layoutlmv2-base-uncased_finetuned_docvqa

This model is a fine-tuned version of microsoft/layoutlmv2-base-uncased on an unknown dataset. It achieves the following results on the evaluation set:

  • Loss: nan

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: 4
  • eval_batch_size: 8
  • seed: 42
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: linear
  • num_epochs: 20

Training results

Training Loss Epoch Step Validation Loss
0.0 0.22 50 nan
0.0 0.44 100 nan
0.0 0.66 150 nan
0.0 0.88 200 nan
0.0 1.11 250 nan
0.0 1.33 300 nan
0.0 1.55 350 nan
0.0 1.77 400 nan
0.0 1.99 450 nan
0.0 2.21 500 nan
0.0 2.43 550 nan
0.0 2.65 600 nan
0.0 2.88 650 nan
0.0 3.1 700 nan
0.0 3.32 750 nan
0.0 3.54 800 nan
0.0 3.76 850 nan
0.0 3.98 900 nan
0.0 4.2 950 nan
0.0 4.42 1000 nan
0.0 4.65 1050 nan
0.0 4.87 1100 nan
0.0 5.09 1150 nan
0.0 5.31 1200 nan
0.0 5.53 1250 nan
0.0 5.75 1300 nan
0.0 5.97 1350 nan
0.0 6.19 1400 nan
0.0 6.42 1450 nan
0.0 6.64 1500 nan
0.0 6.86 1550 nan
0.0 7.08 1600 nan
0.0 7.3 1650 nan
0.0 7.52 1700 nan
0.0 7.74 1750 nan
0.0 7.96 1800 nan
0.0 8.19 1850 nan
0.0 8.41 1900 nan
0.0 8.63 1950 nan
0.0 8.85 2000 nan
0.0 9.07 2050 nan
0.0 9.29 2100 nan
0.0 9.51 2150 nan
0.0 9.73 2200 nan
0.0 9.96 2250 nan
0.0 10.18 2300 nan
0.0 10.4 2350 nan
0.0 10.62 2400 nan
0.0 10.84 2450 nan
0.0 11.06 2500 nan
0.0 11.28 2550 nan
0.0 11.5 2600 nan
0.0 11.73 2650 nan
0.0 11.95 2700 nan
0.0 12.17 2750 nan
0.0 12.39 2800 nan
0.0 12.61 2850 nan
0.0 12.83 2900 nan
0.0 13.05 2950 nan
0.0 13.27 3000 nan
0.0 13.5 3050 nan
0.0 13.72 3100 nan
0.0 13.94 3150 nan
0.0 14.16 3200 nan
0.0 14.38 3250 nan
0.0 14.6 3300 nan
0.0 14.82 3350 nan
0.0 15.04 3400 nan
0.0 15.27 3450 nan
0.0 15.49 3500 nan
0.0 15.71 3550 nan
0.0 15.93 3600 nan
0.0 16.15 3650 nan
0.0 16.37 3700 nan
0.0 16.59 3750 nan
0.0 16.81 3800 nan
0.0 17.04 3850 nan
0.0 17.26 3900 nan
0.0 17.48 3950 nan
0.0 17.7 4000 nan
0.0 17.92 4050 nan
0.0 18.14 4100 nan
0.0 18.36 4150 nan
0.0 18.58 4200 nan
0.0 18.81 4250 nan
0.0 19.03 4300 nan
0.0 19.25 4350 nan
0.0 19.47 4400 nan
0.0 19.69 4450 nan
0.0 19.91 4500 nan

Framework versions

  • Transformers 4.39.3
  • Pytorch 2.1.2
  • Datasets 2.18.0
  • Tokenizers 0.15.2
Downloads last month
11
Safetensors
Model size
200M params
Tensor type
F32
·
Inference Examples
This model does not have enough activity to be deployed to Inference API (serverless) yet. Increase its social visibility and check back later, or deploy to Inference Endpoints (dedicated) instead.

Model tree for ravindrareddytamma/layoutlmv2-base-uncased_finetuned_docvqa

Finetuned
(67)
this model