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-dr2-Project/runs/kxb8ars0) 
+[<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-dr2-Project/runs/nt2427bx) 
 
 
 This model was trained with SFT.

adapter_config.json

@@ -28,16 +28,16 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "gate_proj",
-    "k_proj",
-    "fc1",
-    "v_proj",
-    "up_proj",
-    "out_proj",
     "fc2",
     "o_proj",
+    "down_proj",
+    "gate_proj",
     "q_proj",
-    "down_proj"
+    "k_proj",
+    "out_proj",
+    "v_proj",
+    "fc1",
+    "up_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 sha256:3a822ad2868e747eba498a532683128d47bb58ef07a2bbdc0fe6640cc46b56d6
+oid sha256:2993fb309e643371e4e33f19ea3b173b6a64b0435c2d54b956955e8eb3f057d3
 size 6127553104

runs/Aug15_23-43-01_meedgxh100a/events.out.tfevents.1755315783.meedgxh100a.2981305.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:14dde3e0fe7a951608490289a7b804fd527170fd49d13182cf5bf2963db8820e
+size 11213

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:386100f2afbbab5f8aea294ba63d5b705bf8671ac8aba616501ed8c21cb9e0e2
+oid sha256:f56c7f5f9e164c596231f1eb96bd9e690f4c30a40207db12a95c02635cef1b57
 size 5816