End of training

README.md

@@ -28,15 +28,15 @@ 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/sribalaji-work07-vellore-institute-of-technology/huggingface/runs/qtg8i03t)
+[<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/sribalaji-work07-vellore-institute-of-technology/huggingface/runs/o6ytkm5p)
 
 This model was trained with SFT.
 
 ### Framework versions
 
-- TRL: 0.12.0
+- TRL: 0.12.1
 - Transformers: 4.46.2
-- Pytorch: 2.5.0+cu121
+- Pytorch: 2.5.1+cu121
 - Datasets: 3.1.0
 - Tokenizers: 0.20.3
 

adapter_config.json

@@ -20,13 +20,13 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "q_proj",
-    "down_proj",
-    "k_proj",
-    "up_proj",
     "v_proj",
+    "k_proj",
+    "gate_proj",
+    "down_proj",
     "o_proj",
-    "gate_proj"
+    "q_proj",
+    "up_proj"
   ],
   "task_type": "CAUSAL_LM",
   "use_dora": false,

runs/Nov19_11-29-48_c4f374c6c6e0/events.out.tfevents.1732015801.c4f374c6c6e0.289.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e86f7bc0327d53a3b67c5c7ec213a3089e4dce43f888a57ead8acd337c0d7fd2
+size 69031

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6e8c7f493bacd49de878de3fddd7662709b3a05744347a8b645f2f34b657f9e6
+oid sha256:8338061f3f72ffa17f250b8f87e807c40fbbe854b51283d83a224254bcfdf3d0
 size 5560