0

Framework versions

  • Transformers 4.43.3
  • Pytorch 2.1.0+cu118
  • Datasets 2.20.0
  • Tokenizers 0.19.1
Downloads last month
111
Safetensors
Model size
126M params
Tensor type
F32
·
Inference Providers NEW
This model is not currently available via any of the supported Inference Providers.

Model tree for lamiaaEl/layoutlmv3-finetuned-language-levels-v4

Finetuned
(243)
this model