End of training

README.md

@@ -34,10 +34,10 @@ This model was trained with SFT.
 
 ### Framework versions
 
-- TRL: 0.21.0
+- TRL: 0.15.2
 - Transformers: 4.55.0
 - Pytorch: 2.8.0.dev20250319+cu128
-- Datasets: 4.0.0
+- Datasets: 3.3.2
 - Tokenizers: 0.21.4
 
 ## Citations
@@ -49,7 +49,7 @@ Cite TRL as:
 ```bibtex
 @misc{vonwerra2022trl,
 	title        = {{TRL: Transformer Reinforcement Learning}},
-	author       = {Leandro von Werra and Younes Belkada and Lewis Tunstall and Edward Beeching and Tristan Thrush and Nathan Lambert and Shengyi Huang and Kashif Rasul and Quentin Gallou{\'e}dec},
+	author       = {Leandro von Werra and Younes Belkada and Lewis Tunstall and Edward Beeching and Tristan Thrush and Nathan Lambert and Shengyi Huang and Kashif Rasul and Quentin Gallouédec},
 	year         = 2020,
 	journal      = {GitHub repository},
 	publisher    = {GitHub},

adapter_config.json

@@ -26,16 +26,16 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
+    "q_proj",
+    "fc2",
+    "k_proj",
+    "down_proj",
     "up_proj",
+    "v_proj",
+    "fc1",
     "out_proj",
     "o_proj",
-    "fc2",
-    "q_proj",
-    "fc1",
-    "v_proj",
-    "down_proj",
-    "gate_proj",
-    "k_proj"
+    "gate_proj"
   ],
   "task_type": "CAUSAL_LM",
   "use_dora": false,

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2bd19e04ee2ca14423520f3795b4951beeec761e658ee314d0b4a561679d67fc
+oid sha256:4ceb74106b9491ca7c4a11b85ab808daf5245f06ed7ed0917ba3cc3fb58cd824
 size 2762129216

runs/Aug09_20-23-50_e90b6039d39d/events.out.tfevents.1754771048.e90b6039d39d.2368.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fcc6cf93a0dc6f2ed0c4cd842953b75b5def01045908ac7673e8ca78c2d9ba4b
+size 9329

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a16e22bc3b6cf7965bc189229806c8c4b7988d0cbdbbcd4197bc7cf289515258
+oid sha256:f1ee3789b4543a8eac42062dbbcf5ed522044dd711844efc6a402cf061b35bb8
 size 6033