metadata

license: cc-by-nc-sa-4.0
base_model: microsoft/layoutlmv3-base
tags:
  - generated_from_trainer
metrics:
  - precision
  - recall
  - f1
  - accuracy
model-index:
  - name: test
    results: []

test

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

Loss: 0.0314
Precision: 0.0
Recall: 0.0
F1: 0.0
Accuracy: 0.9933

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: 8
eval_batch_size: 8
seed: 42
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: linear
training_steps: 40000

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
0.0381	0.13	500	0.0777	0.9745
0.0669	0.26	1000	0.0545	0.9790
0.0595	0.39	1500	0.0545	0.9803
0.054	0.52	2000	0.0555	0.9796
0.0502	0.65	2500	0.0451	0.9828
0.0474	0.78	3000	0.0486	0.9818
0.0458	0.92	3500	0.0417	0.9836
0.0415	1.05	4000	0.0440	0.9827
0.0372	1.18	4500	0.0432	0.9839
0.0391	1.31	5000	0.0442	0.9839
0.0368	1.44	5500	0.0377	0.9856
0.0388	1.57	6000	0.0417	0.9846
0.0351	1.7	6500	0.0363	0.9857
0.0357	1.83	7000	0.0383	0.9858
0.0336	1.96	7500	0.0371	0.9860
0.0309	2.09	8000	0.0373	0.9859
0.0288	2.22	8500	0.0355	0.9870
0.0288	2.35	9000	0.0359	0.9867
0.0285	2.49	9500	0.0369	0.9872
0.0307	2.62	10000	0.0322	0.9880
0.028	2.75	10500	0.0307	0.9886
0.0246	2.88	11000	0.0326	0.9881
0.0267	3.01	11500	0.0346	0.9882
0.022	3.14	12000	0.0316	0.9889
0.0218	3.27	12500	0.0357	0.9883
0.0217	3.4	13000	0.0363	0.9883
0.0208	3.53	13500	0.0340	0.9894
0.0223	3.66	14000	0.0304	0.9892
0.0232	3.79	14500	0.0319	0.9894
0.0229	3.92	15000	0.0307	0.9901
0.0192	4.06	15500	0.0310	0.9905
0.0178	4.19	16000	0.0345	0.9897
0.0178	4.32	16500	0.0309	0.9902
0.0173	4.45	17000	0.0328	0.9904
0.0176	4.58	17500	0.0316	0.9908
0.017	4.71	18000	0.0307	0.9912
0.0163	4.84	18500	0.0329	0.9909
0.018	4.97	19000	0.0295	0.9910
0.0143	5.1	19500	0.0367	0.9903
0.0144	5.23	20000	0.0317	0.9915
0.0158	5.36	20500	0.0290	0.9917
0.0143	5.49	21000	0.0315	0.9917
0.0137	5.63	21500	0.0310	0.9913
0.0135	5.76	22000	0.0310	0.9913
0.0128	5.89	22500	0.0290	0.9917
0.0132	6.02	23000	0.0314	0.9921
0.0124	6.15	23500	0.0274	0.9921
0.0114	6.28	24000	0.0300	0.9921
0.0111	6.41	24500	0.0291	0.9922
0.0109	6.54	25000	0.0307	0.9923
0.0117	6.67	25500	0.0328	0.9921
0.0112	6.8	26000	0.0293	0.9924
0.012	6.93	26500	0.0300	0.9924
0.0102	7.06	27000	0.0330	0.9921
0.0094	7.2	27500	0.0323	0.9922
0.0091	7.33	28000	0.0309	0.9924
0.0087	7.46	28500	0.0331	0.9920
0.0091	7.59	29000	0.0332	0.9923
0.0095	7.72	29500	0.0298	0.9925
0.0083	7.85	30000	0.0303	0.9929
0.0097	7.98	30500	0.0298	0.9928
0.0069	8.11	31000	0.0319	0.9926
0.0086	8.24	31500	0.0314	0.9929
0.0079	8.37	32000	0.0306	0.9929
0.0065	8.5	32500	0.0317	0.9926
0.0072	8.63	33000	0.0307	0.9927
0.0082	8.77	33500	0.0306	0.9929
0.0086	8.9	34000	0.0312	0.9931
0.0079	9.03	34500	0.0329	0.9929
0.0061	9.16	35000	0.0326	0.9928
0.0074	9.29	35500	0.0315	0.9928
0.0068	9.42	36000	0.0310	0.9931
0.0059	9.55	36500	0.0318	0.9930
0.0064	9.68	37000	0.0307	0.9933
0.0063	9.81	37500	0.0308	0.9930
0.0062	9.94	38000	0.0311	0.9931
0.0058	10.07	38500	0.0314	0.9932
0.0051	10.2	39000	0.0316	0.9933
0.0065	10.33	39500	0.0315	0.9933
0.0059	10.47	40000	0.0314	0.9933

Framework versions

Transformers 4.35.2
Pytorch 2.1.0+cu121
Datasets 2.15.0
Tokenizers 0.15.0