Model save

README.md

@@ -51,7 +51,7 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss |
 |:-------------:|:-----:|:----:|:---------------:|
-| No log        | 1.0   | 1    | 1.9766          |
+| No log        | 1.0   | 1    | 1.8099          |
 
 
 ### Framework versions

adapter_config.json

@@ -23,13 +23,13 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "v_proj",
-    "o_proj",
-    "down_proj",
+    "up_proj",
+    "k_proj",
     "q_proj",
     "gate_proj",
-    "up_proj",
-    "k_proj"
+    "v_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 sha256:01499542463e3b74eb87368fc773484c76ae96c919da1e612fb6375e9ab4ec7c
-size 8820250192
+oid sha256:e4e7c70b69f5bfd1902d13f38ebf24e6dbe1c5233de6df1a2d214c2a7b782e24
+size 414337624

runs/Jan04_14-52-48_gpu-server/events.out.tfevents.1736002546.gpu-server.1672766.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9a660646e712ceae4e5b31535582660c3befc7f5e625374fac74260259974439
-size 5642
+oid sha256:c13fff9bf0b7f43b88734f3c2089f1fb2b8c308e4af1999ebd082b8874aeec94
+size 6256