End of training

README.md

@@ -34,10 +34,10 @@ This model was trained with SFT.
 
 ### Framework versions
 
-- TRL: 0.15.2
+- TRL: 0.21.0
 - Transformers: 4.55.0
 - Pytorch: 2.8.0.dev20250319+cu128
-- Datasets: 3.3.2
+- Datasets: 4.0.0
 - 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 Gallouédec},
+	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},

adapter_config.json

@@ -26,16 +26,16 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "fc1",
+    "up_proj",
+    "out_proj",
     "o_proj",
+    "fc2",
     "q_proj",
-    "gate_proj",
-    "up_proj",
+    "fc1",
     "v_proj",
     "down_proj",
-    "fc2",
-    "k_proj",
-    "out_proj"
+    "gate_proj",
+    "k_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:bd06f5f4cb5a66cc708ef328c4980735ee57b00249d9bae976ff963e788e07c0
-size 2723633656
+oid sha256:2bd19e04ee2ca14423520f3795b4951beeec761e658ee314d0b4a561679d67fc
+size 2762129216

runs/Aug09_19-43-13_e90b6039d39d/events.out.tfevents.1754768611.e90b6039d39d.1521.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:df7384ce97c370abdeaa5e5588f017c2b3875be08b6a35310dcb683fb7771083
+size 9329

tokenizer_config.json

@@ -51334,12 +51334,8 @@
     "image_token": "<image_soft_token>"
   },
   "image_token": "<image_soft_token>",
-  "max_length": null,
   "model_max_length": 1000000000000000019884624838656,
-  "pad_to_multiple_of": null,
   "pad_token": "<pad>",
-  "pad_token_type_id": 0,
-  "padding_side": "left",
   "processor_class": "Gemma3Processor",
   "sp_model_kwargs": null,
   "spaces_between_special_tokens": false,

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cbdb6c5159f9e871eaf8a63861f8d1a51555f66b5ffed680a96f0c125b95c05d
+oid sha256:a16e22bc3b6cf7965bc189229806c8c4b7988d0cbdbbcd4197bc7cf289515258
 size 6033