Training in progress, step 25

README.md

@@ -29,7 +29,7 @@ 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/srini98/mistral_hackathon/runs/q86jwxrc) 
+[<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/srini98/mistral_hackathon/runs/63dkp981) 
 
 
 This model was trained with SFT.

adapter_config.json

@@ -33,14 +33,14 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "w3",
-    "out_proj",
-    "q_proj",
-    "w2",
-    "w1",
     "in_proj",
+    "w1",
+    "out_proj",
     "v_proj",
-    "k_proj"
+    "w3",
+    "k_proj",
+    "w2",
+    "q_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:f387a61929d9993efae09543e1912e58ecf5fa61b959606128e42fdb0e2008a2
+oid sha256:bce814c4d7a538cb6537782e2cb5953e2fd28b83e4b4c1387f41aa8c83f71005
 size 44457856

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1aca1d609c1076aa150830bfeb55067295f795ebeb80d29fbc8d5862fedef0b9
+oid sha256:5e3358f4e01f8467bd3d953c854e864b71c5f76576d2e4808c3ede692a37fc2a
 size 6417