Model save

README.md

@@ -19,6 +19,8 @@ should probably proofread and complete it, then remove this comment. -->
 # Mistral-7B-3
 
 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 generator dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.0440
 
 ## Model description
 
@@ -51,6 +53,9 @@ The following hyperparameters were used during training:
 
 ### Training results
 
+| Training Loss | Epoch | Step | Validation Loss |
+|:-------------:|:-----:|:----:|:---------------:|
+| 0.5413        | 1.51  | 10   | 0.0440          |
 
 
 ### Framework versions

runs/Jan22_10-55-49_ip-172-31-10-206.us-east-2.compute.internal/events.out.tfevents.1737543389.ip-172-31-10-206.us-east-2.compute.internal.14337.1

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e381e70121bfa21ef25fc8115c66dc85818f65a9a4da17f2001ec81d5e723455
-size 5513
+oid sha256:436f60e68eca6454bba43f424b8766dfa9c561fdacf75da12d372f10b04756f4
+size 5861