donut_experiment_bayesian_trial_9

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: 0.5922
• Bleu: 0.0587
• Precisions: [0.735655737704918, 0.6310904872389791, 0.5668449197860963, 0.5173501577287066]
• Brevity Penalty: 0.0967
• Length Ratio: 0.2998
• Translation Length: 488
• Reference Length: 1628
• Cer: 0.7688
• Wer: 0.8559

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: 1.393489197537874e-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: 2
• 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
1.1982	1.0	253	0.7300	0.0555	[0.6828282828282828, 0.5616438356164384, 0.5091863517060368, 0.45987654320987653]	0.1014	0.3041	495	1628	0.7812	0.8659
0.5755	2.0	506	0.5922	0.0587	[0.735655737704918, 0.6310904872389791, 0.5668449197860963, 0.5173501577287066]	0.0967	0.2998	488	1628	0.7688	0.8559

Framework versions

• Transformers 4.40.0
• Pytorch 2.1.0
• Datasets 2.18.0
• Tokenizers 0.19.1