End of training

README.md

@@ -95,7 +95,7 @@ xformers_attention: true
 
 This model is a fine-tuned version of [jhflow/mistral7b-lora-multi-turn-v2](https://huggingface.co/jhflow/mistral7b-lora-multi-turn-v2) on the None dataset.
 It achieves the following results on the evaluation set:
-- Loss: 2.0885
+- Loss: 2.0884
 
 ## Model description
 
@@ -133,8 +133,8 @@ The following hyperparameters were used during training:
 | Training Loss | Epoch  | Step | Validation Loss |
 |:-------------:|:------:|:----:|:---------------:|
 | 1.8825        | 0.0031 | 1    | 2.3788          |
-| 2.2226        | 0.0766 | 25   | 2.1118          |
-| 2.0586        | 0.1533 | 50   | 2.0885          |
+| 2.2213        | 0.0766 | 25   | 2.1134          |
+| 2.0582        | 0.1533 | 50   | 2.0884          |
 
 
 ### Framework versions

adapter_config.json

@@ -20,13 +20,13 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "k_proj",
-    "q_proj",
+    "v_proj",
     "up_proj",
-    "o_proj",
+    "k_proj",
     "gate_proj",
-    "v_proj",
-    "down_proj"
+    "down_proj",
+    "q_proj",
+    "o_proj"
   ],
   "task_type": "CAUSAL_LM",
   "use_dora": false,

adapter_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:388b9b2c6e80517477bd2744c66c0e3775c3e5c95ff7815899a4941b8c13f219
+oid sha256:d392f243ecf109170111a71b7dd47729653755bac555890c6edd01a356e0b569
 size 335706186

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5704821e9918d31c0d0acaa3815aadbaec64194cb9aad364d12dbb02f99aef36
+oid sha256:57c84eeeff235235a4a863df3f19b945a27ae19cebb81e2291b8e0881cd54c2d
 size 335604696

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b2ed31e570494779bd86d653ae545f1873d662b7f560837aac5f1782bcac42cc
+oid sha256:1baeee59f7debef1f8d94258da455d503cad8cc40f091043441d3366e0216a96
 size 6776