pepe213/chandrika-ft-v3

README.md

@@ -16,7 +16,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [microsoft/Phi-4-mini-instruct](https://huggingface.co/microsoft/Phi-4-mini-instruct) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.0602
+- Loss: 0.0591
 
 ## Model description
 
@@ -49,10 +49,10 @@ The following hyperparameters were used during training:
 
 ### Training results
 
-| Training Loss | Epoch  | Step | Validation Loss |
-|:-------------:|:------:|:----:|:---------------:|
-| 0.7882        | 1.0    | 18   | 0.2160          |
-| 0.1026        | 1.9143 | 34   | 0.0602          |
+| Training Loss | Epoch | Step | Validation Loss |
+|:-------------:|:-----:|:----:|:---------------:|
+| 0.7776        | 0.96  | 18   | 0.1829          |
+| 0.088         | 1.96  | 36   | 0.0591          |
 
 
 ### Framework versions

adapter_config.json

@@ -23,13 +23,13 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
+    "down_proj",
     "o_proj",
-    "v_proj",
-    "up_proj",
-    "k_proj",
     "q_proj",
-    "down_proj",
-    "gate_proj"
+    "gate_proj",
+    "k_proj",
+    "v_proj",
+    "up_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:d0d6b33a9a46eb7693b27af16a3567ee5cf1d7f2b3851ab85d15c1e460e4f963
+oid sha256:9711dff13c811c809af3fd27522f55d977eea1034557796970bf617d91f2ffc2
 size 17842592

runs/Apr12_19-02-33_a12b53588639/events.out.tfevents.1744484556.a12b53588639.28348.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7f3c93b2a7f149f09a47d985fe3ea196948cdccbc871a6378e3d34be23571d67
+size 8758

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dcd906f24a14579929f16cf1dc2ff4d9638df22feba217dff21144e667c20fc3
+oid sha256:4d7da666e0d07594c42a276de042b81a54dee9827fea32437cbbf1057fd6275f
 size 5368