Training in progress, step 100

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/arthuryong-personal/Fine%20tuning%20of%20Mistral%207B/runs/imyuzp4f?apiKey=56fff3f15dd3a20806cd00dfdd0472df42fa5b06) 
+[<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/arthuryong-personal/Fine%20tuning%20of%20Mistral%207B/runs/whlsswu8?apiKey=56fff3f15dd3a20806cd00dfdd0472df42fa5b06) 
 
 
 This model was trained with SFT.

adapter_config.json

@@ -24,9 +24,9 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "gate_proj",
     "up_proj",
-    "down_proj"
+    "down_proj",
+    "gate_proj"
   ],
   "task_type": "CAUSAL_LM",
   "trainable_token_indices": null,

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:eb692e2d8b3e225dfa028cbf81fc0df1df730ca93216106b308436241cdd8459
+oid sha256:e99fee1ad99ca5b885e8bf357f9503faa6b2d7cbeb53560f9ab17667d21df034
 size 113271504

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:333331b45c078e7a9bdb5e63ef35261b0606ed8f834a0e2eaf680036b6d4d524
+oid sha256:62ea2554c80a8ba8118899cd4e83f8386a2a327242b4f1b3b13583e34d35d61c
 size 5688