Zum Inhalt springen
ModelAufgelistetExtern
Browse files

Rfdetr Docvqa Media3 v2 Agree1 Large

This model is a fine-tuned version of Roboflow/rf-detr-large on an unknown dataset. It achieves the following results on the evaluation set: Loss: 16.0585 Map: 0.0038 Map 50: 0.0192 Map 75: 0.0015 Map Small: -1.0 Map...

Quellehuggingface.co/merve/rfdetr-docvqa-media3-v2-agree1-large/tree/f26562301e2173ef8e82dd4f6330ef2fbe6175d5
ArtOtherBasismodellRoboflow/rf-detr-largeVersionRevision f265623CBewertung

Modellquelle

Art
Other
Dateigröße
128 MB
Basismodell
Roboflow/rf-detr-large
Version
vRevision f265623
Aktualisiert
16. Sept. 2026
Downloads
3
Quelle
Hugging Face

Quellenbeschreibung

rfdetr-docvqa-media3-v2-agree1-large

This model is a fine-tuned version of Roboflow/rf-detr-large on an unknown dataset. It achieves the following results on the evaluation set:

  • Loss: 16.0585
  • Map: 0.0038
  • Map 50: 0.0192
  • Map 75: 0.0015
  • Map Small: -1.0
  • Map Medium: 0.0004
  • Map Large: 0.004
  • Mar 1: 0.0117
  • Mar 10: 0.1231
  • Mar 100: 0.3169
  • Mar Small: -1.0
  • Mar Medium: 0.05
  • Mar Large: 0.3313
  • Map Chart: 0.005
  • Mar 100 Chart: 0.025
  • Map Image: 0.0045
  • Mar 100 Image: 0.5917
  • Map Signature: 0.0019
  • Mar 100 Signature: 0.334

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: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
  • lr_scheduler_type: cosine
  • lr_scheduler_warmup_steps: 0.05
  • num_epochs: 10

Training results

Training LossEpochStepValidation LossMapMap 50Map 75Map SmallMap MediumMap LargeMar 1Mar 10Mar 100Mar SmallMar MediumMar LargeMap ChartMar 100 ChartMap ImageMar 100 ImageMap SignatureMar 100 Signature
30.00811.05029.06890.00080.00490.0-1.00.00.00080.00670.02370.0876-1.00.00.08810.00230.210.00010.05280.00.0
17.40702.010026.61080.00040.00180.0-1.00.00.00040.00330.02170.0648-1.00.00.06570.00050.1050.00050.08330.00010.006
14.50973.015023.41110.00230.00790.0-1.00.00.00230.00540.01850.084-1.00.00.08750.00190.0250.00480.16110.00010.066
14.17114.020021.75870.00020.00070.0001-1.00.00.00020.00090.02590.0924-1.00.00.09560.00.00.00060.24720.00.03
13.56165.025019.22260.0020.00630.0004-1.00.00.00210.01910.05370.2058-1.00.00.21530.00390.030.00120.38330.0010.204
12.55626.030017.54390.00050.00150.0003-1.00.00.00050.00190.030.1678-1.00.00.17520.00.00.00090.36940.00050.134
11.39147.035016.88680.00150.00430.0008-1.00.00.00160.00090.05840.2636-1.00.00.27670.00.00.00260.50280.00180.288
11.72018.040016.56620.00790.01510.0113-1.00.00.00810.01360.11180.307-1.00.00.32220.00.00.00360.58890.02020.332
11.46059.045016.21840.00330.01280.0017-1.00.00030.00350.01560.09460.3031-1.00.050.31660.00340.020.00480.58330.00180.306
11.694410.050016.05850.00380.01920.0015-1.00.00040.0040.01170.12310.3169-1.00.050.33130.0050.0250.00450.59170.00190.334

Framework versions

  • Transformers 5.12.1
  • Pytorch 2.12.0+cu130
  • Datasets 5.0.0
  • Tokenizers 0.22.2

Quellen

1 Quelle
Hugging FacePrimärVersion f26562301e2173ef8e82dd4f6330ef2fbe6175d5
huggingface.co/merve/rfdetr-docvqa-media3-v2-agree1-large/tree/f26562301e2173ef8e82dd4f6330ef2fbe6175d5

Verifiziert 2. Sept.

Download files

Modellartefakte

2 Artefakte

final/model.safetensors

safetensors · 128 MB · SHA-256 15d7ab4a95ae…f408 · Hugging Face

Download file

model.safetensors

safetensors · 128 MB · SHA-256 15d7ab4a95ae…f408 · Hugging Face

Download file

Quellenauszüge

2 Auszüge
Readme2. Sept.huggingface.co/merve/rfdetr-docvqa-media3-v2-agree1-large

--- library_name: transformers license: apache-2.0 base_model: Roboflow/rf-detr-large tags: - generated_from_trainer model-index: - name: rfdetr-docvqa-media3-v2-agree1-large results: [] --- <!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. --> # rfdetr-docvqa-media3-v2-agree1-large This model is a fine-tuned version of [Roboflow/rf-detr-large](https://huggingface.co/Roboflow/rf-detr-large) on an unknown dataset. It achieves the following results on the evaluation set: - Loss: 16.0585 - Map: 0.0038 - Map 50: 0.0192 - Map 75: 0.0015 - Map Small: -1.0 - Map Medium: 0.0004 - Map Large: 0.004 - Mar 1: 0.0117 - Mar 10: 0.1231 - Mar 100: 0.3169 - Mar Small: -1.0 - Mar Medium: 0.05 - Mar Large: 0.3313 - Map Chart: 0.005 - Mar 100 Chart: 0.025 - Map Image: 0.0045 - Mar 100 Image: 0.5917 - Map Signature: 0.0019 - Mar 100 Signature: 0.334 ## 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: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments - lr_scheduler_type: cosine - lr_scheduler_warmup_steps: 0.05 - num_epochs: 10 ### Training results | Training Loss | Epoch | Step | Validation Loss | Map | Map 50 | Map 75 | Map Small | Map Medium | Map Large | Mar 1 | Mar 10 | Mar 100 | Mar Small | Mar Medium | Mar Large | Map Chart | Mar 100 Chart | Map Image | Mar 100 Image | Map Signature | Mar 100 Signature | |:-------------:|:-----:|:----:|:---------------:|:------:|:------:|:------:|:---------:|:----------:|:---------:|:------:|:------:|:-------:|:---------:|:----------:|:---------:|:---------:|:-------------:|:---------:|:-------------:|:-------------:|:-----------------:| | 30.0081 | 1.0 | 50 | 29.0689 | 0.0008 | 0.0049 | 0.0 | -1.0 | 0.0 | 0.0008 | 0.0067 | 0.0237 | 0.0876 | -1.0 | 0.0 | 0.0881 | 0.0023 | 0.21 | 0.0001 | 0.0528 | 0.0 | 0.0 | | 17.4070 | 2.0 | 100 | 26.6108 | 0.0004 | 0.0018 | 0.0 | -1.0 | 0.0 | 0.0004 | 0.0033 | 0.0217 | 0.0648 | -1...

Note2. Sept.huggingface.co/merve/rfdetr-docvqa-media3-v2-agree1-large

Source context: 3 downloads · 0 likes · Pipeline object-detection · Library transformers · Repo merve/rfdetr-docvqa-media3-v2-agree1-large