End of training

README.md

@@ -105,7 +105,7 @@ xformers_attention: true
 
 This model is a fine-tuned version of [Artples/L-MChat-7b](https://huggingface.co/Artples/L-MChat-7b) on the None dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.0398
+- Loss: 0.0373
 
 ## Model description
 
@@ -143,8 +143,8 @@ The following hyperparameters were used during training:
 | Training Loss | Epoch  | Step | Validation Loss |
 |:-------------:|:------:|:----:|:---------------:|
 | 61.3338       | 0.0528 | 1    | 3.5628          |
-| 0.9758        | 1.3498 | 25   | 0.1138          |
-| 0.2619        | 2.6997 | 50   | 0.0398          |
+| 0.8231        | 1.3498 | 25   | 0.0906          |
+| 0.285         | 2.6997 | 50   | 0.0373          |
 
 
 ### Framework versions

adapter_config.json

@@ -21,10 +21,10 @@
   "revision": null,
   "target_modules": [
     "k_proj",
-    "down_proj",
-    "gate_proj",
     "q_proj",
+    "gate_proj",
     "v_proj",
+    "down_proj",
     "up_proj",
     "o_proj"
   ],

adapter_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ef8cf0cc5c6ef8f55312bbca3a4f5ef99a8984fd8f72267a8e2559fc1757a98b
+oid sha256:b8d3bf2b588a0c24356a19e37429f67fc1d3580ce7c610189c97635c043fc569
 size 335706186

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:020b5754070bfaf7eaf5513f8adb989bb64a52299a64a292eef6230e71963075
+oid sha256:3446403d2f0c7e1833fe69ae3f77b5a43536a61c7a2973ebdce45154acfcf01f
 size 335604696

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fce2681dc79991c6f33e2d27573b5f6d6f5cf0f1fcde8d296e5d63aeff6c313b
+oid sha256:5dd421ee496f84b943e667379d94c279e81d013b511fd3641f3973aa3000a968
 size 6776