Training in progress, step 113

README.md

@@ -4,8 +4,8 @@ library_name: transformers
 model_name: qwen3-4b-code-lora-lr2e4
 tags:
 - generated_from_trainer
-- trl
 - sft
+- trl
 - hf_jobs
 licence: license
 ---

adapter_config.json

@@ -23,19 +23,19 @@
   "megatron_core": "megatron.core",
   "modules_to_save": null,
   "peft_type": "LORA",
-  "peft_version": "0.18.0",
+  "peft_version": "0.18.1",
   "qalora_group_size": 16,
   "r": 16,
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "down_proj",
-    "up_proj",
     "k_proj",
-    "o_proj",
-    "gate_proj",
+    "up_proj",
     "v_proj",
-    "q_proj"
+    "q_proj",
+    "down_proj",
+    "gate_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 sha256:7f4cbc38e2003498c809c9af348866259cf0f90f8a839b6a1828dfb5aa1b39a0
+oid sha256:7033c8a7135adaf072dfb90afff8aae7e002772b87e7cb5f6d3cc87dc7306913
 size 66127776

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d9702623fa62318d9e8b58e005ea4701eedd5965e03085631fb8c2534c8f5490
+oid sha256:2cc1f5982a30a78fb58ffea416f985f5046e68588bb52ffb4e410cd1fd7eee67
 size 6353