dada22231
/

c652616d-b61a-42ad-99f7-0902847573e6

Generated from Trainer

Model card Files Files and versions Community

dada22231 commited on 18 days ago

Commit

25dcf35

•

1 Parent(s): c2ea96e

End of training

Files changed (2) hide show

README.md +3 -3
adapter_model.bin +1 -1

README.md CHANGED Viewed

@@ -114,7 +114,7 @@ xformers_attention: null
 This model is a fine-tuned version of [NousResearch/CodeLlama-7b-hf-flash](https://huggingface.co/NousResearch/CodeLlama-7b-hf-flash) on the None dataset.
 It achieves the following results on the evaluation set:
-- Loss: 2.6576
 ## Model description
@@ -152,8 +152,8 @@ The following hyperparameters were used during training:
 | Training Loss | Epoch  | Step | Validation Loss |
 |:-------------:|:------:|:----:|:---------------:|
 | 99.4744       | 0.0003 | 1    | 3.5344          |
-| 106.9513      | 0.0067 | 25   | 2.6999          |
-| 99.1348       | 0.0133 | 50   | 2.6576          |
 ### Framework versions

 This model is a fine-tuned version of [NousResearch/CodeLlama-7b-hf-flash](https://huggingface.co/NousResearch/CodeLlama-7b-hf-flash) on the None dataset.
 It achieves the following results on the evaluation set:
+- Loss: 2.6595
 ## Model description
 | Training Loss | Epoch  | Step | Validation Loss |
 |:-------------:|:------:|:----:|:---------------:|
 | 99.4744       | 0.0003 | 1    | 3.5344          |
+| 105.756       | 0.0067 | 25   | 2.6978          |
+| 99.3798       | 0.0133 | 50   | 2.6595          |
 ### Framework versions

adapter_model.bin CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b542fa5496d71b34da614515d93edc65412ae3b94a1e952160fd4ca32598b740
 size 319977674

 version https://git-lfs.github.com/spec/v1
+oid sha256:29308aae0cfee2cf759c6eefca74083ffdcceea7ce3517f26c24edf68889af64
 size 319977674