---
library_name: transformers
base_model: jackf857/qwen3-8b-base-sft-ultrachat-4xh200-batch-128
tags:
- alignment-handbook
- new-dpo
- generated_from_trainer
datasets:
- HuggingFaceH4/ultrafeedback_binarized
model-index:
- name: qwen3-8b-base-new-dpo-ultrafeedback-4xh200-batch-128-q_t-0.4-s_star-0.35-20260430-140517
  results: []
---

<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->

# qwen3-8b-base-new-dpo-ultrafeedback-4xh200-batch-128-q_t-0.4-s_star-0.35-20260430-140517

This model is a fine-tuned version of [jackf857/qwen3-8b-base-sft-ultrachat-4xh200-batch-128](https://huggingface.co/jackf857/qwen3-8b-base-sft-ultrachat-4xh200-batch-128) on the HuggingFaceH4/ultrafeedback_binarized dataset.
It achieves the following results on the evaluation set:
- Loss: 0.6076
- Fcm Dpo/beta: 0.0040
- Margin Dpo/margin Mean: 54.4214
- Margin Dpo/margin Std: 86.7093
- Logps/chosen: -331.5330
- Logps/rejected: -370.1833
- Logps/ref Chosen: -280.4167
- Logps/ref Rejected: -264.6455
- Kl/chosen Kl Mean: -51.1163
- Kl/rejected Kl Mean: -105.5378
- Kl/mean: -78.3270
- Kl/std: 74.4785
- Logits/chosen: 1.4424
- Logits/rejected: 1.5060

## Model description

More information needed

## Intended uses & limitations

More information needed

## Training and evaluation data

More information needed

## Training procedure

### Training hyperparameters

The following hyperparameters were used during training:
- learning_rate: 5e-07
- train_batch_size: 4
- eval_batch_size: 2
- seed: 42
- distributed_type: multi-GPU
- num_devices: 4
- gradient_accumulation_steps: 8
- total_train_batch_size: 128
- total_eval_batch_size: 8
- optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: cosine
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 1

### Training results

| Training Loss | Epoch  | Step | Validation Loss | Fcm Dpo/beta | Margin Dpo/margin Mean | Margin Dpo/margin Std | Logps/chosen | Logps/rejected | Logps/ref Chosen | Logps/ref Rejected | Kl/chosen Kl Mean | Kl/rejected Kl Mean | Kl/mean  | Kl/std  | Logits/chosen | Logits/rejected |
|:-------------:|:------:|:----:|:---------------:|:------------:|:----------------------:|:---------------------:|:------------:|:--------------:|:----------------:|:------------------:|:-----------------:|:-------------------:|:--------:|:-------:|:-------------:|:---------------:|
| 4.9448        | 0.4188 | 200  | 0.6027          | 0.0090       | 26.4387                | 42.3830               | -286.1130    | -296.7805      | -280.4167        | -264.6455          | -5.6962           | -32.1350            | -18.9156 | 36.5734 | 1.6826        | 1.7371          |
| 4.7852        | 0.8377 | 400  | 0.6076          | 0.0040       | 54.4214                | 86.7093               | -331.5330    | -370.1833      | -280.4167        | -264.6455          | -51.1163          | -105.5378           | -78.3270 | 74.4785 | 1.4424        | 1.5060          |


### Framework versions

- Transformers 4.51.0
- Pytorch 2.3.1+cu121
- Datasets 2.21.0
- Tokenizers 0.21.4