Hugging Face's logo

YufeiWeng
/
donut-base-beans

Image Classification
Transformers
Safetensors
beit
vision
Generated from Trainer
Inference Endpoints
Model card Files Community
donut-base-beans / README.md
YufeiWeng's picture
YufeiWeng
End of training
e787da3 verified
preview code
|
raw
history blame
4.72 kB
metadata
base_model: microsoft/dit-base-finetuned-rvlcdip
tags:
  - image-classification
  - vision
  - generated_from_trainer
metrics:
  - f1
model-index:
  - name: donut-base-beans
    results: []

donut-base-beans

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

  • Loss: 0.0404
  • F1: 0.6134

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: 3e-05
  • train_batch_size: 64
  • eval_batch_size: 64
  • seed: 1337
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: linear
  • training_steps: 10000

Training results

Training Loss Epoch Step F1 Validation Loss
0.1165 0.0126 50 0.4177 0.0642
0.0942 0.0252 100 0.4772 0.0485
0.1076 0.0379 150 0.4643 0.0584
0.1103 0.0505 200 nan 0.0446
0.0873 0.0631 250 0.5313 0.0518
0.1053 0.0757 300 0.5329 0.0736
0.0797 0.0884 350 0.5326 0.0726
0.0857 0.1010 400 0.5498 0.0693
0.0885 0.1136 450 nan 0.0917
0.102 0.1262 500 0.5649 0.0580
0.0716 0.1389 550 0.5381 0.0797
0.0854 0.1515 600 0.5718 0.0744
0.089 0.1641 650 0.5790 0.0504
0.0721 0.1767 700 0.5727 0.0618
0.0721 0.1893 750 0.5904 0.0703
0.0865 0.2020 800 0.5953 0.0588
0.0767 0.2146 850 0.5918 0.0437
0.0773 0.2272 900 0.5957 0.0568
0.0748 0.2398 950 0.5942 0.0465
0.0761 0.2525 1000 nan 0.0660
0.0855 0.2651 1050 0.5964 0.0491
0.0832 0.2777 1100 0.6048 0.0498
0.0821 0.2903 1150 0.6032 0.0597
0.0715 0.3030 1200 nan 0.0643
0.085 0.3156 1250 0.6054 0.0659
0.0826 0.3282 1300 0.6012 0.0556
0.064 0.3408 1350 nan 0.0564
0.0854 0.3534 1400 nan 0.0552
0.0702 0.3661 1450 0.6061 0.0675
0.0771 0.3787 1500 nan 0.0578
0.08 0.3913 1550 nan 0.0492
0.0804 0.4039 1600 0.6112 0.0538
0.083 0.4166 1650 0.6048 0.0579
0.0701 0.4292 1700 0.6045 0.0674
0.0721 0.4418 1750 0.5979 0.0491
0.0765 0.4544 1800 nan 0.0439
0.0692 0.4671 1850 0.6058 0.0468
0.0761 0.4797 1900 0.6125 0.0574
0.0757 0.4923 1950 0.6126 0.0569
0.0654 0.5049 2000 0.6095 0.0549
0.0736 0.5175 2050 0.0538 0.6122
0.0685 0.5302 2100 0.0485 0.6104
0.0726 0.5428 2150 0.0566 0.6120
0.0731 0.5554 2200 0.0585 0.6112
0.0722 0.5680 2250 0.0589 0.6140
0.0819 0.5807 2300 0.0505 0.6122
0.0694 0.5933 2350 0.0537 0.6101
0.0705 0.6059 2400 0.0646 0.6130
0.0702 0.6185 2450 0.0462 0.6124
0.0709 0.6312 2500 0.0404 0.6134
0.0804 0.6438 2550 0.0478 0.6123
0.0666 0.6564 2600 0.0455 0.6104
0.0749 0.6690 2650 0.0479 0.6132
0.067 0.6816 2700 0.0558 0.6132
0.068 0.6943 2750 0.0539 0.6108

Framework versions

  • Transformers 4.43.0.dev0
  • Pytorch 2.1.2+cu118
  • Datasets 2.20.0
  • Tokenizers 0.19.1