metadata
library_name: transformers
license: apache-2.0
base_model: microsoft/resnet-18
tags:
- generated_from_trainer
datasets:
- imagefolder
metrics:
- accuracy
model-index:
- name: resnet-18-dungeons-001
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: 0.5
resnet-18-dungeons-001
This model is a fine-tuned version of microsoft/resnet-18 on the imagefolder dataset. It achieves the following results on the evaluation set:
- Loss: 1.1886
- Accuracy: 0.5
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: 1e-05
- train_batch_size: 8
- eval_batch_size: 8
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 32
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: cosine_with_restarts
- lr_scheduler_warmup_steps: 100
- num_epochs: 85
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 0.0594 | 6.6667 | 10 | 1.3086 | 0.5833 |
| 0.0973 | 13.3333 | 20 | 1.3523 | 0.5 |
| 0.068 | 20.0 | 30 | 1.2428 | 0.5833 |
| 0.0671 | 26.6667 | 40 | 1.2280 | 0.5833 |
| 0.0527 | 33.3333 | 50 | 1.2677 | 0.5833 |
| 0.0592 | 40.0 | 60 | 1.2846 | 0.5833 |
| 0.0446 | 46.6667 | 70 | 1.2210 | 0.5833 |
| 0.0565 | 53.3333 | 80 | 1.1886 | 0.5 |
Framework versions
- Transformers 4.44.2
- Pytorch 2.5.0+cu121
- Datasets 3.1.0
- Tokenizers 0.19.1