Training in progress, step 4400

README.md

@@ -28,7 +28,7 @@ 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/yasuhito-yanagisawa/my-llm-finetuning/runs/rn56chii) 
+[<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/yasuhito-yanagisawa/my-llm-finetuning/runs/t2881j6b) 
 
 
 This model was trained with SFT.

adapter_config.json

@@ -25,13 +25,13 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "up_proj",
+    "down_proj",
     "q_proj",
     "v_proj",
-    "down_proj",
+    "up_proj",
     "o_proj",
-    "k_proj",
-    "gate_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 sha256:041663b70b794d31ca13566136a34c764e738af5ab1d2eba409dd16785e39637
+oid sha256:fa7f53403b89c352525993ae758d1b243b26cc807c2e3496a03dbc3e597b2e9a
 size 1073863208

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:70b41dd94087c09b97a26d68bf56152eef207a28c9c1b33c5a39cce1eeb6e97a
+oid sha256:ba3db525866d103e4bd3d0029dd11eb00913e7b0fe35e8dbd879261ceb33f516
 size 6225