img_twitter_test
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: 1.0959
- Accuracy: 0.3604
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: 0.1
- train_batch_size: 16
- eval_batch_size: 16
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 64
- optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: linear
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 5
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 1.1706 | 1.0 | 61 | 1.1410 | 0.3737 |
| 1.108 | 2.0 | 122 | 1.0930 | 0.3470 |
| 1.1057 | 3.0 | 183 | 1.1984 | 0.3439 |
| 1.0956 | 4.0 | 244 | 1.0968 | 0.3491 |
| 1.0959 | 5.0 | 305 | 1.0959 | 0.3604 |
Framework versions
- Transformers 4.49.0
- Pytorch 2.5.1+cu121
- Datasets 3.4.1
- Tokenizers 0.21.1