metadata
license: apache-2.0
tags:
- generated_from_trainer
datasets:
- imagefolder
metrics:
- accuracy
model-index:
- name: resnet50-finetuned-memes
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: 0.5741885625965997
- task:
type: image-classification
name: Image Classification
dataset:
type: custom
name: custom
split: test
metrics:
- type: f1
value: 0.47811617701687364
name: F1
- type: precision
value: 0.43689216537139497
name: Precision
- type: recall
value: 0.5695517774343122
name: Recall
resnet50-finetuned-memes
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: 1.0625
- Accuracy: 0.5742
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: 0.00012
- 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 |
|---|---|---|---|---|
| 1.4795 | 0.99 | 40 | 1.4641 | 0.4382 |
| 1.3455 | 1.99 | 80 | 1.3281 | 0.4389 |
| 1.262 | 2.99 | 120 | 1.2583 | 0.4583 |
| 1.1975 | 3.99 | 160 | 1.1978 | 0.4876 |
| 1.1358 | 4.99 | 200 | 1.1614 | 0.5139 |
| 1.1273 | 5.99 | 240 | 1.1316 | 0.5379 |
| 1.0379 | 6.99 | 280 | 1.1024 | 0.5464 |
| 1.041 | 7.99 | 320 | 1.0927 | 0.5580 |
| 0.9952 | 8.99 | 360 | 1.0790 | 0.5541 |
| 1.0146 | 9.99 | 400 | 1.0625 | 0.5742 |
Framework versions
- Transformers 4.22.1
- Pytorch 1.12.1+cu113
- Datasets 2.4.0
- Tokenizers 0.12.1