Model save

Logs/events.out.tfevents.1718384259.e29ec45d9208.134.10

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:199c98ae3b8441ba84f8b14281db5b6b018e38b960129dee2f8d94f21aabdba4
-size 7751
+oid sha256:88ed668393e7bde68180263c6c4f2d247ebb82bb3d606062a708e159897e5d75
+size 8587

README.md

@@ -18,7 +18,7 @@ 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 the ecgt_vision dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.0006
+- Loss: 0.0009
 
 ## Model description
 
@@ -46,20 +46,23 @@ The following hyperparameters were used during training:
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
 - lr_scheduler_warmup_steps: 2
-- num_epochs: 2
+- num_epochs: 5
 
 ### Training results
 
 | Training Loss | Epoch  | Step | Validation Loss |
 |:-------------:|:------:|:----:|:---------------:|
-| 1.4751        | 0.9961 | 129  | 0.0008          |
-| 0.0003        | 1.9923 | 258  | 0.0006          |
+| 3.3557        | 0.9961 | 129  | 0.0054          |
+| 0.0039        | 2.0    | 259  | 0.0015          |
+| 0.0008        | 2.9961 | 388  | 0.0011          |
+| 0.0003        | 4.0    | 518  | 0.0010          |
+| 0.0002        | 4.9807 | 645  | 0.0009          |
 
 
 ### Framework versions
 
 - PEFT 0.11.1
 - Transformers 4.41.0
-- Pytorch 2.1.0+cu118
+- Pytorch 2.0.1+cu118
 - Datasets 2.19.1
 - Tokenizers 0.19.1

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a12af3b9f8ec65975068a9f91102291a7bfca674d7c89bf2652903717d0f37f4
+oid sha256:1221ca71a3265abcbd4364c01980644a607a4d8bc57a43480b3eb5e8464da03d
 size 45258384