End of training

README.md

@@ -34,7 +34,7 @@ This model was trained with SFT.
 
 ### Framework versions
 
-- TRL: 0.27.2
+- TRL: 0.28.0
 - Transformers: 4.57.1
 - Pytorch: 2.8.0+cu126
 - Datasets: 4.4.2
@@ -47,12 +47,11 @@ This model was trained with SFT.
 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},
-	year         = 2020,
-	journal      = {GitHub repository},
-	publisher    = {GitHub},
-	howpublished = {\url{https://github.com/huggingface/trl}}
+@software{vonwerra2020trl,
+  title   = {{TRL: Transformers Reinforcement Learning}},
+  author  = {von Werra, Leandro and Belkada, Younes and Tunstall, Lewis and Beeching, Edward and Thrush, Tristan and Lambert, Nathan and Huang, Shengyi and Rasul, Kashif and Gallouédec, Quentin},
+  license = {Apache-2.0},
+  url     = {https://github.com/huggingface/trl},
+  year    = {2020}
 }
 ```

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a5052d758d89f59c6e3e2b0f8f8edbbe08632647cfe498265f36f2bb69fc43ee
+oid sha256:a7809a7a336cdd1afc751efb35937ac2a73940b092025119951ca9872c5bc69b
 size 1072419256

runs/Feb14_13-38-21_9ca5c28012b5/events.out.tfevents.1771076994.9ca5c28012b5.65.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c26389e13eb550b19ff846f67399f873c3c4e126c1abf1e697cb35788d4ee220
+size 254604

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:80bd63b7109fd42b73648ecd62d5bd70345fe3cc364a9b2f4a250708a126c1f9
+oid sha256:a201640ba64cdd18261d8bc7d2fc4ade29e54906d680e10a52bdc26b7e0a0290
 size 6225