Training in progress, step 200

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/mohamed-ahmed/medgemma-4b-it-multi-gpu/runs/2v12ra3f) 
+[<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/mohamed-ahmed/medgemma-4b-it-multi-gpu/runs/mokjlbor) 
 
 
 This model was trained with SFT.

adapter_config.json

@@ -25,15 +25,15 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "v_proj",
-    "down_proj",
+    "q_proj",
     "k_proj",
+    "down_proj",
+    "v_proj",
+    "gate_proj",
     "o_proj",
-    "q_proj",
-    "lm_head",
-    "up_proj",
     "embed_tokens",
-    "gate_proj"
+    "lm_head",
+    "up_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:fbf0729cc272c338fc8b05f472317f72fb5cec132dae9d7ac5f6cb397fca5cce
+oid sha256:329bdcae7ce48a9136b14834381cef23fcdd88a6d9bc37311993358ce33bdd49
 size 2767633984

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:741abbb72c5b704e8a76f4576949ae12cf6c26f526aa675c4913b2399a2f5441
+oid sha256:82c61d623553198ef6d846e39d7872388de8537777cf2943f15342d01c1d84fb
 size 8273