End of training

README.md

@@ -19,8 +19,6 @@ should probably proofread and complete it, then remove this comment. -->
 # Mistral
 
 This model is a fine-tuned version of [mistralai/Mistral-7B-Instruct-v0.1](https://huggingface.co/mistralai/Mistral-7B-Instruct-v0.1) on the generator dataset.
-It achieves the following results on the evaluation set:
-- Loss: 0.8892
 
 ## Model description
 
@@ -48,17 +46,6 @@ The following hyperparameters were used during training:
 - lr_scheduler_warmup_steps: 0.03
 - training_steps: 100
 
-### Training results
-
-| Training Loss | Epoch | Step | Validation Loss |
-|:-------------:|:-----:|:----:|:---------------:|
-| 1.2479        | 1.05  | 20   | 1.0203          |
-| 0.7783        | 2.11  | 40   | 0.8369          |
-| 0.6816        | 3.16  | 60   | 0.8164          |
-| 0.5776        | 4.21  | 80   | 0.8447          |
-| 0.5015        | 5.26  | 100  | 0.8892          |
-
-
 ### Framework versions
 
 - PEFT 0.10.0

adapter_config.json

@@ -20,8 +20,8 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "q_proj",
-    "v_proj"
+    "v_proj",
+    "q_proj"
   ],
   "task_type": "CAUSAL_LM",
   "use_dora": false,

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b8e5e7e047059cfef28aff25f4ebe131aa10e9254cd4010319eba5a1277aed6b
+oid sha256:6e023d90885eda29a96bfe39c0a02811ac84e7b3ecc9eabb236dc017b6ed3d3c
 size 109069176

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0b64efa0c04b6e7760bd13fbf5f6e5b22a86325ac5ab5cf88fa683681e3c0cc2
+oid sha256:05c4481f9df24562931185effa86230a85be7f14d10de3ca85933c9739a5251c
 size 5048