metadata
tags:
- generated_from_trainer
datasets:
- imagefolder
metrics:
- accuracy
model-index:
- name: resnet-18
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: 0.647255502925606
resnet-18
This model was trained from scratch on the imagefolder dataset. It achieves the following results on the evaluation set:
- Loss: 0.9476
- Accuracy: 0.6473
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: 10
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 1.472 | 1.0 | 252 | 1.3291 | 0.4887 |
| 1.2941 | 2.0 | 505 | 1.1145 | 0.5793 |
| 1.2117 | 3.0 | 757 | 1.0483 | 0.6043 |
| 1.1616 | 4.0 | 1010 | 1.0137 | 0.6233 |
| 1.1654 | 5.0 | 1262 | 0.9975 | 0.6291 |
| 1.1297 | 6.0 | 1515 | 0.9766 | 0.6414 |
| 1.0645 | 7.0 | 1767 | 0.9668 | 0.6372 |
| 1.0692 | 8.0 | 2020 | 0.9603 | 0.6450 |
| 1.0711 | 9.0 | 2272 | 0.9521 | 0.6425 |
| 1.0344 | 9.98 | 2520 | 0.9476 | 0.6473 |
Framework versions
- Transformers 4.30.0
- Pytorch 2.1.0+cu118
- Datasets 2.14.6
- Tokenizers 0.13.3