You can deploy this model and start earning money today!

StKirill/
layoutlmv2-base-uncased_finetuned_docvqa_v2

Name: layoutlmv2-base-uncased_finetuned_docvqa_v2
Availability: InStock

document-question-answering

generated_from_trainer

microsoft/layoutlmv2-base-uncased

finetune

cc-by-nc-sa-4.0

endpoints_compatible

Views

No views yet

layoutlmv2-base-uncased_finetuned_docvqa_v2

This model is a fine-tuned version of microsoft/layoutlmv2-base-uncased on an unknown dataset. It achieves the following results on the evaluation set:

Loss: 2.4977

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: 5e-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
num_epochs: 10

Training results

Training Loss	Epoch	Step	Validation Loss
5.1316	0.44	50	4.3296
4.3071	0.88	100	3.9311
3.8545	1.33	150	3.7061
3.6578	1.77	200	3.5642
3.2506	2.21	250	3.3789
2.9991	2.65	300	3.1969
2.7893	3.1	350	3.2842
2.3975	3.54	400	2.8765
2.1188	3.98	450	3.0513
1.9405	4.42	500	2.6575
1.7123	4.87	550	2.8113
1.6361	5.31	600	2.6848
1.5425	5.75	650	2.7986
1.2871	6.19	700	2.9508
1.1132	6.64	750	2.7070
1.1105	7.08	800	2.6293
0.8855	7.52	850	2.9005
0.9427	7.96	900	2.4977
0.8359	8.41	950	2.7100
0.7038	8.85	1000	2.8090
0.7068	9.29	1050	2.8265
0.7037	9.73	1100	2.8136

Framework versions

Transformers 4.35.0
Pytorch 2.1.0+cu118
Datasets 2.14.6
Tokenizers 0.14.1

StKirill/layoutlmv2-base-uncased_finetuned_docvqa_v2

layoutlmv2-base-uncased_finetuned_docvqa_v2

Model description

Intended uses & limitations

Training and evaluation data

Training procedure

Training hyperparameters

Training results

Framework versions

StKirill/
layoutlmv2-base-uncased_finetuned_docvqa_v2