Model save

README.md

@@ -18,10 +18,10 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [mistralai/Mistral-7B-Instruct-v0.3](https://huggingface.co/mistralai/Mistral-7B-Instruct-v0.3) on the None dataset.
 It achieves the following results on the evaluation set:
-- Loss: 2.1006
-- Model Preparation Time: 0.0062
-- Accuracy: 0.5632
-- Perplexity: 8.1712
+- Loss: 1.6632
+- Model Preparation Time: 0.006
+- Accuracy: 0.6411
+- Perplexity: 5.2760
 
 ## Model description
 
@@ -53,9 +53,9 @@ The following hyperparameters were used during training:
 
 ### Training results
 
-| Training Loss | Epoch | Step | Validation Loss | Model Preparation Time | Accuracy | Perplexity |
-|:-------------:|:-----:|:----:|:---------------:|:----------------------:|:--------:|:----------:|
-| 2.0506        | 1.0   | 4995 | 2.1006          | 0.0062                 | 0.5632   | 8.1712     |
+| Training Loss | Epoch  | Step  | Validation Loss | Model Preparation Time | Accuracy | Perplexity |
+|:-------------:|:------:|:-----:|:---------------:|:----------------------:|:--------:|:----------:|
+| 1.7317        | 1.0000 | 30564 | 1.6632          | 0.006                  | 0.6411   | 5.2760     |
 
 
 ### Framework versions

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 sha256:4534e5c31a6f9cf3584a0a96e3ec41b118bc8ea25fbfe8c6efb42eb40611e81b
+oid sha256:eda765dab7dc66c73b984d32bfae8242f708f6cff87de02b9329e3a0dc7eb4a0
 size 27280152

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d1584503202b26ec947f6d9f3b85e39a3be6f59f903479f0030a2a257465e197
+oid sha256:defd0961db880caa628e0907319242160c364731f567cf1ad5059b6a50c16cc1
 size 5432