Training in progress, step 10

README.md

@@ -4,8 +4,8 @@ library_name: transformers
 model_name: Qwen3-235B-test8
 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/neko-llm/huggingface/runs/icjurr2g) 
+[<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/neko-llm/huggingface/runs/oup9nenm) 
 
 
 This model was trained with SFT.

adapter_config.json

@@ -25,10 +25,10 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
+    "k_proj",
     "q_proj",
     "v_proj",
-    "o_proj",
-    "k_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 sha256:788ddb4a1ad28ef93dd917d697fe93059833c466f2c92f04fdd89ca7f8bca604
+oid sha256:bf68d015af1da0f0c924d36459ccc557cf5dbb6e9c6a59fcefaaab89a0c7b67d
 size 101748240

trainer_state.json

@@ -47,7 +47,7 @@
   "max_steps": 3,
   "num_input_tokens_seen": 0,
   "num_train_epochs": 1,
-  "save_steps": 1,
+  "save_steps": 5,
   "stateful_callbacks": {
     "TrainerControl": {
       "args": {

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4a0c1272244efbf3b784cf7223d5199b967ce9f7d37a9bab58eb76d72dc0c82b
+oid sha256:4506758d6499685679a514d2890801362dc00bef1a2763dfc41b1347d7cb5223
 size 7480