Training in progress, step 30

README.md

@@ -4,8 +4,8 @@ library_name: transformers
 model_name: training_output
 tags:
 - generated_from_trainer
-- trl
 - sft
+- trl
 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/g-puca1-deloitte/llmv3/runs/qzfktbkz) 
+[<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/g-puca1-deloitte/llmv3/runs/pnlds90a) 
 
 
 This model was trained with SFT.

adapter_config.json

@@ -25,9 +25,9 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "o_proj",
-    "k_proj",
     "q_proj",
+    "k_proj",
+    "o_proj",
     "v_proj"
   ],
   "target_parameters": [

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:27d56f2286dd3858c8aa152fe5cfbb3f1838514f5c78c7463247f6e3ced521ac
+oid sha256:db8e80ad25838200548d87734c6554a995dda35e6d85fb155943e80f810d86b0
 size 200875760

modelopt_state_train.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d256528065ed3795df621e70cb5dc5af57a74f4365f546758bb2399d57815027
+oid sha256:7707130df73908b8251b8c5fca69b6bd6172d478c6a28a381d392cfba049ac35
 size 994683

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1bb52c09399ba2a7866c72754d470355c5586140a6c7f0e3a27908cc8f9f0033
+oid sha256:f82c343f61be8fad671fe7a01a7ddab16d3700c0b2aaa050705732b34953997b
 size 6353