Training in progress, step 1

adapter_config.json

@@ -1,7 +1,7 @@
 {
   "alpha_pattern": {},
   "auto_mapping": null,
-  "base_model_name_or_path": "google/paligemma-3b-pt-224",
+  "base_model_name_or_path": "google/paligemma-3b-mix-224",
   "bias": "none",
   "fan_in_fan_out": false,
   "inference_mode": true,
@@ -20,13 +20,13 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "up_proj",
+    "v_proj",
+    "down_proj",
+    "gate_proj",
     "k_proj",
-    "q_proj",
     "o_proj",
-    "down_proj",
-    "v_proj",
-    "gate_proj"
+    "q_proj",
+    "up_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:ffd39e2cf8aa6a6c84800d9b45b0dfa06efc17dd21b0340885120d106a483376
+oid sha256:881743f5e436a2c0bd9685a932cc43120b809b7a75e0a321dfa46c5dc5095514
 size 45258384

runs/Jun24_07-46-27_aid-iad-bm-gpu4-8-ad1-002/events.out.tfevents.1719215198.aid-iad-bm-gpu4-8-ad1-002.1304290.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:838d814d108fa260278cfe81ac1080eac7d24c76afcd6d8d186d66f95d018c60
+size 5674

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4d6c6bbc2940afb72a424cf3d9be3b0b5f23f5eb2e8bc26225524e7ed2d1b292
+oid sha256:ff6f3742646f4fedfdb3f22968f02ecffd8d57640c096ba0debd3d90715a3910
 size 5112