Abhay11
/

RewardModel

Generated from Trainer

Model card Files Files and versions

Abhay11 commited on Apr 28, 2024

Commit

7e2f8a2

·

verified ·

1 Parent(s): f2033a7

Model save

Files changed (2) hide show

README.md +5 -5
adapter_model.safetensors +1 -1

README.md CHANGED Viewed

@@ -19,8 +19,8 @@ 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 None dataset.
 It achieves the following results on the evaluation set:
-- Loss: 1.0930
-- Accuracy: 0.8659
 ## Model description
@@ -52,9 +52,9 @@ The following hyperparameters were used during training:
 | Training Loss | Epoch | Step | Validation Loss | Accuracy |
 |:-------------:|:-----:|:----:|:---------------:|:--------:|
-| 0.4859        | 1.0   | 1696 | 0.9486          | 0.8541   |
-| 0.1289        | 2.0   | 3392 | 1.0216          | 0.8588   |
-| 0.0048        | 3.0   | 5088 | 1.0930          | 0.8659   |
 ### Framework versions

 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 None dataset.
 It achieves the following results on the evaluation set:
+- Loss: 0.7352
+- Accuracy: 0.8753
 ## Model description
 | Training Loss | Epoch | Step | Validation Loss | Accuracy |
 |:-------------:|:-----:|:----:|:---------------:|:--------:|
+| 0.4869        | 1.0   | 1696 | 0.6277          | 0.88     |
+| 0.1106        | 2.0   | 3392 | 0.7112          | 0.88     |
+| 0.0008        | 3.0   | 5088 | 0.7352          | 0.8753   |
 ### Framework versions

adapter_model.safetensors CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e2e6badc9ed2f06cf521ad2822d8765abccda13f36af58296b8a28b65566f877
 size 13681304

 version https://git-lfs.github.com/spec/v1
+oid sha256:9600699bba1fbc9e23afa0c22d7277ec75889cade39784a759675bb38116d632
 size 13681304