End of training

README.md

@@ -20,7 +20,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 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: 1.0141
+- Loss: 0.9941
 
 ## Model description
 
@@ -52,11 +52,11 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss |
 |:-------------:|:-----:|:----:|:---------------:|
-| 1.0245        | 1.25  | 20   | 0.9835          |
-| 0.833         | 2.5   | 40   | 0.9249          |
-| 0.7451        | 3.75  | 60   | 0.9172          |
-| 0.6741        | 5.0   | 80   | 0.9335          |
-| 0.5957        | 6.25  | 100  | 1.0141          |
+| 1.0455        | 1.25  | 20   | 0.9839          |
+| 0.8594        | 2.5   | 40   | 0.9259          |
+| 0.7674        | 3.75  | 60   | 0.9125          |
+| 0.6763        | 5.0   | 80   | 0.9213          |
+| 0.5779        | 6.25  | 100  | 0.9941          |
 
 
 ### Framework versions

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f25cb8bc11ff3405d94d8ef0da21908bffc976d06bae27d352da056451175a0d
+oid sha256:63d1b3fef86af3898d8f023f28c5025731427004b29bbb8f9ba48baa9c6e171d
 size 109069176

runs/Mar12_06-35-03_95d8353d3044/events.out.tfevents.1710225328.95d8353d3044.114.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:18a9c484adff2cd9c8ecee35240ea4fb0b9b2dd7f4819c2ad752d9b15658be8d
+size 8015

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5fd16ac66f553d6c601e2f5a75b1c9a9ef7e8fb05141fcba9499d58d44d98fef
+oid sha256:4c3dc62a01c9d3d21ba3a250c8f738e32c7dd05d5ac555c4b04c4c4cb7c0d316
 size 4728