EshAhm/LoRa-Python2

README.md

@@ -5,6 +5,7 @@ base_model: microsoft/phi-2
 tags:
 - base_model:adapter:microsoft/phi-2
 - lora
+- transformers
 pipeline_tag: text-generation
 model-index:
 - name: phi-2-LoRa-Python
@@ -18,7 +19,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [microsoft/phi-2](https://huggingface.co/microsoft/phi-2) on the None dataset.
 It achieves the following results on the evaluation set:
-- Loss: 4.4689
+- Loss: 4.4864
 
 ## Model description
 
@@ -52,28 +53,28 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch  | Step | Validation Loss |
 |:-------------:|:------:|:----:|:---------------:|
-| 4.5284        | 0.1333 | 100  | 4.4728          |
-| 4.4172        | 0.2667 | 200  | 4.4776          |
-| 4.2789        | 0.4    | 300  | 4.4774          |
-| 4.4041        | 0.5333 | 400  | 4.4751          |
-| 4.3978        | 0.6667 | 500  | 4.4777          |
-| 4.061         | 0.8    | 600  | 4.4762          |
-| 4.1693        | 0.9333 | 700  | 4.4764          |
-| 4.5403        | 1.0667 | 800  | 4.4727          |
-| 4.5481        | 1.2    | 900  | 4.4725          |
-| 4.0223        | 1.3333 | 1000 | 4.4757          |
-| 4.5108        | 1.4667 | 1100 | 4.4747          |
-| 4.0763        | 1.6    | 1200 | 4.4719          |
-| 4.1443        | 1.7333 | 1300 | 4.4723          |
-| 4.4699        | 1.8667 | 1400 | 4.4738          |
-| 4.7084        | 2.0    | 1500 | 4.4713          |
-| 3.9716        | 2.1333 | 1600 | 4.4710          |
-| 4.5229        | 2.2667 | 1700 | 4.4711          |
-| 3.8189        | 2.4    | 1800 | 4.4702          |
-| 4.6479        | 2.5333 | 1900 | 4.4695          |
-| 4.4305        | 2.6667 | 2000 | 4.4690          |
-| 4.2955        | 2.8    | 2100 | 4.4690          |
-| 4.2989        | 2.9333 | 2200 | 4.4689          |
+| 4.5433        | 0.1333 | 100  | 4.4747          |
+| 4.4162        | 0.2667 | 200  | 4.4774          |
+| 4.2759        | 0.4    | 300  | 4.4755          |
+| 4.4021        | 0.5333 | 400  | 4.4764          |
+| 4.3925        | 0.6667 | 500  | 4.4775          |
+| 4.6016        | 0.8    | 600  | 4.5976          |
+| 4.2527        | 0.9333 | 700  | 4.5484          |
+| 4.5823        | 1.0667 | 800  | 4.5037          |
+| 4.5826        | 1.2    | 900  | 4.5032          |
+| 4.0654        | 1.3333 | 1000 | 4.5073          |
+| 4.5386        | 1.4667 | 1100 | 4.4961          |
+| 4.1046        | 1.6    | 1200 | 4.4957          |
+| 4.1705        | 1.7333 | 1300 | 4.4943          |
+| 4.4922        | 1.8667 | 1400 | 4.4918          |
+| 4.7333        | 2.0    | 1500 | 4.4901          |
+| 3.997         | 2.1333 | 1600 | 4.4889          |
+| 4.5407        | 2.2667 | 1700 | 4.4880          |
+| 3.8457        | 2.4    | 1800 | 4.4877          |
+| 4.6653        | 2.5333 | 1900 | 4.4873          |
+| 4.4524        | 2.6667 | 2000 | 4.4865          |
+| 4.3138        | 2.8    | 2100 | 4.4870          |
+| 4.3203        | 2.9333 | 2200 | 4.4865          |
 
 
 ### Framework versions

adapter_config.json

@@ -1,7 +1,7 @@
 {
   "alpha_pattern": {},
   "auto_mapping": null,
-  "base_model_name_or_path": null,
+  "base_model_name_or_path": "microsoft/phi-2",
   "bias": "none",
   "corda_config": null,
   "eva_config": null,
@@ -25,10 +25,10 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "v_proj",
     "k_proj",
     "dense",
-    "q_proj"
+    "q_proj",
+    "v_proj"
   ],
   "target_parameters": null,
   "task_type": "CAUSAL_LM",

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2746cc7bdcac3d6b58df64efac21ef3160762157b0ea2c2af8976c80df4b6ef8
-size 83924816
+oid sha256:d0cb54926955f8465684c4f5a5d7fa4f8f6a6a2ecb1b624fdca9677961b29f12
+size 83920464

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:77a7985546e2331302690dc943aa4032cf03d6e8a512705d41ba11c33fac01ec
+oid sha256:92c05c04197940bf30d25a6ee8a5208e08514d553240522c61099e94cceb9a3b
 size 5777