End of training

README.md

@@ -35,7 +35,7 @@ This model was trained with SFT.
 
 - TRL: 0.12.0
 - Transformers: 4.46.2
-- Pytorch: 2.3.0
+- Pytorch: 2.5.1
 - Datasets: 3.1.0
 - Tokenizers: 0.20.3
 

adapter_config.json

@@ -21,9 +21,9 @@
   "revision": null,
   "target_modules": [
     "qkv_proj",
+    "o_proj",
     "gate_up_proj",
-    "down_proj",
-    "o_proj"
+    "down_proj"
   ],
   "task_type": "CAUSAL_LM",
   "use_dora": false,

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7d41f2c5ea984bd9a448b196029b7799521cbdae7957559f68d063d08e9dac9f
+oid sha256:c367a9a00326d65f647674ac4e78bdb2218e26c557a7be8b5440510ab4d8f4c1
 size 402688040

runs/Dec06_06-52-59_e18105abca6d/events.out.tfevents.1733467984.e18105abca6d.990.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:89c4283b256431e2fed0b240d86b380ab442659d96481da2f30fa85480f89ee1
+size 55548

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:36ec25ca36266515a0532685286b4820aea030f2957030fbc761c020a5bb97e9
+oid sha256:3875142473c372e1b1002d98734c7c92a79e238656f0dec4e8b4623b4518408b
 size 5560