Training in progress, epoch 0

adapter_config.json

@@ -1,7 +1,7 @@
 {
   "alpha_pattern": {},
   "auto_mapping": null,
-  "base_model_name_or_path": "google/paligemma-3b-ft-ocrvqa-448",
+  "base_model_name_or_path": "google/paligemma-3b-mix-448",
   "bias": "none",
   "fan_in_fan_out": false,
   "inference_mode": true,
@@ -21,12 +21,12 @@
   "revision": null,
   "target_modules": [
     "o_proj",
-    "q_proj",
     "up_proj",
-    "down_proj",
-    "k_proj",
     "v_proj",
-    "gate_proj"
+    "down_proj",
+    "q_proj",
+    "gate_proj",
+    "k_proj"
   ],
   "task_type": "CAUSAL_LM",
   "use_dora": false,

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5bb18727887b2bb2ef69c876cb66c0451b225578f163badf69d3c7e8a2f9665f
+oid sha256:649d3238333edf98764decb69d07bbb52a45c2964c1a5afae6cecb13e4b07708
 size 45258384

runs/Dec03_15-50-50_mmg2/events.out.tfevents.1733266251.mmg2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:00492f2782868a82fd3282cce82ed6ee3b8210b04de0067b05ad02961473ed1b
+size 6057

runs/Dec03_17-01-12_mmg2/events.out.tfevents.1733270473.mmg2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cb41156ae93691cddf7943b44a7766fe79802bfafd3b48dc08255d1b50861e95
+size 10067

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:610951118a90a7a51c14582e09b3927b8cddc087cd2b1c4353476c303cce30e7
+oid sha256:22fb6d8be30d8de103996ca90112ebf35ca16dd718e246a0daba0d5404f1a1b7
 size 5304