Training in progress, step 421

adapter_config.json

@@ -1,7 +1,7 @@
 {
   "alpha_pattern": {},
   "auto_mapping": null,
-  "base_model_name_or_path": "314e/abstrakthealth-VLM-Gemma3-Entity",
+  "base_model_name_or_path": "google/gemma-3-12b-it",
   "bias": "none",
   "eva_config": null,
   "exclude_modules": null,
@@ -12,24 +12,24 @@
   "layers_pattern": null,
   "layers_to_transform": null,
   "loftq_config": {},
-  "lora_alpha": 256,
+  "lora_alpha": 128,
   "lora_bias": false,
   "lora_dropout": 0.05,
   "megatron_config": null,
   "megatron_core": "megatron.core",
   "modules_to_save": null,
   "peft_type": "LORA",
-  "r": 256,
+  "r": 64,
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "v_proj",
-    "o_proj",
+    "up_proj",
     "q_proj",
-    "gate_proj",
+    "v_proj",
     "down_proj",
+    "o_proj",
     "k_proj",
-    "up_proj"
+    "gate_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:afc1418f543b7977df5334462249b599b0eb70c6a8af889cc10c16354cb4ca20
-size 4381342624
+oid sha256:7107277f38e05f2fc0b1440a5d9ca792cacf2186e76ad37e78db192c93db458a
+size 1095431224

runs/Jan13_17-59-49_50a8614b5f3b/events.out.tfevents.1768327192.50a8614b5f3b.9696.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1a82be9487859fba14e008b06eb231771a9ee55ca926e9ec073596514b029fab
+size 24707

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4784955d042f1953bde2a462c6961c85ca1aa698b74a0cda6b87706b01326555
+oid sha256:16d4b4587f8b9d6bb7d61a428a6b00bd464864b19980de3b47bfd427e8814a34
 size 5624