Model save
Browse files
README.md
CHANGED
|
@@ -14,21 +14,21 @@ model-index:
|
|
| 14 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 15 |
should probably proofread and complete it, then remove this comment. -->
|
| 16 |
|
| 17 |
-
[<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="200" height="32"/>](https://wandb.ai/algo-llm/huggingface/runs/
|
| 18 |
# orpo-phi3
|
| 19 |
|
| 20 |
This model is a fine-tuned version of [microsoft/Phi-3-mini-4k-instruct](https://huggingface.co/microsoft/Phi-3-mini-4k-instruct) on the None dataset.
|
| 21 |
It achieves the following results on the evaluation set:
|
| 22 |
-
- Loss:
|
| 23 |
-
- Rewards/chosen: -0.
|
| 24 |
-
- Rewards/rejected: -0.
|
| 25 |
- Rewards/accuracies: 0.0
|
| 26 |
- Rewards/margins: 0.0
|
| 27 |
-
- Logps/rejected: -
|
| 28 |
-
- Logps/chosen: -
|
| 29 |
-
- Logits/rejected:
|
| 30 |
-
- Logits/chosen:
|
| 31 |
-
- Nll Loss:
|
| 32 |
- Log Odds Ratio: -0.6931
|
| 33 |
- Log Odds Chosen: 0.0
|
| 34 |
|
|
@@ -64,7 +64,7 @@ The following hyperparameters were used during training:
|
|
| 64 |
|
| 65 |
| Training Loss | Epoch | Step | Validation Loss | Rewards/chosen | Rewards/rejected | Rewards/accuracies | Rewards/margins | Logps/rejected | Logps/chosen | Logits/rejected | Logits/chosen | Nll Loss | Log Odds Ratio | Log Odds Chosen |
|
| 66 |
|:-------------:|:-----:|:----:|:---------------:|:--------------:|:----------------:|:------------------:|:---------------:|:--------------:|:------------:|:---------------:|:-------------:|:--------:|:--------------:|:---------------:|
|
| 67 |
-
|
|
| 68 |
|
| 69 |
|
| 70 |
### Framework versions
|
|
|
|
| 14 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 15 |
should probably proofread and complete it, then remove this comment. -->
|
| 16 |
|
| 17 |
+
[<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="200" height="32"/>](https://wandb.ai/algo-llm/huggingface/runs/g44k7xr4)
|
| 18 |
# orpo-phi3
|
| 19 |
|
| 20 |
This model is a fine-tuned version of [microsoft/Phi-3-mini-4k-instruct](https://huggingface.co/microsoft/Phi-3-mini-4k-instruct) on the None dataset.
|
| 21 |
It achieves the following results on the evaluation set:
|
| 22 |
+
- Loss: 5.4687
|
| 23 |
+
- Rewards/chosen: -0.5200
|
| 24 |
+
- Rewards/rejected: -0.5200
|
| 25 |
- Rewards/accuracies: 0.0
|
| 26 |
- Rewards/margins: 0.0
|
| 27 |
+
- Logps/rejected: -5.2002
|
| 28 |
+
- Logps/chosen: -5.2002
|
| 29 |
+
- Logits/rejected: 23.0851
|
| 30 |
+
- Logits/chosen: 23.0851
|
| 31 |
+
- Nll Loss: 5.3994
|
| 32 |
- Log Odds Ratio: -0.6931
|
| 33 |
- Log Odds Chosen: 0.0
|
| 34 |
|
|
|
|
| 64 |
|
| 65 |
| Training Loss | Epoch | Step | Validation Loss | Rewards/chosen | Rewards/rejected | Rewards/accuracies | Rewards/margins | Logps/rejected | Logps/chosen | Logits/rejected | Logits/chosen | Nll Loss | Log Odds Ratio | Log Odds Chosen |
|
| 66 |
|:-------------:|:-----:|:----:|:---------------:|:--------------:|:----------------:|:------------------:|:---------------:|:--------------:|:------------:|:---------------:|:-------------:|:--------:|:--------------:|:---------------:|
|
| 67 |
+
| 2.9122 | 1.0 | 1 | 5.4687 | -0.5200 | -0.5200 | 0.0 | 0.0 | -5.2002 | -5.2002 | 23.0851 | 23.0851 | 5.3994 | -0.6931 | 0.0 |
|
| 68 |
|
| 69 |
|
| 70 |
### Framework versions
|