Training in progress, step 17

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/abstrakthealth-VLM-Gemma3-Entity",
   "bias": "none",
   "eva_config": null,
   "exclude_modules": null,
@@ -12,24 +12,24 @@
   "layers_pattern": null,
   "layers_to_transform": null,
   "loftq_config": {},
-  "lora_alpha": 512,
+  "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": [
-    "gate_proj",
-    "q_proj",
     "v_proj",
-    "o_proj",
-    "down_proj",
+    "up_proj",
+    "q_proj",
     "k_proj",
-    "up_proj"
+    "gate_proj",
+    "o_proj",
+    "down_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:dd2f41155f65440f53748e991df91202e41ba9965a91df448d1ccebee457d28e
-size 4381342624
+oid sha256:4af615d767bf25cdf3da41046946a31ab59eef44cba56fbfe805a8151d929d8d
+size 1095431224

runs/Jan08_13-11-21_ebb1c45d2bcb/events.out.tfevents.1767877884.ebb1c45d2bcb.9602.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a4911b4be3372e8ebf936001a39b75584231ac0f308a129072817a13c2a95886
+size 7695

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c082cf8633495d3e957216c644fc7f99804985bc12ab445e02719adc841296d9
+oid sha256:d67df540b6d828de295fa8c236282cfcf132b76b103ab200898dd670846fa1fd
 size 5624