music_layoutlmv3_model

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

• Loss: 0.0083
• Precision: 0.9627
• Recall: 0.9773
• F1: 0.9699
• Accuracy: 0.9990

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	8.33	100	0.0191	0.9338	0.9621	0.9478	0.9981
No log	16.67	200	0.0120	0.9412	0.9697	0.9552	0.9981
No log	25.0	300	0.0125	0.9412	0.9697	0.9552	0.9981
No log	33.33	400	0.0101	0.9412	0.9697	0.9552	0.9981
0.0527	41.67	500	0.0121	0.9412	0.9697	0.9552	0.9981
0.0527	50.0	600	0.0083	0.9627	0.9773	0.9699	0.9990
0.0527	58.33	700	0.0082	0.9627	0.9773	0.9699	0.9990
0.0527	66.67	800	0.0082	0.9627	0.9773	0.9699	0.9990
0.0527	75.0	900	0.0083	0.9627	0.9773	0.9699	0.9990
0.0006	83.33	1000	0.0083	0.9627	0.9773	0.9699	0.9990

Framework versions

• Transformers 4.28.0.dev0
• Pytorch 1.13.1+cu116
• Datasets 2.2.2
• Tokenizers 0.13.2