Configuration Parsing Warning:In adapter_config.json: "peft.task_type" must be a string
medsiglip-448-vindr-lora
This model is a fine-tuned version of google/medsiglip-448 on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.9237
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: 3e-05
- train_batch_size: 8
- eval_batch_size: 8
- seed: 42
- gradient_accumulation_steps: 8
- total_train_batch_size: 64
- 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: 3
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 2.524 | 0.4938 | 100 | 1.3698 |
| 0.9851 | 0.9877 | 200 | 0.9441 |
| 0.9155 | 1.4790 | 300 | 0.9346 |
| 0.8986 | 1.9728 | 400 | 0.9283 |
| 0.8851 | 2.4642 | 500 | 0.9243 |
| 0.8963 | 2.9580 | 600 | 0.9237 |
Framework versions
- PEFT 0.17.0
- Transformers 4.55.0
- Pytorch 2.8.0+cu128
- Datasets 4.0.0
- Tokenizers 0.21.4
- Downloads last month
- 3
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support
Model tree for aysangh/medsiglip-448-vindr-lora
Base model
google/medsiglip-448