---
library_name: transformers
base_model: W-61/llama-3-8b-base-sft-ultrachat-8xh200
tags:
- alignment-handbook
- slic-hf
- generated_from_trainer
datasets:
- HuggingFaceH4/ultrafeedback_binarized
model-index:
- name: llama-3-8b-base-slic-hf-ultrafeedback-4xh200-batch-128-20260428-054623
  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. -->

# llama-3-8b-base-slic-hf-ultrafeedback-4xh200-batch-128-20260428-054623

This model is a fine-tuned version of [W-61/llama-3-8b-base-sft-ultrachat-8xh200](https://huggingface.co/W-61/llama-3-8b-base-sft-ultrachat-8xh200) on the HuggingFaceH4/ultrafeedback_binarized dataset.
It achieves the following results on the evaluation set:
- Loss: 341.8599
- Rewards/chosen: -260.7975
- Rewards/rejected: -247.1082
- Rewards/accuracies: 0.4935
- Rewards/margins: -13.6894
- Logps/chosen: -260.7975
- Logps/rejected: -247.1082
- Slic/rank Loss: 81.0624
- Slic/ce Loss: 260.7975
- Logits/chosen: -0.6037
- Logits/rejected: -0.6097

## 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: 4
- seed: 42
- distributed_type: multi-GPU
- num_devices: 4
- gradient_accumulation_steps: 8
- total_train_batch_size: 128
- total_eval_batch_size: 16
- 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 | Rewards/chosen | Rewards/rejected | Rewards/accuracies | Rewards/margins | Logps/chosen | Logps/rejected | Slic/rank Loss | Slic/ce Loss | Logits/chosen | Logits/rejected |
|:-------------:|:------:|:----:|:---------------:|:--------------:|:----------------:|:------------------:|:---------------:|:------------:|:--------------:|:--------------:|:------------:|:-------------:|:---------------:|
| 2735.9918     | 0.4188 | 200  | 345.5438        | -262.1006      | -246.2827        | 0.4885             | -15.8179        | -262.1006    | -246.2827      | 83.4432        | 262.1006     | -0.6110       | -0.6187         |
| 2791.6219     | 0.8377 | 400  | 341.8599        | -260.7975      | -247.1082        | 0.4935             | -13.6894        | -260.7975    | -247.1082      | 81.0624        | 260.7975     | -0.6037       | -0.6097         |


### Framework versions

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