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: 1.4548
+- Loss: 1.4542
 
 ## Model description
 
@@ -51,8 +51,8 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch  | Step | Validation Loss |
 |:-------------:|:------:|:----:|:---------------:|
-| 1.5408        | 0.2174 | 25   | 1.4671          |
-| 1.5391        | 0.4348 | 50   | 1.4548          |
+| 1.5062        | 0.2174 | 25   | 1.4632          |
+| 1.5253        | 0.4348 | 50   | 1.4542          |
 
 
 ### Framework versions

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e44ce263e6fd885f50d82ca515b9325375b43ee36ededb75acf161ce88bc2e41
-size 48
+oid sha256:dd029680b70943377c4c6a2c7cdbc2c59d0efb470953d3bd77e2c2d6dd92c76c
+size 27284504

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ab7a0b65ef9047dcc97d854d90a9d95a84ffe9da19cc079646fcd22c3754844e
+oid sha256:349bdccd339aa968646e63835c60e5fd67200b1a4e04674e6138b882d447c902
 size 4984