Training in progress, step 5

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/g-puca1-deloitte/llmv3/runs/r90j0vhw) 
+[<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/t2exxzwk) 
 
 
 This model was trained with SFT.

adapter_config.json

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

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:95809efc518a3df6747e3834e81265a64d3a1fb3bff90fbf87c1e2909bd9b0b8
+oid sha256:2d00465c2da4aa7a53d4d976babb20481d3dc35dbd690f9f8da75718e9fc361d
 size 200875760

modelopt_state_train.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cf6d21ae40bf98a08f046758317438fc2ef105b8c4d77ac3f2d8db0ecac607e2
+oid sha256:08b72d12efee4760a7976fc1b1999766aa9b7e4c0424db574290a3244c7bf2b6
 size 994683

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ca7e2de62eadcae8b44099dbc0339db5aa9b486c34f7669b164b51f54acd8c76
+oid sha256:19c9f8c1573117bfcc34b1aa9927ed4b7998d0a4953f7850283bc10589236efb
 size 6289