Training in progress, step 3000

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/lucas01/llmv3/runs/dp6q56e4) 
+[<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/lucas01/llmv3/runs/lik3s1hi) 
 
 
 This model was trained with SFT.

adapter_config.json

@@ -26,9 +26,9 @@
   "revision": null,
   "target_modules": [
     "k_proj",
-    "o_proj",
     "v_proj",
-    "q_proj"
+    "q_proj",
+    "o_proj"
   ],
   "target_parameters": null,
   "task_type": "CAUSAL_LM",

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f3634d85fa57df9c58a766b3c0428acc83994259af398cd63bdb62c59fe816af
+oid sha256:3a6f9105881144e65a0b9537a07f891b5fb54e53e40d375dd5048fb1f23d677f
 size 191141984

modelopt_state_train.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:74fc53932082694dccae0d3bf3bdf8d40547c68d4c28a10f095a8f1f6a97a59e
+oid sha256:3d072c91d56ed6af64096e3e03d12f90ef2887336f69b6c46a505bbb64d21baa
 size 975611

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7546d710638c25dad821dceaa8664fb4a76ad6c5670f14d9154e55607fc519e9
-size 6353
+oid sha256:e5af7bd53c10fbafabca4b6e490b2adc1fdfa72547892059e33e2764eb125240
+size 6289