metadata
library_name: transformers
license: apache-2.0
base_model: microsoft/resnet-50
tags:
- generated_from_trainer
datasets:
- imagefolder
metrics:
- accuracy
- f1
model-index:
- name: resnet-kitchen-object
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: 0.8677685950413223
- name: F1
type: f1
value: 0.8678765100301015
resnet-kitchen-object
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: 0.4314
- Accuracy: 0.8678
- F1: 0.8679
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_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: 0.05
- num_epochs: 12
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 |
|---|---|---|---|---|---|
| 2.0478 | 1.0 | 447 | 1.8372 | 0.5119 | 0.5147 |
| 0.9774 | 2.0 | 894 | 0.7962 | 0.7832 | 0.7816 |
| 0.6756 | 3.0 | 1341 | 0.5893 | 0.8221 | 0.8211 |
| 0.5692 | 4.0 | 1788 | 0.5361 | 0.8347 | 0.8349 |
| 0.5087 | 5.0 | 2235 | 0.5034 | 0.8439 | 0.8438 |
| 0.4525 | 6.0 | 2682 | 0.4738 | 0.8483 | 0.8480 |
| 0.4211 | 7.0 | 3129 | 0.4518 | 0.8610 | 0.8604 |
| 0.4156 | 8.0 | 3576 | 0.4418 | 0.8629 | 0.8628 |
| 0.3394 | 9.0 | 4023 | 0.4394 | 0.8663 | 0.8659 |
| 0.3452 | 10.0 | 4470 | 0.4341 | 0.8653 | 0.8654 |
| 0.3121 | 11.0 | 4917 | 0.4457 | 0.8658 | 0.8655 |
| 0.3392 | 12.0 | 5364 | 0.4314 | 0.8678 | 0.8679 |
Framework versions
- Transformers 4.57.1
- Pytorch 2.8.0+cu126
- Datasets 4.0.0
- Tokenizers 0.22.1