Training in progress, step 712

adapter_config.json

@@ -1,7 +1,7 @@
 {
   "alpha_pattern": {},
   "auto_mapping": null,
-  "base_model_name_or_path": "314e/abstrakthealth-rerun-VLM-Gemma3-Entity",
+  "base_model_name_or_path": "google/gemma-3-12b-it",
   "bias": "none",
   "eva_config": null,
   "exclude_modules": null,
@@ -12,7 +12,7 @@
   "layers_pattern": null,
   "layers_to_transform": null,
   "loftq_config": {},
-  "lora_alpha": 64,
+  "lora_alpha": 128,
   "lora_bias": false,
   "lora_dropout": 0.05,
   "megatron_config": null,
@@ -23,13 +23,13 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "down_proj",
-    "v_proj",
     "o_proj",
-    "up_proj",
-    "k_proj",
+    "gate_proj",
     "q_proj",
-    "gate_proj"
+    "v_proj",
+    "up_proj",
+    "down_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 sha256:127915a342bf2c6e8d01905ea65f9295003fefbe13c13e18a121239bdc3d311f
+oid sha256:68c29a73ec03bff8bf6cba1f4f361a721c7228b4fb0498bd4ab09b2c08caa593
 size 1095431224

runs/Jan19_09-06-44_235a30109698/events.out.tfevents.1768813608.235a30109698.9582.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0d614f8061e81b5e3f59b387395908f2dbbdcf330d45b631fc518603bd8853e7
+size 36944

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9ffb2d2e259cb4aef0e42a1e1e3204a40a2bee725ebca96c984eb88475324de2
+oid sha256:8550087d81e728db2b44ec622fa565bb28686039a33fcc70f38cf5382fa73851
 size 5624