Training in progress, step 220

README.md

@@ -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/yyiliu/ft/runs/y1vk3asi) 
+[<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/yyiliu/ft/runs/h6ekepkq) 
 
 
 This model was trained with SFT.

adapter_config.json

@@ -29,10 +29,10 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "gate_up_proj",
-    "down_proj",
+    "qkv_proj",
     "o_proj",
-    "qkv_proj"
+    "down_proj",
+    "gate_up_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:e84cf9f4da9c2c95b23cca61457b08c85815583fe4e20d98a6df1212e9f860d7
+oid sha256:7406811cb000b84a14114031e6c13b095773138b810fb7cf87906d89d292df39
 size 25200088

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:73e267a2aa89e295386b7e64cc2364c3d8685b41940df974ed8f31c6309705e9
+oid sha256:7a8e778138cc288a2aa754bcda09768e19559c6d4c4527855d4e3f2339bbdd3e
 size 5585