metadata
library_name: transformers
license: apache-2.0
base_model: microsoft/resnet-50
tags:
- generated_from_trainer
datasets:
- imagefolder
metrics:
- accuracy
model-index:
- name: cat_dog_classifier_with_small_datasest
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: 0.8714285714285714
cat_dog_classifier_with_small_datasest
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: 0.3807
- Accuracy: 0.8714
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: 4e-05
- train_batch_size: 4
- eval_batch_size: 8
- seed: 42
- optimizer: Use adamw_torch 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: 500
- num_epochs: 10
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| No log | 1.0 | 140 | 0.6967 | 0.4929 |
| No log | 2.0 | 280 | 0.6870 | 0.5357 |
| No log | 3.0 | 420 | 0.6729 | 0.6214 |
| 0.6818 | 4.0 | 560 | 0.6306 | 0.7429 |
| 0.6818 | 5.0 | 700 | 0.5554 | 0.8714 |
| 0.6818 | 6.0 | 840 | 0.4894 | 0.8429 |
| 0.6818 | 7.0 | 980 | 0.4511 | 0.8286 |
| 0.5676 | 8.0 | 1120 | 0.4113 | 0.8643 |
| 0.5676 | 9.0 | 1260 | 0.4318 | 0.8643 |
| 0.5676 | 10.0 | 1400 | 0.3807 | 0.8714 |
Framework versions
- Transformers 4.47.1
- Pytorch 2.4.1+cu121
- Datasets 3.2.0
- Tokenizers 0.21.0