donut-base-sroie-metrics-combined-new-fixed-version

This model is a fine-tuned version of naver-clova-ix/donut-base on the None dataset. It achieves the following results on the evaluation set:

• Loss: 0.4187
• Bleu: 0.0659
• Precisions: [0.8259958071278826, 0.7547619047619047, 0.7107438016528925, 0.6601307189542484]
• Brevity Penalty: 0.0895
• Length Ratio: 0.2930
• Translation Length: 477
• Reference Length: 1628
• Cer: 0.7531
• Wer: 0.8260

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: 2e-05
• train_batch_size: 1
• eval_batch_size: 1
• seed: 42
• gradient_accumulation_steps: 2
• total_train_batch_size: 2
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 4
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Bleu	Precisions	Brevity Penalty	Length Ratio	Translation Length	Reference Length	Cer	Wer
0.9081	1.0	253	0.5714	0.0513	[0.7483731019522777, 0.6584158415841584, 0.6138328530259366, 0.5724137931034483]	0.0795	0.2832	461	1628	0.7796	0.8572
0.3952	2.0	506	0.4489	0.0579	[0.7913978494623656, 0.7254901960784313, 0.6809116809116809, 0.6360544217687075]	0.0820	0.2856	465	1628	0.7632	0.8394
0.3077	3.0	759	0.4266	0.0666	[0.8218029350104822, 0.7642857142857142, 0.721763085399449, 0.673202614379085]	0.0895	0.2930	477	1628	0.7556	0.8273
0.2307	4.0	1012	0.4187	0.0659	[0.8259958071278826, 0.7547619047619047, 0.7107438016528925, 0.6601307189542484]	0.0895	0.2930	477	1628	0.7531	0.8260

Framework versions

• Transformers 4.40.2
• Pytorch 2.1.0
• Datasets 2.18.0
• Tokenizers 0.19.1