---
base_model: meta-llama/Meta-Llama-3-8B-Instruct
library_name: peft
license: llama3
tags:
- trl
- kto
- generated_from_trainer
model-index:
- name: llama3_false_positives_1207_KTO_top_model
  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. -->

# llama3_false_positives_1207_KTO_top_model

This model is a fine-tuned version of [meta-llama/Meta-Llama-3-8B-Instruct](https://huggingface.co/meta-llama/Meta-Llama-3-8B-Instruct) on the None dataset.
It achieves the following results on the evaluation set:
- Loss: 0.6147
- Eval/rewards/chosen: 2.1965
- Eval/logps/chosen: -176.1719
- Eval/rewards/rejected: 2.1473
- Eval/logps/rejected: -189.5401
- Eval/rewards/margins: 0.0492
- Eval/kl: 21.0715

## 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: 0.0001
- train_batch_size: 1
- eval_batch_size: 2
- seed: 42
- gradient_accumulation_steps: 8
- total_train_batch_size: 8
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: cosine
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 2.0

### Training results

| Training Loss | Epoch | Step | Validation Loss |         |
|:-------------:|:-----:|:----:|:---------------:|:-------:|
| 0.4583        | 0.96  | 12   | 0.6057          | 15.7841 |
| 0.4333        | 1.92  | 24   | 0.6147          | 21.0715 |


### Framework versions

- PEFT 0.11.1
- Transformers 4.44.0
- Pytorch 2.2.0
- Datasets 2.20.0
- Tokenizers 0.19.1