hannahbillo
/

dpo-llama3-8b-sample-rules

Generated from Trainer

Model card Files Files and versions Metrics Training metrics Community

hannahbillo commited on Aug 19, 2024

Commit

56238db

·

verified ·

1 Parent(s): b0f0513

End of training

Files changed (1) hide show

README.md +10 -10

README.md CHANGED Viewed

@@ -18,15 +18,15 @@ should probably proofread and complete it, then remove this comment. -->
 This model is a fine-tuned version of [meta-llama/Meta-Llama-3.1-8B](https://huggingface.co/meta-llama/Meta-Llama-3.1-8B) on the None dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.1877
-- Rewards/chosen: 0.0468
-- Rewards/rejected: -1.6718
 - Rewards/accuracies: 1.0
-- Rewards/margins: 1.7186
-- Logps/rejected: -533.8027
-- Logps/chosen: -205.1740
-- Logits/rejected: -1.4124
-- Logits/chosen: -1.2468
 ## Model description
@@ -61,8 +61,8 @@ The following hyperparameters were used during training:
 | Training Loss | Epoch  | Step | Validation Loss | Rewards/chosen | Rewards/rejected | Rewards/accuracies | Rewards/margins | Logps/rejected | Logps/chosen | Logits/rejected | Logits/chosen |
 |:-------------:|:------:|:----:|:---------------:|:--------------:|:----------------:|:------------------:|:---------------:|:--------------:|:------------:|:---------------:|:-------------:|
-| 0.4235        | 0.4444 | 50   | 0.3831          | 0.1873         | -0.5971          | 1.0                | 0.7844          | -426.3294      | -191.1236    | -1.4109         | -1.2728       |
-| 0.1946        | 0.8889 | 100  | 0.1877          | 0.0468         | -1.6718          | 1.0                | 1.7186          | -533.8027      | -205.1740    | -1.4124         | -1.2468       |
 ### Framework versions

 This model is a fine-tuned version of [meta-llama/Meta-Llama-3.1-8B](https://huggingface.co/meta-llama/Meta-Llama-3.1-8B) on the None dataset.
 It achieves the following results on the evaluation set:
+- Loss: 0.1915
+- Rewards/chosen: 0.1004
+- Rewards/rejected: -1.6031
 - Rewards/accuracies: 1.0
+- Rewards/margins: 1.7035
+- Logps/rejected: -517.5475
+- Logps/chosen: -200.9981
+- Logits/rejected: -1.3936
+- Logits/chosen: -1.2455
 ## Model description
 | Training Loss | Epoch  | Step | Validation Loss | Rewards/chosen | Rewards/rejected | Rewards/accuracies | Rewards/margins | Logps/rejected | Logps/chosen | Logits/rejected | Logits/chosen |
 |:-------------:|:------:|:----:|:---------------:|:--------------:|:----------------:|:------------------:|:---------------:|:--------------:|:------------:|:---------------:|:-------------:|
+| 0.4345        | 0.4444 | 50   | 0.3859          | 0.2018         | -0.5860          | 1.0                | 0.7877          | -415.8305      | -190.8644    | -1.3991         | -1.2723       |
+| 0.2288        | 0.8889 | 100  | 0.1915          | 0.1004         | -1.6031          | 1.0                | 1.7035          | -517.5475      | -200.9981    | -1.3936         | -1.2455       |
 ### Framework versions