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
 ---
 
@@ -27,18 +27,18 @@ 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/4gtu1vqh) 
+[<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/mi06jcd2) 
 
 
 This model was trained with SFT.
 
 ### Framework versions
 
-- TRL: 0.21.0
-- Transformers: 4.55.0
-- Pytorch: 2.8.0
-- Datasets: 4.0.0
-- Tokenizers: 0.21.4
+- TRL: 0.25.0
+- Transformers: 4.57.1
+- Pytorch: 2.9.0
+- Datasets: 4.4.1
+- Tokenizers: 0.22.1
 
 ## Citations
 

adapter_config.json

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

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7e1cec513b0bfae8cdad246461483cfedd353c44b4bcd5a2ee0d75da2b5a4120
+oid sha256:33bade23015f4045ee0a8d0d679bae5c4dc74148e0f11343dcf69b439959847a
 size 6127553104

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fd81184c4386bdd5320f1754d4cda79540e3bb45d4e9eeffadfdb4c17e09fef2
-size 6353
+oid sha256:c665ff9710ba066622bdc47a0845adeeeb156957d33148906e62f67561245a3f
+size 6481