convnext_model

This model is a fine-tuned version of facebook/convnext-base-224 on the imagefolder dataset. It achieves the following results on the evaluation set:

  • Loss: 0.0712

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: 16
  • eval_batch_size: 16
  • seed: 42
  • optimizer: Use OptimizerNames.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: 5

Training results

Training Loss Epoch Step Validation Loss
0.0945 1.0 100 0.1009
0.0233 2.0 200 0.0851
0.0041 3.0 300 0.0755
0.0026 4.0 400 0.0715
0.0024 5.0 500 0.0712

Framework versions

  • Transformers 4.46.3
  • Pytorch 2.5.1+cu124
  • Datasets 3.1.0
  • Tokenizers 0.20.3
Downloads last month
13
Safetensors
Model size
87.6M params
Tensor type
F32
·
Inference Providers NEW
This model is not currently available via any of the supported Inference Providers.

Model tree for FA24-CS462-Group-26/convnext_model

Finetuned
(6)
this model