Training in progress, step 500

README.md

@@ -6,6 +6,7 @@ tags:
 - generated_from_trainer
 - grpo
 - trl
+- hf_jobs
 licence: license
 ---
 

adapter_config.json

@@ -25,13 +25,13 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "k_proj",
-    "up_proj",
-    "o_proj",
     "gate_proj",
-    "v_proj",
     "q_proj",
-    "down_proj"
+    "down_proj",
+    "v_proj",
+    "up_proj",
+    "o_proj",
+    "k_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:a201eb79b883696f3308cfe084c98f161ba392b9f7a64c708ef71e68ce807a0a
-size 74405904
+oid sha256:7b5afa24ee694714b6ad2a1079fd17d780dbba004b12bd3f3ee047682dc35671
+size 37253648

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0e736039d09a02f279c14a2b6fe16882e7396e8246b1637223973da8a0041ca6
-size 7185
+oid sha256:5e0050b78e0dc2d79e5284709579f2e9911d4786ae1e0f3f3e5bd45a8fdd02a6
+size 8593