Training in progress, step 100

README.md

@@ -4,8 +4,8 @@ library_name: transformers
 model_name: fine-tuned_mistral
 tags:
 - generated_from_trainer
-- sft
 - trl
+- sft
 licence: license
 ---
 
@@ -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/wvequ980?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/imyuzp4f?apiKey=56fff3f15dd3a20806cd00dfdd0472df42fa5b06) 
 
 
 This model was trained with SFT.

adapter_config.json

@@ -24,9 +24,9 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "down_proj",
+    "gate_proj",
     "up_proj",
-    "gate_proj"
+    "down_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 sha256:6435096e2db59b773a97b073d2e73b49de7b7c2ea0fed2369b1aee2c18a788fa
+oid sha256:eb692e2d8b3e225dfa028cbf81fc0df1df730ca93216106b308436241cdd8459
 size 113271504

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f459660ab64ed136df48db48d6a25766cd8a70950b820b9dbaaf99376111e669
+oid sha256:333331b45c078e7a9bdb5e63ef35261b0606ed8f834a0e2eaf680036b6d4d524
 size 5688