Training in progress, step 100

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": null,
   "bias": "none",
   "fan_in_fan_out": false,
   "inference_mode": true,
@@ -10,23 +10,23 @@
   "layers_pattern": null,
   "layers_to_transform": null,
   "loftq_config": {},
-  "lora_alpha": 8,
-  "lora_dropout": 0.0,
+  "lora_alpha": 32,
+  "lora_dropout": 0.05,
   "megatron_config": null,
   "megatron_core": "megatron.core",
   "modules_to_save": null,
   "peft_type": "LORA",
-  "r": 8,
+  "r": 4,
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
+    "o_proj",
+    "down_proj",
     "up_proj",
-    "v_proj",
     "q_proj",
     "gate_proj",
     "k_proj",
-    "o_proj",
-    "down_proj"
+    "v_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:be2e388da8128d4e742b8c5694b4cca4f4d0f1ad850674a9d3b42802f0677443
-size 45258384
+oid sha256:3e80459b937d16b3bac4476fd25f6a1131efdd385e5c763a2a451f3691df1256
+size 22674688

runs/Jul07_09-28-10_b7d666c0a375/events.out.tfevents.1720344496.b7d666c0a375.696.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:04423a332e1eed94a7c285b53d38b4dda18a2016461b265a94611e064ce6ab2e
+size 7748

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:108ef084ad9815b612f657a9b5a5d9ffbff4638cdd8ed7803e3e6ddb4ea3d2cd
+oid sha256:0e87226bab508bb5be16688504c80a7ca3c87c8e21cd3b84da65f43c269653a7
 size 5112