End of training

README.md

@@ -18,7 +18,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [LeoLM/leo-mistral-hessianai-7b-chat](https://huggingface.co/LeoLM/leo-mistral-hessianai-7b-chat) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Loss: 1.9194
+- Loss: 2.6241
 
 ## Model description
 
@@ -52,7 +52,7 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss |
 |:-------------:|:-----:|:----:|:---------------:|
-| 2.1214        | 1.0   | 312  | 1.9194          |
+| 2.6723        | 0.99  | 62   | 2.6241          |
 
 
 ### Framework versions

adapter_config.json

@@ -19,11 +19,11 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "gate_proj",
     "up_proj",
-    "k_proj",
     "q_proj",
     "o_proj",
+    "k_proj",
+    "gate_proj",
     "v_proj",
     "down_proj"
   ],

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:43fd875f62ea00eea4bcb76fcb5ebb5f28ca95ab61e0f2c24647936e32e28a7c
+oid sha256:0360398c748ac5df5c09ad4aa5da7022afedbb1ccdc812a4f0cf089eea1b02cc
 size 83945296

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0cc70fee4a8b70fa3e111f252b5abc862338e512a40cf267e0689cc97a48f7d9
+oid sha256:4c774b0b8b6eeed0829576644108a87d0a830175d98ed53cb65990c206ecd50e
 size 4664