metadata
license: apache-2.0
base_model: microsoft/resnet-50
tags:
- generated_from_trainer
datasets:
- imagefolder
metrics:
- accuracy
model-index:
- name: resnet-50-finetuned-hateful-meme-restructured
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-50-finetuned-hateful-meme-restructured
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: 0.7132
- 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: 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 |
|---|---|---|---|---|
| 0.6633 | 0.99 | 66 | 0.7132 | 0.5 |
| 0.6561 | 2.0 | 133 | 0.7309 | 0.5 |
| 0.6497 | 2.99 | 199 | 0.7314 | 0.5 |
| 0.6529 | 4.0 | 266 | 0.7296 | 0.5 |
| 0.6336 | 4.99 | 332 | 0.7386 | 0.5 |
| 0.625 | 6.0 | 399 | 0.7403 | 0.5 |
| 0.6511 | 6.99 | 465 | 0.7425 | 0.5 |
| 0.6567 | 8.0 | 532 | 0.7314 | 0.5 |
| 0.6389 | 8.99 | 598 | 0.7380 | 0.5 |
| 0.6446 | 9.92 | 660 | 0.7426 | 0.5 |
Framework versions
- Transformers 4.31.0
- Pytorch 2.0.1+cu117
- Datasets 2.13.1
- Tokenizers 0.13.3