End of training

README.md

@@ -4,8 +4,8 @@ library_name: transformers
 model_name: outputs
 tags:
 - generated_from_trainer
-- grpo
 - trl
+- grpo
 licence: license
 ---
 
@@ -34,9 +34,9 @@ This model was trained with GRPO, a method introduced in [DeepSeekMath: Pushing
 
 ### Framework versions
 
-- TRL: 0.23.1
-- Transformers: 4.56.2
-- Pytorch: 2.8.0+cu129
+- TRL: 0.24.0
+- Transformers: 4.57.0
+- Pytorch: 2.8.0+cu126
 - Datasets: 4.1.1
 - Tokenizers: 0.22.1
 

adapter_config.json

@@ -21,14 +21,14 @@
   "modules_to_save": null,
   "peft_type": "LORA",
   "qalora_group_size": 16,
-  "r": 16,
+  "r": 32,
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "k_proj",
-    "v_proj",
     "o_proj",
-    "q_proj"
+    "down_proj",
+    "gate_up_proj",
+    "qkv_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:aac5d4c268fd60de4d378348cf3e9ca1c039ca84f40530812587b2043b40a1aa
-size 12591456
+oid sha256:8b5a945595c8d2c04f78865b6e9ca7cbe932e031eaaa17e90d5619a3237d565a
+size 184584072

tokenizer.json

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d27bf952925b6e14ec92a0a31758494613e50dd289b4496b49db0c015a98dae7
-size 15524645
+oid sha256:37b10016a39382ff2d24acc20a291ed83243a26c4549ab01f6240e72c6291d56
+size 15524472

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:81e11fdc026269ad9e7c955bf1192f3856b85a20528efff7bbbf03f4fc71752b
-size 7121
+oid sha256:60a0cf0420a6ce27c1428d63743609bedfb1d82d0921253d7efab8cd2f233083
+size 7185