metadata
tags:
- generated_from_trainer
datasets:
- imagefolder
metrics:
- accuracy
- f1
model-index:
- name: resnet_weather_model
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: 0.6735537190082644
- name: F1
type: f1
value: 0.6654635943888922
resnet_weather_model
This model was trained from scratch on the imagefolder dataset. It achieves the following results on the evaluation set:
- Loss: 1.7452
- Accuracy: 0.6736
- F1: 0.6655
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: 0.0002
- train_batch_size: 8
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 3
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 |
|---|---|---|---|---|---|
| 2.3598 | 1.0 | 91 | 2.1983 | 0.5165 | 0.5146 |
| 2.0319 | 2.0 | 182 | 1.8708 | 0.6446 | 0.6433 |
| 1.7971 | 3.0 | 273 | 1.7452 | 0.6736 | 0.6655 |
Framework versions
- Transformers 4.25.1
- Pytorch 1.13.0+cu116
- Datasets 2.8.0
- Tokenizers 0.13.2