Training in progress, step 20

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/wangyichen25-mayo-clinic/medgemma_finetune/runs/ndu6dcmi) 
+[<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/wangyichen25-mayo-clinic/medgemma_finetune/runs/ptk5c4pk) 
 
 
 This model was trained with SFT.

adapter_config.json

@@ -28,16 +28,16 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "fc1",
-    "up_proj",
     "out_proj",
+    "fc1",
     "v_proj",
+    "q_proj",
     "k_proj",
-    "fc2",
-    "o_proj",
     "gate_proj",
-    "q_proj",
-    "down_proj"
+    "fc2",
+    "down_proj",
+    "up_proj",
+    "o_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 sha256:8ef10df24d519dcedf5b6f840a5740e09413c6b17c87c45d827ab8fa6451b2d6
+oid sha256:19c45df154137122b53fc3630f074f7b3d4a757e310d0894a231b513757b5f57
 size 2839126480

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:09a9baff00283695ce70ca75d7d996c90cc5734afa7d9ed3f9a6113fde47b709
+oid sha256:7fa3299c8cd6826c610bec43e932e8377d63e21789add24e4c875f4d75cb544d
 size 5880