Training in progress, step 500

README.md

@@ -4,8 +4,8 @@ library_name: transformers
 model_name: test
 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/rustin_r-the-university-of-texas-at-austin/huggingface/runs/wq5ae4l0) 
+[<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/rustin_r-the-university-of-texas-at-austin/medgemma-4b-it-123/runs/5w7t2z2m) 
 
 
 This model was trained with SFT.

adapter_config.json

@@ -27,16 +27,16 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "q_proj",
-    "up_proj",
-    "o_proj",
-    "out_proj",
-    "gate_proj",
     "down_proj",
     "k_proj",
-    "fc1",
+    "up_proj",
+    "o_proj",
+    "v_proj",
     "fc2",
-    "v_proj"
+    "fc1",
+    "q_proj",
+    "out_proj",
+    "gate_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 sha256:022e2c083d0097cbffcaf89f6f77197b01ae8188cb51342b1167d1a480315cdc
+oid sha256:dc53bb133c5c4b28717b4c36e0cc3771e35621972567e378a0d5c83b3a93293f
 size 2762134176

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a77a7d9d3172c0704d34f9f14f57d9bed9dc7dbee7c07c0228564f25ab6b3869
-size 7825
+oid sha256:58836496a540e643471f1625c9cc091017b2cff82a48648fead9922b935071ff
+size 7761