Training in progress, epoch 1

README.md

@@ -4,8 +4,8 @@ library_name: transformers
 model_name: medgemma-27b-it-amd1
 tags:
 - generated_from_trainer
-- sft
 - trl
+- sft
 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/yoon307-kaist/medgemma-27b-it-amd1-AMD-Project/runs/nj58xzxt) 
+[<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-amd1-AMD-Project/runs/4ni3rpuo) 
 
 
 This model was trained with SFT.

adapter_config.json

@@ -28,15 +28,15 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "out_proj",
-    "fc2",
     "fc1",
     "down_proj",
+    "o_proj",
+    "fc2",
     "q_proj",
+    "out_proj",
     "gate_proj",
-    "v_proj",
-    "o_proj",
     "k_proj",
+    "v_proj",
     "up_proj"
   ],
   "task_type": "CAUSAL_LM",

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:faf857fe176cae384355b3364b951583b8a43f4db9b31fd946702efb46540183
+oid sha256:7d1af327e4b5a49240a70da996464ba05d5ad305abaa8540cfebdceb07e93289
 size 6127553104

runs/Aug20_20-32-13_meedgxh100a/events.out.tfevents.1755736336.meedgxh100a.1659164.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7ff4185259267559a61551042157089f3ccde9d3936038873db9b78fb9ecec5a
+size 12841

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1c021003fb5e8aca4844cd8167491371388513407dc7d2d3c028bb7ed2a2aeaf
+oid sha256:fd5c3c82653a9a58eaa9f3ed793ff90604742bda08e7462e1a417abbaf92100e
 size 5816