Revert "rahul4862/adapter-phi-3-mini"

This reverts commit 46a18595a28a0125ee568d156556ab29f55fe9e0.

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 an unknown dataset.
 It achieves the following results on the evaluation set:
-- Loss: 1.6901
+- Loss: 1.7121
 
 ## Model description
 
@@ -52,16 +52,43 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch  | Step | Validation Loss |
 |:-------------:|:------:|:----:|:---------------:|
-| 1.8562        | 0.6734 | 100  | 1.7290          |
-| 1.7394        | 1.3468 | 200  | 1.7045          |
-| 1.7176        | 2.0202 | 300  | 1.6950          |
-| 1.7102        | 2.6936 | 400  | 1.6901          |
+| 1.94          | 0.0953 | 100  | 1.8918          |
+| 1.8113        | 0.1907 | 200  | 1.7877          |
+| 1.7578        | 0.2860 | 300  | 1.7701          |
+| 1.756         | 0.3813 | 400  | 1.7637          |
+| 1.7632        | 0.4766 | 500  | 1.7582          |
+| 1.7477        | 0.5720 | 600  | 1.7542          |
+| 1.7605        | 0.6673 | 700  | 1.7508          |
+| 1.7312        | 0.7626 | 800  | 1.7482          |
+| 1.7315        | 0.8580 | 900  | 1.7439          |
+| 1.7148        | 0.9533 | 1000 | 1.7414          |
+| 1.7263        | 1.0486 | 1100 | 1.7385          |
+| 1.7184        | 1.1439 | 1200 | 1.7361          |
+| 1.7187        | 1.2393 | 1300 | 1.7336          |
+| 1.7231        | 1.3346 | 1400 | 1.7313          |
+| 1.7433        | 1.4299 | 1500 | 1.7290          |
+| 1.6962        | 1.5253 | 1600 | 1.7268          |
+| 1.7136        | 1.6206 | 1700 | 1.7253          |
+| 1.6969        | 1.7159 | 1800 | 1.7236          |
+| 1.7028        | 1.8112 | 1900 | 1.7217          |
+| 1.7066        | 1.9066 | 2000 | 1.7200          |
+| 1.7123        | 2.0019 | 2100 | 1.7191          |
+| 1.7005        | 2.0972 | 2200 | 1.7178          |
+| 1.7052        | 2.1926 | 2300 | 1.7168          |
+| 1.6946        | 2.2879 | 2400 | 1.7160          |
+| 1.6728        | 2.3832 | 2500 | 1.7150          |
+| 1.7033        | 2.4786 | 2600 | 1.7144          |
+| 1.6893        | 2.5739 | 2700 | 1.7136          |
+| 1.7206        | 2.6692 | 2800 | 1.7129          |
+| 1.6747        | 2.7645 | 2900 | 1.7126          |
+| 1.6981        | 2.8599 | 3000 | 1.7123          |
+| 1.6928        | 2.9552 | 3100 | 1.7121          |
 
 
 ### Framework versions
 
 - PEFT 0.12.0
-- Transformers 4.43.4
+- Transformers 4.43.3
 - Pytorch 2.3.1+cu121
 - Datasets 2.20.0
 - Tokenizers 0.19.1

adapter_config.json

@@ -20,13 +20,13 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "gate_proj",
-    "q_proj",
+    "k_proj",
     "up_proj",
-    "down_proj",
     "o_proj",
     "v_proj",
-    "k_proj"
+    "q_proj",
+    "gate_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 sha256:5794232b2ee5b76e73dbc7b568f45c5e7bde407a8676e5fe8a91fb0c665a951e
+oid sha256:c2c9769cc3e20938c52e84856d9503dc5c0ac655b4ca5e07772aae1c58f008e9
 size 35668592

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c73541313d0c94189bf7c46f17749d6f3c1981d626f56c44419af43a8ac2def6
+oid sha256:66b1502ea703ca20bf23fe8283e9579a8a32ae8648447b71e55cb6e204ceabec
 size 5432