<!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. -->
triage_R5_model
This model is a fine-tuned version of microsoft/swin-tiny-patch4-window7-224 on the None dataset. It achieves the following results on the evaluation set:
- Loss: 1.0123
- Accuracy: 0.6837
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: 12
Training results
Training Loss | Epoch | Step | Validation Loss | Accuracy |
---|---|---|---|---|
2.0452 | 1.0 | 159 | 1.9622 | 0.3814 |
1.7034 | 2.0 | 319 | 1.5695 | 0.4923 |
1.441 | 3.0 | 479 | 1.4427 | 0.5433 |
1.2908 | 4.0 | 639 | 1.2970 | 0.5895 |
1.2294 | 5.0 | 798 | 1.2293 | 0.6071 |
1.1097 | 6.0 | 958 | 1.1892 | 0.6300 |
1.0342 | 7.0 | 1118 | 1.1048 | 0.6546 |
0.9644 | 8.0 | 1278 | 1.0731 | 0.6678 |
0.8534 | 9.0 | 1437 | 1.0367 | 0.6766 |
0.8037 | 10.0 | 1597 | 1.0211 | 0.6802 |
0.7765 | 11.0 | 1757 | 1.0073 | 0.6885 |
0.7658 | 11.94 | 1908 | 1.0123 | 0.6837 |
Framework versions
- Transformers 4.30.2
- Pytorch 2.0.1+cu118
- Datasets 2.13.1
- Tokenizers 0.13.3