Training in progress, step 5

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/k6f61y61) 
+[<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/r90j0vhw) 
 
 
 This model was trained with SFT.

adapter_config.json

@@ -26,8 +26,8 @@
   "revision": null,
   "target_modules": [
     "k_proj",
-    "v_proj",
     "q_proj",
+    "v_proj",
     "o_proj"
   ],
   "target_parameters": [

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:90134b3557653265126306cb09bee18aa61ecec8bd5dd73ccfde79ba5d286217
+oid sha256:899ece3d991fcf4477741f33738eb12dd4d05dd7e77c6c3f38ec1666801d10e0
 size 200875760

modelopt_state_train.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5fb58b1a2230a15446d2a396b1c5e305c4aa166e62d7b2268c720281a54ff470
+oid sha256:cf6d21ae40bf98a08f046758317438fc2ef105b8c4d77ac3f2d8db0ecac607e2
 size 994683

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e0489ff95f13a7e7bfd58ee172102fe361e99f1734e386f32c9545af44d48c07
+oid sha256:ca7e2de62eadcae8b44099dbc0339db5aa9b486c34f7669b164b51f54acd8c76
 size 6289