End of training

README.md

@@ -16,7 +16,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [mistralai/Mistral-7B-v0.1](https://huggingface.co/mistralai/Mistral-7B-v0.1) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Loss: 1.3865
+- Loss: 1.3613
 
 ## Model description
 
@@ -48,9 +48,9 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss |
 |:-------------:|:-----:|:----:|:---------------:|
-| 0.9372        | 1.0   | 50   | 1.1058          |
-| 0.442         | 2.0   | 100  | 1.3338          |
-| 0.4032        | 3.0   | 150  | 1.3865          |
+| 0.9514        | 1.0   | 50   | 1.1079          |
+| 0.4733        | 2.0   | 100  | 1.3809          |
+| 0.398         | 3.0   | 150  | 1.3613          |
 
 
 ### Framework versions

adapter_config.json

@@ -22,12 +22,12 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "k_proj",
-    "gate_proj",
+    "o_proj",
     "v_proj",
     "down_proj",
+    "k_proj",
     "up_proj",
-    "o_proj",
+    "gate_proj",
     "q_proj"
   ],
   "task_type": "CAUSAL_LM"

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1960f98740b19a99da1860b2f7b576c952ececd2eb269986fdfa217ba9ee169a
+oid sha256:f657825d3a4710ce025498fd39abe8abe17ee7fed5519d758783d80f4b26d4b5
 size 1719726424

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a8ed5d80f4a69a0002c3515cb0ebac5b6388c6e0c850bf9ad8590259eb7243cc
+oid sha256:35a5397206dac42c321c66abb698236f02927727390bfcb6d851d40f6ecf1bc6
 size 4728