End of training

README.md

@@ -15,6 +15,8 @@ should probably proofread and complete it, then remove this comment. -->
 # paligemma2_json_extraction
 
 This model is a fine-tuned version of [google/paligemma2-3b-pt-224](https://huggingface.co/google/paligemma2-3b-pt-224) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Loss: 1.1100
 
 ## Model description
 
@@ -42,10 +44,13 @@ The following hyperparameters were used during training:
 - optimizer: Use paged_adamw_8bit 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: 3
+- num_epochs: 1
 
 ### Training results
 
+| Training Loss | Epoch  | Step | Validation Loss |
+|:-------------:|:------:|:----:|:---------------:|
+| 1.5382        | 0.6093 | 100  | 1.1100          |
 
 
 ### Framework versions

adapter_config.json

@@ -23,11 +23,11 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "o_proj",
-    "down_proj",
-    "v_proj",
     "gate_proj",
     "up_proj",
+    "down_proj",
+    "o_proj",
+    "v_proj",
     "q_proj",
     "k_proj"
   ],

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:09a89a6c09ac4d3676f369d5d11d12227e9151228145adc10a4655ba05d1bb23
+oid sha256:ee6fcd08732ed1a6d8a2c419a73ed469fb1ea1194c0db86f5472ca52eee54892
 size 47584968

runs/Mar12_06-28-19_7e0b04f2e93d/events.out.tfevents.1741761122.7e0b04f2e93d.18.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4ed4fcfb31491f7d5ef5b7670347a7286b44cbe7b0226130d85d3768c51a1275
+size 7108

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:de3d14d54d4f1f05251143de2cd290b99be3c6856d4875bb8851fb0ff83a3e23
+oid sha256:5c4d613156b6c067e886e63e3d32491c28b370a12ea3e8ff2390f83e47c10cf1
 size 5368