Professor/phiner2

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-mini-4k-instruct](https://huggingface.co/microsoft/Phi-3-mini-4k-instruct) on the None dataset.
 It achieves the following results on the evaluation set:
-- Loss: 1.8122
+- Loss: 3.3835
 
 ## Model description
 
@@ -53,10 +53,10 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss |
 |:-------------:|:-----:|:----:|:---------------:|
-| No log        | 1.0   | 5    | 2.7710          |
-| No log        | 2.0   | 10   | 2.0554          |
-| No log        | 3.0   | 15   | 1.8377          |
-| No log        | 4.0   | 20   | 1.8122          |
+| No log        | 1.0   | 1    | 3.8530          |
+| No log        | 2.0   | 2    | 3.6124          |
+| No log        | 3.0   | 3    | 3.4412          |
+| No log        | 4.0   | 4    | 3.3835          |
 
 
 ### Framework versions

adapter_config.json

@@ -20,10 +20,10 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "qkv_proj",
     "o_proj",
-    "gate_up_proj",
-    "down_proj"
+    "down_proj",
+    "qkv_proj",
+    "gate_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:fe4f5aebb3b2ac64837a9eae3cf929fd3bc5cd352dacab30aa98cfd4d2c2e887
+oid sha256:c24a3e1169ec25022a33d6737f0667d30d88df991499c133b655928bf186f15e
 size 100697728

runs/Sep11_16-12-02_851156c6a784/events.out.tfevents.1726071123.851156c6a784.36.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d510403ab3bd66e5dc46ba21baaf6da84a6705476fe5de2e982e121e4b8d5bae
+size 7263

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:334fc63f288d69e3abcbb5daa5a388d18b521dc1dfd13fe85bb96daeda2084cc
+oid sha256:37aeb61e58ad55f458165ebc62de2efa3259c31b5cfdece809151365c91e1f9d
 size 5240