Training in progress, epoch 0

adapter_config.json

@@ -1,11 +1,12 @@
 {
   "alpha_pattern": {},
   "auto_mapping": null,
-  "base_model_name_or_path": "google/paligemma-3b-pt-224",
+  "base_model_name_or_path": "google/paligemma-3b-mix-448",
   "bias": "none",
   "fan_in_fan_out": false,
   "inference_mode": true,
   "init_lora_weights": true,
+  "layer_replication": null,
   "layers_pattern": null,
   "layers_to_transform": null,
   "loftq_config": {},
@@ -19,13 +20,15 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
+    "v_proj",
+    "down_proj",
+    "q_proj",
     "o_proj",
     "up_proj",
-    "down_proj",
-    "v_proj",
     "gate_proj",
-    "q_proj",
     "k_proj"
   ],
-  "task_type": "CAUSAL_LM"
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": false
 }

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:34df1687d7db0c148044454eed8520c8a96f84d57dda15d260792522607b7bae
+oid sha256:712a73fe4bc280ee4713f354906d5c74b53cfca25b3146bd7e55edb3a89e8ff3
 size 45258384