End of training

README.md

@@ -104,7 +104,7 @@ xformers_attention: true
 
 This model is a fine-tuned version of [NousResearch/Yarn-Mistral-7b-128k](https://huggingface.co/NousResearch/Yarn-Mistral-7b-128k) on the None dataset.
 It achieves the following results on the evaluation set:
-- Loss: 1.0360
+- Loss: 1.0354
 
 ## Model description
 
@@ -142,8 +142,8 @@ The following hyperparameters were used during training:
 | Training Loss | Epoch  | Step | Validation Loss |
 |:-------------:|:------:|:----:|:---------------:|
 | 1.7005        | 0.0124 | 1    | 1.5441          |
-| 0.9647        | 0.3091 | 25   | 1.0565          |
-| 0.9203        | 0.6182 | 50   | 1.0360          |
+| 0.9649        | 0.3091 | 25   | 1.0556          |
+| 0.9192        | 0.6182 | 50   | 1.0354          |
 
 
 ### Framework versions

adapter_config.json

@@ -20,13 +20,13 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "o_proj",
     "up_proj",
     "q_proj",
+    "k_proj",
     "gate_proj",
     "down_proj",
     "v_proj",
-    "k_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 sha256:98a161e02ddd69da4bd3d1ea2cd987f07a7455614c5069d7a7a02d4619f3cab5
+oid sha256:0aa6348b9df39a35e85bcde5fa2600cf277fdc34f6a2e9e45c004c6b987969af
 size 335706186

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8aa329c5af8be49237ec6cbf7cd7b41a9d168f1bd675bb8dd6c40d1f9e518fa0
+oid sha256:20dba402be068580d83c349df7bfa19ffa24da5405bb81aac9b521966ba1281b
 size 335604696

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7ec7a24b66787d2564811f1dc1209b71bc9e9e6e058875b5a7e97f8a60519fc7
+oid sha256:d5088dc23c6397af8783b01b33eec8575b490cbf9f4f4e1a8c92e7c4b1b56b82
 size 6776