Edit model card

gemini-beauty

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

  • Loss: 1.1226
  • Accuracy: 0.5158

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: 32
  • eval_batch_size: 32
  • seed: 42
  • gradient_accumulation_steps: 4
  • total_train_batch_size: 128
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: linear
  • lr_scheduler_warmup_ratio: 0.1
  • num_epochs: 8

Training results

Training Loss Epoch Step Validation Loss Accuracy
1.3724 1.0 148 1.2028 0.4586
1.3217 2.0 296 1.1831 0.4812
1.2649 3.0 444 1.1674 0.4981
1.2456 4.0 592 1.1236 0.5146
1.2176 5.0 740 1.1384 0.5040
1.2069 6.0 888 1.1165 0.5207
1.2083 7.0 1036 1.1663 0.4985
1.1663 8.0 1184 1.1226 0.5158

Framework versions

  • Transformers 4.36.2
  • Pytorch 2.1.2+cu121
  • Datasets 2.16.1
  • Tokenizers 0.15.0
Downloads last month
248
Safetensors
Model size
2.26M params
Tensor type
F32
ยท
Inference API
Drag image file here or click to browse from your device
This model can be loaded on Inference API (serverless).

Space using Aruno/gemini-beauty 1

Evaluation results