dwb2023/paligemma-cnmc-ft

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-pt-224](https://huggingface.co/google/paligemma-3b-pt-224) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.3801
+- Loss: 0.3006
 
 ## Model description
 
@@ -43,15 +43,21 @@ The following hyperparameters were used during training:
 - total_train_batch_size: 16
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
-- lr_scheduler_warmup_steps: 2
+- lr_scheduler_warmup_steps: 50
 - num_epochs: 100
 
 ### Training results
 
 | Training Loss | Epoch  | Step | Validation Loss |
 |:-------------:|:------:|:----:|:---------------:|
-| No log        | 0.9645 | 17   | 0.3739          |
-| No log        | 1.9858 | 35   | 0.3801          |
+| No log        | 0.9645 | 17   | 1.2278          |
+| No log        | 1.9858 | 35   | 0.4162          |
+| 0.8676        | 2.9504 | 52   | 0.3132          |
+| 0.8676        | 3.9716 | 70   | 0.2602          |
+| 0.8676        | 4.9929 | 88   | 0.2446          |
+| 0.2526        | 5.9574 | 105  | 0.2100          |
+| 0.2526        | 6.9787 | 123  | 0.1986          |
+| 0.2526        | 8.0    | 141  | 0.3006          |
 
 
 ### Framework versions

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5340194c5b70e894226a8d78dec1dba0ae8c3e82c03d37cc3a2ac9ef3ac52213
+oid sha256:533803b23ad52072f72e1a4e1ef4292911483ae782d2a5d530c11eb50a8220be
 size 45258384