Hitisha commited on
Commit
4453d2e
·
verified ·
1 Parent(s): 6e939ef

Model save

Browse files
Files changed (1) hide show
  1. README.md +10 -11
README.md CHANGED
@@ -14,22 +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/12ettnkn)
18
- [<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/12ettnkn)
19
  # orpo-phi3
20
 
21
  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.
22
  It achieves the following results on the evaluation set:
23
- - Loss: 4.1677
24
- - Rewards/chosen: -0.4133
25
- - Rewards/rejected: -0.4133
26
  - Rewards/accuracies: 0.0
27
  - Rewards/margins: 0.0
28
- - Logps/rejected: -4.1330
29
- - Logps/chosen: -4.1330
30
- - Logits/rejected: 24.1632
31
- - Logits/chosen: 24.1632
32
- - Nll Loss: 4.0984
33
  - Log Odds Ratio: -0.6931
34
  - Log Odds Chosen: 0.0
35
 
@@ -65,7 +64,7 @@ The following hyperparameters were used during training:
65
 
66
  | 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 |
67
  |:-------------:|:-----:|:----:|:---------------:|:--------------:|:----------------:|:------------------:|:---------------:|:--------------:|:------------:|:---------------:|:-------------:|:--------:|:--------------:|:---------------:|
68
- | 3.1975 | 1.0 | 1 | 4.1677 | -0.4133 | -0.4133 | 0.0 | 0.0 | -4.1330 | -4.1330 | 24.1632 | 24.1632 | 4.0984 | -0.6931 | 0.0 |
69
 
70
 
71
  ### 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/8cgkk8bv)
 
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: 3.9381
23
+ - Rewards/chosen: -0.4248
24
+ - Rewards/rejected: -0.4248
25
  - Rewards/accuracies: 0.0
26
  - Rewards/margins: 0.0
27
+ - Logps/rejected: -4.2478
28
+ - Logps/chosen: -4.2478
29
+ - Logits/rejected: 18.4407
30
+ - Logits/chosen: 18.4407
31
+ - Nll Loss: 3.8688
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
+ | 3.0778 | 1.0 | 1 | 3.9381 | -0.4248 | -0.4248 | 0.0 | 0.0 | -4.2478 | -4.2478 | 18.4407 | 18.4407 | 3.8688 | -0.6931 | 0.0 |
68
 
69
 
70
  ### Framework versions