Training in progress, step 8

README.md

@@ -4,8 +4,8 @@ library_name: transformers
 model_name: gpt-oss-20b-rlinv-sft
 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/ido-pinto/huggingface/runs/nu186dq0) 
+[<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/ido-pinto/huggingface/runs/xfujnqxn) 
 
 
 This model was trained with SFT.

adapter_config.json

@@ -26,9 +26,9 @@
   "revision": null,
   "target_modules": [
     "o_proj",
+    "q_proj",
     "k_proj",
-    "v_proj",
-    "q_proj"
+    "v_proj"
   ],
   "target_parameters": [
     "7.mlp.experts.gate_up_proj",

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8b1b4282d57cbc64a3a73aa406a184c76afeaaf487430272c7eae30dbbb92d82
+oid sha256:bb2bafcb5f0285895202f7df040272dd8cd33922f232e6c703172fbfbd9603f8
 size 60189176

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f17e8447002ff7a9acd7bbda298ec7cca6d3e8d821b766e40568e5117d1f0aa6
+oid sha256:09c8d177878d70d22ed555c92b48151712b2b88e651db8012a4fa5cb2985f7ee
 size 6225