Training in progress, step 5

README.md

@@ -4,8 +4,8 @@ library_name: transformers
 model_name: outputr24
 tags:
 - generated_from_trainer
-- trl
 - grpo
+- trl
 licence: license
 ---
 

adapter_config.json

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

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1f9bd26d332ab6f2ada79a0283c9a94da9d74ee2d7bec698fb8354bb6879c22d
+oid sha256:77a525e274b2a7e8f154e35f6ea72142e1f20806a44927302cacf0df975bc2a7
 size 15744552

runs/Sep01_12-14-16_ampere001.int.ada.nottingham.ac.uk/events.out.tfevents.1756725257.ampere001.int.ada.nottingham.ac.uk.2280725.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c7dd85976198ce8546733ee1e2e84ee6ba87dd944cb8aa605c1d516cf5a74d41
+size 6282

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:35cf24d4c00b14a812a383f44b672846bb9d260ff2af4ffe69882734c4a4a96c
+oid sha256:f881c8e29c9d705134eba9fe1932dc7a2a57a8531b50264f3ccd873dc0939af7
 size 6993