metadata
license: apache-2.0
tags:
- generated_from_trainer
datasets:
- imagefolder
metrics:
- accuracy
model-index:
- name: histo_train_resnet
results:
- task:
name: Image Classification
type: image-classification
dataset:
name: imagefolder
type: imagefolder
config: default
split: train
args: default
metrics:
- name: Accuracy
type: accuracy
value: 0.375
histo_train_resnet
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: 1.2257
- Accuracy: 0.375
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: 0.001
- train_batch_size: 64
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 10
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 1.2218 | 1.67 | 10 | 1.3308 | 0.475 |
| 1.1647 | 3.33 | 20 | 1.1842 | 0.525 |
| 1.132 | 5.0 | 30 | 1.1902 | 0.5 |
| 1.1372 | 6.67 | 40 | 1.1355 | 0.5 |
| 1.1006 | 8.33 | 50 | 1.0911 | 0.45 |
| 1.0876 | 10.0 | 60 | 1.2257 | 0.375 |
Framework versions
- Transformers 4.28.0
- Pytorch 2.0.0+cu118
- Datasets 2.11.0
- Tokenizers 0.13.3