Sorour
/

cls_headline_llama3_v3

Generated from Trainer

Model card Files Files and versions Metrics Training metrics Community

Sorour commited on 9 days ago

Commit

ec9ffef

•

1 Parent(s): c13ea80

Model save

Files changed (1) hide show

README.md +4 -4

README.md CHANGED Viewed

@@ -20,7 +20,7 @@ should probably proofread and complete it, then remove this comment. -->
 This model is a fine-tuned version of [meta-llama/Meta-Llama-3-8B-Instruct](https://huggingface.co/meta-llama/Meta-Llama-3-8B-Instruct) on the generator dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.7088
 ## Model description
@@ -55,9 +55,9 @@ The following hyperparameters were used during training:
 | Training Loss | Epoch  | Step | Validation Loss |
 |:-------------:|:------:|:----:|:---------------:|
-| 0.782         | 0.4040 | 20   | 0.7524          |
-| 0.739         | 0.8081 | 40   | 0.7112          |
-| 0.6063        | 1.2121 | 60   | 0.7088          |
 ### Framework versions

 This model is a fine-tuned version of [meta-llama/Meta-Llama-3-8B-Instruct](https://huggingface.co/meta-llama/Meta-Llama-3-8B-Instruct) on the generator dataset.
 It achieves the following results on the evaluation set:
+- Loss: 1.4488
 ## Model description
 | Training Loss | Epoch  | Step | Validation Loss |
 |:-------------:|:------:|:----:|:---------------:|
+| 1.4909        | 0.0275 | 20   | 1.5325          |
+| 1.511         | 0.0550 | 40   | 1.4779          |
+| 1.3699        | 0.0824 | 60   | 1.4488          |
 ### Framework versions