Training in progress, step 10

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": 128,
+  "lora_alpha": 512,
   "lora_bias": false,
   "lora_dropout": 0.05,
   "megatron_config": null,
   "megatron_core": "megatron.core",
   "modules_to_save": null,
   "peft_type": "LORA",
-  "r": 64,
+  "r": 256,
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
     "o_proj",
-    "down_proj",
-    "gate_proj",
-    "k_proj",
     "up_proj",
+    "v_proj",
+    "down_proj",
     "q_proj",
-    "v_proj"
+    "gate_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 sha256:2da2339cd54c7d807dc40a6e0d51da3746b69295535135a0c96c822fdd477955
-size 1095431224
+oid sha256:b9a84fb7715233a0225d729f0f216d111bc223486c1313577dad79cd21673372
+size 4381342624

runs/Jan05_10-15-47_13546f8c9c40/events.out.tfevents.1767608157.13546f8c9c40.9615.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e2a04c3d84793e759fd86dcc1c6d003e29845670b77f70d60dc175bbb737add0
+size 7487

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:07a5c0949d0e546e140d4445032f7589a9c5535e4b5d517f469dd893c876a82c
+oid sha256:3b2a851ff136c7315bcb91fc6872133265432e7ff0f7375d24cd1ac1e2e0bb7d
 size 5624