Training in progress, step 100

README.md

@@ -4,8 +4,8 @@ library_name: transformers
 model_name: training_output
 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/g-puca1-deloitte/llmv3/runs/a9aokmnb) 
+[<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) 
 
 
 This model was trained with SFT.

adapter_config.json

@@ -25,8 +25,8 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "k_proj",
     "o_proj",
+    "k_proj",
     "q_proj",
     "v_proj"
   ],

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6606718d102ef84da13ed91aa798e223bec594fac151f11f75c42903c83f63b4
+oid sha256:b55f6c5dcd3e08ea76bbca02339c17fe35b716ad389ae7986579dcdbc0f2b55b
 size 200875760

modelopt_state_train.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:44f95c3e27ce7b5f911a5305439a2babb4fbde021c0fded422ff1801d88e7692
+oid sha256:d256528065ed3795df621e70cb5dc5af57a74f4365f546758bb2399d57815027
 size 994683

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:49d6e73fccca4f3a92ac31c8f65fcf5168e6000c7bde2bc08310753e70f05545
+oid sha256:1bb52c09399ba2a7866c72754d470355c5586140a6c7f0e3a27908cc8f9f0033
 size 6353