Model save

README.md

@@ -0,0 +1,63 @@
+---
+library_name: peft
+base_model: ybelkada/blip2-opt-2.7b-fp16-sharded
+tags:
+- generated_from_trainer
+model-index:
+- name: blip2-vqa-pathology
+  results: []
+---
+
+<!-- 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. -->
+
+# blip2-vqa-pathology
+
+This model is a fine-tuned version of [ybelkada/blip2-opt-2.7b-fp16-sharded](https://huggingface.co/ybelkada/blip2-opt-2.7b-fp16-sharded) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.0001
+
+## 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: 0.0001
+- train_batch_size: 4
+- eval_batch_size: 8
+- seed: 42
+- gradient_accumulation_steps: 4
+- total_train_batch_size: 16
+- 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
+- num_epochs: 2
+- mixed_precision_training: Native AMP
+
+### Training results
+
+| Training Loss | Epoch  | Step | Validation Loss |
+|:-------------:|:------:|:----:|:---------------:|
+| 0.0002        | 0.5814 | 500  | 0.0001          |
+| 0.0001        | 1.1628 | 1000 | 0.0001          |
+| 0.0001        | 1.7442 | 1500 | 0.0001          |
+
+
+### Framework versions
+
+- PEFT 0.15.2.dev0
+- Transformers 4.51.3
+- Pytorch 2.6.0+cu124
+- Datasets 3.6.0
+- Tokenizers 0.21.1