Training in progress, step 40

README.md

@@ -4,8 +4,8 @@ library_name: transformers
 model_name: medgemma-27b-it-sft-lora-hyperkvasir
 tags:
 - generated_from_trainer
-- trl
 - sft
+- trl
 licence: license
 ---
 
@@ -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_it_27b_hyperkvasir/runs/r7370xj2) 
+[<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_it_27b_hyperkvasir/runs/u0wm17kn) 
 
 
 This model was trained with SFT.

adapter_config.json

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

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:773ac70ffcb23afc76ee67d63c6fe4561b5808ffcf6f6919881e771d6fea57d5
+oid sha256:6c71211f5f0e2a913ae611ab507210ee79545f372ac0d4cd80471a997fd5d4c0
 size 6127553104

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c1bebc67618e014c760eda21fce679ce0675e3a51da68b3f33bf511148f795f1
+oid sha256:a7d1da37edb56f19d5d0e4a00c4a139121e78d4c28df66d5a6172229619a3e96
 size 6481