Hugging Face's logo

davanstrien
/
test-timm

Image Classification
Transformers
TensorBoard
Safetensors
timm_wrapper
vision
Generated from Trainer
Inference Endpoints
Model card Files Metrics Community
test-timm / README.md
davanstrien's picture
davanstrien HF staff
End of training
7b2ef42 verified
preview code
|
raw
history blame
4.61 kB
metadata
library_name: transformers
license: apache-2.0
base_model: timm/mobilenetv3_large_100.miil_in21k
tags:
  - image-classification
  - vision
  - generated_from_trainer
metrics:
  - accuracy
model-index:
  - name: test-timm
    results: []

test-timm

This model is a fine-tuned version of timm/mobilenetv3_large_100.miil_in21k on the davanstrien/zenodo-presentations-open-labels dataset. It achieves the following results on the evaluation set:

  • Loss: 0.4904
  • Accuracy: 0.7874

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: 64
  • eval_batch_size: 64
  • seed: 1337
  • optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
  • lr_scheduler_type: linear
  • num_epochs: 50.0

Training results

Training Loss Epoch Step Validation Loss Accuracy
0.6794 1.0 23 0.6560 0.6063
0.6215 2.0 46 0.5833 0.7362
0.5784 3.0 69 0.5490 0.7598
0.5347 4.0 92 0.5306 0.7638
0.5307 5.0 115 0.5235 0.7638
0.5391 6.0 138 0.5090 0.7677
0.48 7.0 161 0.5108 0.7717
0.473 8.0 184 0.5028 0.7756
0.5014 9.0 207 0.5054 0.7717
0.496 10.0 230 0.5040 0.7717
0.4688 11.0 253 0.4972 0.7677
0.4943 12.0 276 0.4977 0.7638
0.5012 13.0 299 0.5057 0.7717
0.4639 14.0 322 0.5010 0.7717
0.4709 15.0 345 0.4949 0.7795
0.4888 16.0 368 0.4955 0.7835
0.4594 17.0 391 0.4986 0.7717
0.4745 18.0 414 0.5011 0.7677
0.4667 19.0 437 0.4928 0.7756
0.4551 20.0 460 0.5055 0.7795
0.4657 21.0 483 0.4928 0.7756
0.4818 22.0 506 0.5002 0.7756
0.4633 23.0 529 0.4946 0.7835
0.4779 24.0 552 0.4942 0.7795
0.4718 25.0 575 0.4963 0.7835
0.4511 26.0 598 0.5011 0.7717
0.4798 27.0 621 0.4904 0.7874
0.4868 28.0 644 0.4982 0.7835
0.4653 29.0 667 0.4988 0.7874
0.4613 30.0 690 0.4985 0.7795
0.4675 31.0 713 0.5060 0.7717
0.4587 32.0 736 0.5059 0.7717
0.464 33.0 759 0.5042 0.7795
0.4374 34.0 782 0.5063 0.7677
0.4864 35.0 805 0.5040 0.7677
0.4354 36.0 828 0.5109 0.7717
0.4655 37.0 851 0.5107 0.7717
0.4691 38.0 874 0.5093 0.7677
0.4826 39.0 897 0.5044 0.7717
0.4577 40.0 920 0.5000 0.7795
0.4636 41.0 943 0.4963 0.7717
0.4361 42.0 966 0.4958 0.7717
0.4534 43.0 989 0.5008 0.7795
0.4559 44.0 1012 0.5025 0.7795
0.4189 45.0 1035 0.5014 0.7756
0.4861 46.0 1058 0.5004 0.7677
0.4709 47.0 1081 0.5005 0.7795
0.4726 48.0 1104 0.5008 0.7717
0.4441 49.0 1127 0.4988 0.7756
0.4579 50.0 1150 0.5000 0.7756

Framework versions

  • Transformers 4.46.0.dev0
  • Pytorch 2.4.1+cu121
  • Datasets 3.0.1
  • Tokenizers 0.20.1