Training in progress, step 1

adapter_config.json

@@ -1,7 +1,7 @@
 {
   "alpha_pattern": {},
   "auto_mapping": null,
-  "base_model_name_or_path": null,
+  "base_model_name_or_path": "google/paligemma-3b-mix-224",
   "bias": "none",
   "fan_in_fan_out": false,
   "inference_mode": true,
@@ -21,12 +21,12 @@
   "revision": null,
   "target_modules": [
     "gate_proj",
-    "up_proj",
-    "o_proj",
-    "v_proj",
     "k_proj",
     "q_proj",
-    "down_proj"
+    "v_proj",
+    "down_proj",
+    "up_proj",
+    "o_proj"
   ],
   "task_type": "CAUSAL_LM",
   "use_dora": false,

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:01b291e4ac3a4371248132b03f97f196dd0099250ad8662ad3ce548620afc865
-size 45266256
+oid sha256:6566af9ca314733e69a9a575a49563447619b9720b8bc45ff3fcd16a6e524835
+size 45259216

runs/Jun27_12-41-10_aid-iad-bm-gpu4-8-ad1-004/events.out.tfevents.1719492079.aid-iad-bm-gpu4-8-ad1-004.2386178.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:42481c5614cdb4aa6ba3300f10a692f3104d24c8d73197b07a4b3055a255a63e
+size 5270

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d18459a5db39ba427543855dc2849da9e89f5a8897fb3a7e70080f9c12481cd9
+oid sha256:238c88b2c6f0c842f68d3174ca66d230935766eef3b9fc8369542544ee6a4092
 size 5176