paligemma_Mix_vqa_rad_YES_N0_11

README.md

@@ -16,7 +16,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [google/paligemma-3b-mix-224](https://huggingface.co/google/paligemma-3b-mix-224) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.4049
+- Loss: 0.3830
 
 ## Model description
 
@@ -35,22 +35,23 @@ More information needed
 ### Training hyperparameters
 
 The following hyperparameters were used during training:
-- learning_rate: 2e-05
-- train_batch_size: 4
+- learning_rate: 0.0002
+- train_batch_size: 6
 - eval_batch_size: 8
 - seed: 42
 - gradient_accumulation_steps: 8
-- total_train_batch_size: 32
+- total_train_batch_size: 48
 - optimizer: Use adamw_hf with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
 - lr_scheduler_type: linear
 - lr_scheduler_warmup_steps: 2
-- num_epochs: 4
+- num_epochs: 8
 
 ### Training results
 
 | Training Loss | Epoch  | Step | Validation Loss |
 |:-------------:|:------:|:----:|:---------------:|
-| 1.9094        | 3.8368 | 112  | 0.4049          |
+| No log        | 3.9560 | 76   | 0.2013          |
+| 0.1719        | 7.9560 | 152  | 0.3830          |
 
 
 ### Framework versions