End of training

README.md

@@ -27,17 +27,18 @@ print(output["generated_text"])
 
 ## Training procedure
 
+ 
 
 
 This model was trained with SFT.
 
 ### Framework versions
 
-- TRL: 0.12.2
-- Transformers: 4.46.3
+- TRL: 0.13.0
+- Transformers: 4.47.1
 - Pytorch: 2.5.1+cu121
 - Datasets: 3.2.0
-- Tokenizers: 0.20.3
+- Tokenizers: 0.21.0
 
 ## Citations
 

adapter_config.json

@@ -23,12 +23,12 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "q_proj",
-    "up_proj",
-    "down_proj",
     "o_proj",
+    "up_proj",
     "v_proj",
     "k_proj",
+    "q_proj",
+    "down_proj",
     "gate_proj"
   ],
   "task_type": "CAUSAL_LM",

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a1ce3f79e35c7f7812a6ab7b1130e384ed61a50e057f55081e85d5a156d9ef21
+oid sha256:849bf486e8d8a7f83a04b71c31713b161d519d61c63b41bd97421e4fa3d07390
 size 2332095256

runs/Dec22_14-04-53_b7e549e10e5f/events.out.tfevents.1734876308.b7e549e10e5f.5931.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2dc5e4d9ac2bde2aca0b5797d97192cccc5ae10771ed3e3eaaaa9bd284d8227f
+size 182270

tokenizer_config.json

@@ -78,6 +78,7 @@
   "clean_up_tokenization_spaces": false,
   "eos_token": "</s>",
   "eot_token": "▁<EOT>",
+  "extra_special_tokens": {},
   "fill_token": "<FILL_ME>",
   "legacy": null,
   "middle_token": "▁<MID>",

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e27b34c197e15df32f32379c11b3fde527439c8709751b5f548d576bae9abcc8
-size 5560
+oid sha256:282286dc8bbe6445ca0ecef09efaf67874c790156e11533cc93bc11bf0ccef78
+size 5624