End of training

README.md

@@ -4,9 +4,9 @@ library_name: transformers
 model_name: SOC_Task_Generation_Base_GPT_OSS_20B
 tags:
 - generated_from_trainer
-- trl
 - unsloth
 - sft
+- trl
 licence: license
 ---
 
@@ -35,7 +35,7 @@ This model was trained with SFT.
 
 ### Framework versions
 
-- TRL: 0.26.1
+- TRL: 0.24.0
 - Transformers: 4.57.3
 - Pytorch: 2.10.0a0+b558c986e8.nv25.11
 - Datasets: 4.3.0

adapter_config.json

@@ -20,7 +20,7 @@
   "layers_pattern": null,
   "layers_to_transform": null,
   "loftq_config": {},
-  "lora_alpha": 32,
+  "lora_alpha": 16,
   "lora_bias": false,
   "lora_dropout": 0,
   "megatron_config": null,
@@ -29,17 +29,17 @@
   "peft_type": "LORA",
   "peft_version": "0.18.1",
   "qalora_group_size": 16,
-  "r": 32,
+  "r": 8,
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
+    "q_proj",
     "o_proj",
-    "v_proj",
-    "k_proj",
     "up_proj",
-    "q_proj",
+    "k_proj",
+    "gate_proj",
     "down_proj",
-    "gate_proj"
+    "v_proj"
   ],
   "target_parameters": null,
   "task_type": "CAUSAL_LM",

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:659336bcc434d9000b6f4dcf035ab0c00b88d186417018ab88ac3edefe37b0e9
-size 31876384
+oid sha256:e5c2af0bcf565c4b98589edbb83095f17ba07792ff9ea4a81e417134ff2bb036
+size 15950616

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a1ea6d24dfe5e22310f5691b59c053f4dabd0cbe23837adf61f4ce00176fea3a
+oid sha256:95df2588c348d024f51a2ca56681f4a4ff77da205285e10065b7c72dfd1454d9
 size 6353