ymath/mistral-7binstruct-summary-100s

README.md

@@ -19,7 +19,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [mistralai/Mistral-7B-Instruct-v0.2](https://huggingface.co/mistralai/Mistral-7B-Instruct-v0.2) on the generator dataset.
 It achieves the following results on the evaluation set:
-- Loss: 1.4671
+- Loss: 1.4648
 
 ## Model description
 
@@ -51,8 +51,8 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch  | Step | Validation Loss |
 |:-------------:|:------:|:----:|:---------------:|
-| 1.692         | 0.2174 | 25   | 1.5555          |
-| 1.5401        | 0.4348 | 50   | 1.4671          |
+| 1.6929        | 0.2174 | 25   | 1.5559          |
+| 1.5408        | 0.4348 | 50   | 1.4648          |
 
 
 ### Framework versions

adapter_config.json

@@ -20,8 +20,8 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "v_proj",
-    "q_proj"
+    "q_proj",
+    "v_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:e44ce263e6fd885f50d82ca515b9325375b43ee36ededb75acf161ce88bc2e41
-size 48
+oid sha256:7a53f706ef14c6f3486c3fe3a2f7d90fec5219688ccb4a5c2f86c4af1dfc9b7d
+size 27280152

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b8389b78b4c21d2c7fc84e46046891d31957d2460fc46f11becfd6469f56efca
+oid sha256:3a919705c69c7fdcd31c7a6da908c283ebd38afe403fa2602f045af2d626c5e5
 size 4984