shouray/Condition-Model-2

README.md

@@ -1,9 +1,9 @@
 ---
-license: llama2
+base_model: TheBloke/Llama-2-13B-chat-GPTQ
 library_name: peft
+license: llama2
 tags:
 - generated_from_trainer
-base_model: TheBloke/Llama-2-13B-chat-GPTQ
 model-index:
 - name: qlora
   results: []
@@ -16,7 +16,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [TheBloke/Llama-2-13B-chat-GPTQ](https://huggingface.co/TheBloke/Llama-2-13B-chat-GPTQ) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.2281
+- Loss: 0.0570
 
 ## Model description
 
@@ -51,26 +51,26 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss |
 |:-------------:|:-----:|:----:|:---------------:|
-| 1.7256        | 1.0   | 1    | 2.3492          |
-| 0.8422        | 2.0   | 3    | 2.0594          |
-| 0.7278        | 3.0   | 5    | 1.6949          |
-| 1.2299        | 4.0   | 6    | 1.5504          |
-| 1.1219        | 5.0   | 7    | 1.4207          |
-| 0.4884        | 6.0   | 9    | 1.2156          |
-| 0.4229        | 7.0   | 11   | 0.9934          |
-| 0.7082        | 8.0   | 12   | 0.8837          |
-| 0.6263        | 9.0   | 13   | 0.7754          |
-| 0.2502        | 10.0  | 15   | 0.5958          |
-| 0.1915        | 11.0  | 17   | 0.4347          |
-| 0.2841        | 12.0  | 18   | 0.3766          |
-| 0.2395        | 13.0  | 19   | 0.3339          |
-| 0.0959        | 14.0  | 21   | 0.2914          |
-| 0.0808        | 15.0  | 23   | 0.2631          |
-| 0.1391        | 16.0  | 24   | 0.2533          |
-| 0.13          | 17.0  | 25   | 0.2434          |
-| 0.0589        | 18.0  | 27   | 0.2357          |
-| 0.0558        | 19.0  | 29   | 0.2298          |
-| 0.1076        | 20.0  | 30   | 0.2281          |
+| 0.8           | 1.0   | 1    | 1.0124          |
+| 0.3868        | 2.0   | 3    | 0.8254          |
+| 0.3112        | 3.0   | 5    | 0.5926          |
+| 0.4737        | 4.0   | 6    | 0.5064          |
+| 0.4067        | 5.0   | 7    | 0.4373          |
+| 0.163         | 6.0   | 9    | 0.3445          |
+| 0.1325        | 7.0   | 11   | 0.2647          |
+| 0.2128        | 8.0   | 12   | 0.2263          |
+| 0.1826        | 9.0   | 13   | 0.1899          |
+| 0.0706        | 10.0  | 15   | 0.1438          |
+| 0.0574        | 11.0  | 17   | 0.1187          |
+| 0.0971        | 12.0  | 18   | 0.1078          |
+| 0.0864        | 13.0  | 19   | 0.0992          |
+| 0.0372        | 14.0  | 21   | 0.0841          |
+| 0.0318        | 15.0  | 23   | 0.0729          |
+| 0.0572        | 16.0  | 24   | 0.0688          |
+| 0.0539        | 17.0  | 25   | 0.0657          |
+| 0.0249        | 18.0  | 27   | 0.0609          |
+| 0.0231        | 19.0  | 29   | 0.0577          |
+| 0.044         | 20.0  | 30   | 0.0570          |
 
 
 ### Framework versions

adapter_config.json

@@ -20,10 +20,10 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "k_proj",
-    "q_proj",
     "o_proj",
-    "v_proj"
+    "k_proj",
+    "v_proj",
+    "q_proj"
   ],
   "task_type": "CAUSAL_LM",
   "use_dora": false,

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:32cb0c34b918a098f8049525bd83fd8078a5f2306024537195072170e79b57fd
+oid sha256:a790be2ccc118bf5f53205683a05aaab2038957693175722da253a20b2dc31d0
 size 52471504

runs/Jun20_21-55-30_9a43862ea95a/events.out.tfevents.1718920531.9a43862ea95a.168.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9057671a96f5af391fd709e0a5255a7c12b62966a1ba42dd0f66030cab05bd67
+size 15372

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c87801c6747a4cd159adbfe4f2017b4086ce356a7f6327f2e2eb3f5e8fd66427
+oid sha256:5cec7146a65f7d55f647021da9410ca0431bcca38582b3cd4a842a4c6032570b
 size 5112