README.md

metadata

library_name: transformers
license: apache-2.0
base_model: microsoft/resnet-50
tags:
  - generated_from_trainer
datasets:
  - imagefolder
metrics:
  - accuracy
model-index:
  - name: resnet50
    results:
      - task:
          name: Image Classification
          type: image-classification
        dataset:
          name: imagefolder
          type: imagefolder
          config: default
          split: validation
          args: default
        metrics:
          - name: Accuracy
            type: accuracy
            value: 0.9926

resnet50

This model is a fine-tuned version of microsoft/resnet-50 on the imagefolder dataset. It achieves the following results on the evaluation set:

• Loss: 0.0210
• Accuracy: 0.9926
• F1 Weighted: 0.9926
• F1 Macro: 0.9925
• Precision Weighted: 0.9926

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: 0.0003
• train_batch_size: 128
• eval_batch_size: 256
• seed: 42
• gradient_accumulation_steps: 2
• total_train_batch_size: 256
• 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: linear
• lr_scheduler_warmup_steps: 0.1
• num_epochs: 5
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy	F1 Weighted	F1 Macro	Precision Weighted
3.7125	1.0	193	0.1263	0.961	0.9604	0.9602	0.9628
0.1261	2.0	386	0.0376	0.9882	0.9882	0.9881	0.9885
0.0347	3.0	579	0.0232	0.9926	0.9926	0.9925	0.9927
0.0165	4.0	772	0.0238	0.992	0.992	0.9919	0.9921
0.0109	5.0	965	0.0210	0.9926	0.9926	0.9925	0.9926

Framework versions

• Transformers 5.0.0
• Pytorch 2.10.0+cu128
• Datasets 4.0.0
• Tokenizers 0.22.2