medsiglip-448-cied-650-binary-cied_presence-classification
This model is a fine-tuned version of google/medsiglip-448 on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 3.7159
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: 8
- total_train_batch_size: 128
- optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: cosine
- lr_scheduler_warmup_steps: 5
- num_epochs: 5
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 7.2983 | 1.0 | 5 | 7.7995 |
| 4.8343 | 2.0 | 10 | 3.7648 |
| 3.7965 | 3.0 | 15 | 3.7432 |
| 3.7219 | 4.0 | 20 | 3.7173 |
| 3.7008 | 5.0 | 25 | 3.7159 |
Framework versions
- Transformers 4.57.3
- Pytorch 2.9.0+cu126
- Datasets 4.4.2
- Tokenizers 0.22.2
- Downloads last month
- 2
Model tree for aomocelin/medsiglip-448-cied-650-binary-cied_presence-classification
Base model
google/medsiglip-448