---
base_model: TinyLlama/TinyLlama-1.1B-Chat-v1.0
library_name: transformers
license: apache-2.0
tags:
- trl
- dpo
- generated_from_trainer
model-index:
- name: TinyLlama-1.1B-IPO-PKU-SafeRLHF
  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. -->

# TinyLlama-1.1B-IPO-PKU-SafeRLHF

This model is a fine-tuned version of [TinyLlama/TinyLlama-1.1B-Chat-v1.0](https://huggingface.co/TinyLlama/TinyLlama-1.1B-Chat-v1.0) on an unknown dataset.
It achieves the following results on the evaluation set:
- Loss: 18.4083
- Rewards/chosen: -0.3421
- Rewards/rejected: -0.4737
- Rewards/accuracies: 0.7389
- Rewards/margins: 0.1316
- Logps/rejected: -6.7403
- Logps/chosen: -5.4225
- Logits/rejected: -2.2712
- Logits/chosen: -2.4037

## 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-06
- train_batch_size: 4
- eval_batch_size: 4
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 16
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- 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/rejected | Logps/chosen | Logits/rejected | Logits/chosen |
|:-------------:|:------:|:----:|:---------------:|:--------------:|:----------------:|:------------------:|:---------------:|:--------------:|:------------:|:---------------:|:-------------:|
| 24.8672       | 0.0960 | 200  | 24.8184         | -0.0031        | -0.0050          | 0.7069             | 0.0018          | -2.0534        | -2.0334      | -2.7185         | -2.8480       |
| 24.1359       | 0.1920 | 400  | 24.2118         | -0.0132        | -0.0215          | 0.7351             | 0.0083          | -2.2183        | -2.1337      | -2.6542         | -2.7800       |
| 22.6582       | 0.2880 | 600  | 22.9068         | -0.0523        | -0.0760          | 0.7280             | 0.0237          | -2.7638        | -2.5252      | -2.4992         | -2.6281       |
| 21.2405       | 0.3840 | 800  | 19.5980         | -0.2860        | -0.3895          | 0.7207             | 0.1036          | -5.8987        | -4.8616      | -2.3572         | -2.4838       |
| 16.8004       | 0.4800 | 1000 | 18.8829         | -0.3386        | -0.4676          | 0.7299             | 0.1290          | -6.6800        | -5.3883      | -2.2910         | -2.4227       |
| 20.9951       | 0.5760 | 1200 | 18.5470         | -0.3274        | -0.4552          | 0.7343             | 0.1279          | -6.5555        | -5.2756      | -2.2822         | -2.4138       |
| 19.3603       | 0.6719 | 1400 | 18.4526         | -0.3367        | -0.4669          | 0.7367             | 0.1303          | -6.6729        | -5.3688      | -2.2770         | -2.4091       |
| 16.8747       | 0.7679 | 1600 | 18.4182         | -0.3410        | -0.4724          | 0.7383             | 0.1314          | -6.7270        | -5.4120      | -2.2717         | -2.4042       |
| 20.3795       | 0.8639 | 1800 | 18.4132         | -0.3418        | -0.4733          | 0.7370             | 0.1315          | -6.7369        | -5.4201      | -2.2711         | -2.4037       |
| 18.8851       | 0.9599 | 2000 | 18.4097         | -0.3421        | -0.4737          | 0.7381             | 0.1316          | -6.7404        | -5.4228      | -2.2713         | -2.4037       |


### Framework versions

- Transformers 4.44.2
- Pytorch 2.11.0+cu130
- Datasets 2.21.0
- Tokenizers 0.19.1