Training in progress, epoch 1

README.md

@@ -27,7 +27,7 @@ print(output["generated_text"])
 
 ## Training procedure
 
-[<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="150" height="24"/>](https://wandb.ai/yoon307-kaist/medgemma-27b-it-amd4-AMD-Project/runs/u07pheu2) 
+[<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="150" height="24"/>](https://wandb.ai/yoon307-kaist/medgemma-27b-it-amd4-AMD-Project/runs/yucz78gz) 
 
 
 This model was trained with SFT.

adapter_config.json

@@ -28,16 +28,16 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "q_proj",
-    "down_proj",
-    "out_proj",
-    "gate_proj",
-    "k_proj",
+    "up_proj",
     "o_proj",
     "v_proj",
-    "up_proj",
+    "gate_proj",
+    "out_proj",
+    "k_proj",
+    "q_proj",
+    "fc2",
     "fc1",
-    "fc2"
+    "down_proj"
   ],
   "task_type": "CAUSAL_LM",
   "trainable_token_indices": null,

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f072f00e4830d988a86500869af10261dde2eeb0d6fb85ed0c0cc271240ec083
+oid sha256:950de88008e63a063b076fa975afce2bf52a9897ffca0b16175b5d4208f619b4
 size 6127553104

runs/Aug25_00-25-19_meedgxh100a/events.out.tfevents.1756095921.meedgxh100a.3680610.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f393fbb0bd12ce471afe505e08f6a8379df4dae533a1f9f259139ca060b0a130
+size 10567

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a2cf32154cf359b6afc100fa282be642065e42f49816e83930c2abd027e0c9a3
+oid sha256:931383971c1de7e823c3b5021cc747fa3d60f1941921a72d0e3a8b749e767328
 size 5816