resnet18
This model is a fine-tuned version of pretrained/resnet18 on the datasets/Galaxy10 dataset. It achieves the following results on the evaluation set:
- Loss: 0.5140
- Accuracy: 0.8455
- Precision: 0.7114
- Recall: 0.6703
- F1: 0.6809
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: 64
- eval_batch_size: 64
- seed: 3047
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 10.0
Training results
Training Loss | Epoch | Step | Validation Loss | Accuracy | Precision | Recall | F1 |
---|---|---|---|---|---|---|---|
1.072 | 1.0 | 273 | 1.0307 | 0.6360 | 0.1946 | 0.2432 | 0.2106 |
0.744 | 2.0 | 546 | 0.7900 | 0.7521 | 0.3302 | 0.3748 | 0.3494 |
0.591 | 3.0 | 819 | 0.6428 | 0.7776 | 0.3413 | 0.4052 | 0.3682 |
0.4759 | 4.0 | 1092 | 0.6169 | 0.7767 | 0.3421 | 0.4121 | 0.3703 |
0.3265 | 5.0 | 1365 | 0.5688 | 0.7948 | 0.4576 | 0.4642 | 0.4314 |
0.2267 | 6.0 | 1638 | 0.5499 | 0.8185 | 0.5920 | 0.5296 | 0.5252 |
0.1517 | 7.0 | 1911 | 0.5399 | 0.8308 | 0.6139 | 0.6033 | 0.6015 |
0.1313 | 8.0 | 2184 | 0.5132 | 0.8405 | 0.7027 | 0.6429 | 0.6562 |
0.0926 | 9.0 | 2457 | 0.5138 | 0.8426 | 0.7110 | 0.6517 | 0.6643 |
0.0927 | 10.0 | 2730 | 0.5140 | 0.8455 | 0.7114 | 0.6703 | 0.6809 |
Framework versions
- Transformers 4.40.1
- Pytorch 2.3.0+cu121
- Datasets 2.19.0
- Tokenizers 0.19.1
- Downloads last month
- 1
Invalid base_model specified in model card
metadata. Needs to be a model id from
hf.co/models.