metadata

tags:
  - generated_from_trainer
datasets:
  - cord
metrics:
  - precision
  - recall
  - f1
  - accuracy
model-index:
  - name: layoutlmv3-finetuned-cord
    results:
      - task:
          name: Token Classification
          type: token-classification
        dataset:
          name: cord
          type: cord
          args: cord
        metrics:
          - name: Precision
            type: precision
            value: 0.9190581309786607
          - name: Recall
            type: recall
            value: 0.9348802395209581
          - name: F1
            type: f1
            value: 0.9269016697588126
          - name: Accuracy
            type: accuracy
            value: 0.9384550084889643

layoutlmv3-finetuned-cord

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

Loss: 0.3056
Precision: 0.9191
Recall: 0.9349
F1: 0.9269
Accuracy: 0.9385

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: 16
eval_batch_size: 16
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	2.0	100	1.6054	0.52	0.6130	0.5627	0.6367
No log	4.0	200	0.9172	0.7923	0.8278	0.8097	0.8315
No log	6.0	300	0.6382	0.8367	0.8630	0.8497	0.8667
No log	8.0	400	0.4974	0.8648	0.8907	0.8776	0.8960
1.1589	10.0	500	0.4124	0.8769	0.9064	0.8914	0.9164
1.1589	12.0	600	0.3767	0.8961	0.9169	0.9064	0.9236
1.1589	14.0	700	0.3388	0.9120	0.9304	0.9211	0.9338
1.1589	16.0	800	0.3138	0.9198	0.9356	0.9276	0.9393
1.1589	18.0	900	0.3073	0.9176	0.9334	0.9254	0.9376
0.2992	20.0	1000	0.3056	0.9191	0.9349	0.9269	0.9385

Framework versions

Transformers 4.19.0.dev0
Pytorch 1.11.0+cu113
Datasets 2.0.0
Tokenizers 0.11.6