End of training

README.md

@@ -36,8 +36,8 @@ This model was trained with SFT.
 
 - TRL: 0.15.1
 - Transformers: 4.49.0
-- Pytorch: 2.4.1+cu121
-- Datasets: 3.2.0
+- Pytorch: 2.5.1+cu121
+- Datasets: 3.3.1
 - Tokenizers: 0.21.0
 
 ## Citations

adapter_config.json

@@ -12,22 +12,22 @@
   "layers_pattern": null,
   "layers_to_transform": null,
   "loftq_config": {},
-  "lora_alpha": 32,
+  "lora_alpha": 8,
   "lora_bias": false,
   "lora_dropout": 0.05,
   "megatron_config": null,
   "megatron_core": "megatron.core",
   "modules_to_save": null,
   "peft_type": "LORA",
-  "r": 8,
+  "r": 16,
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "q_proj",
-    "v_proj",
-    "gate_proj",
     "o_proj",
     "k_proj",
+    "gate_proj",
+    "q_proj",
+    "v_proj",
     "up_proj",
     "down_proj"
   ],

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a2f7aac257193429b2d0b249169272f4779908ca9c4c180572b7007f44ab8e80
-size 48679352
+oid sha256:4f18a823d269720f308bd71bfb4672017bd2cb2254c4d393036c1fbbe1aa4a89
+size 97307544

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bff0889f4e69961d2cfe60b76d01f2cc8932e1251c18f43875d3cfce5e9bee1a
+oid sha256:986b67fd0aedf9101749792ccb23747b957837b5e8ed1d458a996e48342f7a3d
 size 5624