End of training

README.md

@@ -18,7 +18,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [microsoft/Phi-3.5-mini-instruct](https://huggingface.co/microsoft/Phi-3.5-mini-instruct) on the None dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.1667
+- Loss: 0.3710
 
 ## Model description
 
@@ -46,14 +46,13 @@ The following hyperparameters were used during training:
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
 - lr_scheduler_warmup_ratio: 0.1
-- training_steps: 52
+- training_steps: 12
 
 ### Training results
 
 | Training Loss | Epoch  | Step | Validation Loss |
 |:-------------:|:------:|:----:|:---------------:|
-| 0.3316        | 0.1852 | 25   | 0.2099          |
-| 0.1567        | 0.3704 | 50   | 0.1667          |
+| 3.3127        | 0.0741 | 10   | 0.3710          |
 
 
 ### Framework versions

adapter_config.json

@@ -20,13 +20,13 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "q_proj",
-    "v_proj",
-    "k_proj",
     "down_proj",
     "gate_proj",
     "o_proj",
-    "up_proj"
+    "k_proj",
+    "q_proj",
+    "up_proj",
+    "v_proj"
   ],
   "task_type": "CAUSAL_LM",
   "use_dora": false,

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5bc5f7844254d65aeed2b9147fc8bea07b5972c83b18f679ad5424ffd972981a
+oid sha256:81fe87a0bb399e45dcab0db76602e0b1b639219a6bf39d618f6f0e947d0057b9
 size 35669232

runs/Oct18_15-57-55_8ce57b37d7a3/events.out.tfevents.1729267081.8ce57b37d7a3.775.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a6d1bfa1c80fad77cf88d44914086b7a603dc16092640702f456d7c6993ff6ac
+size 9559

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9bec72c5bff4340c7a8eb9edc63f3762ed5f8966db95753b023434944d73a950
+oid sha256:3380d1505cf80dcedcd701332deba22e6bb8ae07aeed74080ea5d1e4342cbb6b
 size 5560