Training in progress, step 10

README.md

@@ -4,8 +4,8 @@ library_name: transformers
 model_name: Qwen2.5-7B-Instruct-GRPO-test
 tags:
 - generated_from_trainer
-- grpo
 - trl
+- grpo
 licence: license
 ---
 

adapter_config.json

@@ -25,8 +25,8 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "v_proj",
-    "q_proj"
+    "q_proj",
+    "v_proj"
   ],
   "task_type": "CAUSAL_LM",
   "trainable_token_indices": null,

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b4dcfae68cd903244cc70730451fce118e6a511f5f27e0beec2346aa50af1ff6
+oid sha256:917933eb12ac118ed87e23112d687f031f6f8d7ff747a9ca1f9e734bbad1e5ec
 size 10107280

runs/Jul03_21-41-36_3cde1693ecac/events.out.tfevents.1751578936.3cde1693ecac.893.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cc7f2122d7fb37065e5c2ca6de00040790706b4959f102ec8f30cc3454d4e738
+size 8366

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e852e502cbb3a73a806419799c9a8ee08516cacc09a22c4849b55ccea122399c
+oid sha256:177c299fcdc2fde97aa979449f07f12aeae51eae4812e7ecd16210a41d1fe53b
 size 6456