Training in progress, step 1

adapter_config.json

@@ -1,7 +1,7 @@
 {
   "alpha_pattern": {},
   "auto_mapping": null,
-  "base_model_name_or_path": "google/gemma-3-12b-it",
+  "base_model_name_or_path": "314e/dexit-VLM-Gemma3-Entity-test5-integration",
   "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": 256,
   "lora_bias": false,
   "lora_dropout": 0.05,
   "megatron_config": null,
   "megatron_core": "megatron.core",
   "modules_to_save": null,
   "peft_type": "LORA",
-  "r": 64,
+  "r": 126,
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "q_proj",
-    "gate_proj",
+    "k_proj",
+    "v_proj",
     "o_proj",
-    "down_proj",
     "up_proj",
-    "v_proj",
-    "k_proj"
+    "down_proj",
+    "q_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:d7c3b13d2ae3883889ee5dd37ec608bbaf0dac3863bdb95ac59d6bd99d96cc0f
-size 1095431224
+oid sha256:d5255574f967b5e74fe3ff907a0bed540db72cc87c8013ee421515ecddbdc698
+size 2156507696

runs/Feb25_04-11-59_601d42e78ca9/events.out.tfevents.1771992723.601d42e78ca9.9556.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1ca693a4508e7c51c3ad3bf20d4745c747d4832e9d4dbca5781bf3ba592b4b3b
+size 7071

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c2746a3222ac1c5caecb9fb34f06dce2961116652722eea3f5e8d03bae87706d
+oid sha256:a80bcd1efe626ceb6e4a14073d32a566d379139b403e366d9d409966aa82607a
 size 5624