Training in progress, step 40

README.md

@@ -27,15 +27,15 @@ 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/nb04610c) 
+[<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_hyperkvasir/runs/bzimgz03) 
 
 
 This model was trained with SFT.
 
 ### Framework versions
 
-- TRL: 0.19.1
-- Transformers: 4.54.0
+- TRL: 0.20.0
+- Transformers: 4.54.1
 - Pytorch: 2.6.0+cu124
 - Datasets: 4.0.0
 - Tokenizers: 0.21.2

adapter_config.json

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

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4553c09c8d0b7d145d62bb44522fcda68ada1d70d02e86c0a6d9035ce6bdedb7
+oid sha256:68d4f36ae33bf0d0c1dfbfe3868814696fd1fc8c1249a531a05f726372f600aa
 size 2839126480

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dd8015c9bbe5c0dbff1905684d15785ccb3cb07ead997cd50301f35dcf48b143
-size 5880
+oid sha256:4a99c92db5718c8e3fa68a50a104ce7f740a033660d2ea251fbb6febbc7e4942
+size 5816