10-resnet-50-finetuned-spiderTraining100-100
This model is a fine-tuned version of microsoft/resnet-50 on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 1.2563
- Accuracy: 0.657
- Precision: 0.6605
- Recall: 0.6572
- F1: 0.6430
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: 0.0005
- train_batch_size: 16
- eval_batch_size: 16
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 64
- optimizer: Use OptimizerNames.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: 10
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | Precision | Recall | F1 |
|---|---|---|---|---|---|---|---|
| 4.2022 | 1.0 | 125 | 3.8106 | 0.132 | 0.1190 | 0.1385 | 0.0908 |
| 2.6442 | 2.0 | 250 | 2.2022 | 0.405 | 0.4258 | 0.4145 | 0.3772 |
| 2.1982 | 3.0 | 375 | 1.7984 | 0.495 | 0.5307 | 0.5046 | 0.4798 |
| 1.7721 | 4.0 | 500 | 1.5778 | 0.557 | 0.5734 | 0.5654 | 0.5452 |
| 1.6367 | 5.0 | 625 | 1.4217 | 0.599 | 0.6173 | 0.6007 | 0.5859 |
| 1.4437 | 6.0 | 750 | 1.3486 | 0.63 | 0.6574 | 0.6330 | 0.6214 |
| 1.3602 | 7.0 | 875 | 1.2996 | 0.635 | 0.6554 | 0.6363 | 0.6242 |
| 1.3112 | 8.0 | 1000 | 1.2792 | 0.643 | 0.6487 | 0.6458 | 0.6289 |
| 1.2492 | 9.0 | 1125 | 1.2267 | 0.66 | 0.6699 | 0.6605 | 0.6481 |
| 1.1791 | 10.0 | 1250 | 1.2563 | 0.657 | 0.6605 | 0.6572 | 0.6430 |
Framework versions
- Transformers 4.55.2
- Pytorch 2.6.0+cu124
- Datasets 4.0.0
- Tokenizers 0.21.4