agentmish's picture
Model save
f2bd1cb verified
metadata
library_name: transformers
license: apache-2.0
base_model: google/vit-base-patch16-224-in21k
tags:
  - generated_from_trainer
metrics:
  - accuracy
model-index:
  - name: dog-emotion-classifier-v2
    results: []

dog-emotion-classifier-v2

This model is a fine-tuned version of google/vit-base-patch16-224-in21k on an unknown dataset. It achieves the following results on the evaluation set:

  • Loss: 0.6903
  • Accuracy: 0.8562

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: 0.0001
  • train_batch_size: 16
  • 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_ratio: 0.1
  • num_epochs: 10
  • mixed_precision_training: Native AMP
  • label_smoothing_factor: 0.1

Training results

Training Loss Epoch Step Validation Loss Accuracy
No log 0.5 100 0.9887 0.7688
No log 1.0 200 0.6958 0.81
No log 1.5 300 0.6492 0.8413
No log 2.0 400 0.6726 0.8387
0.7269 2.5 500 0.6561 0.8562
0.7269 3.0 600 0.6745 0.85
0.7269 3.5 700 0.6711 0.8638
0.7269 4.0 800 0.6874 0.8612
0.7269 4.5 900 0.6850 0.86
0.3736 5.0 1000 0.6903 0.8562

Framework versions

  • Transformers 4.57.1
  • Pytorch 2.8.0+cu126
  • Datasets 4.0.0
  • Tokenizers 0.22.1