---
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_0609_KTO_hp_screening_seeds
  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_0609_KTO_hp_screening_seeds

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: 0.6455
- Eval/rewards/chosen: 4.7894
- Eval/logps/chosen: -155.6419
- Eval/rewards/rejected: 5.2271
- Eval/logps/rejected: -162.9411
- Eval/rewards/margins: -0.4377
- Eval/kl: 43.6119

## 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: 5678
- 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: 6.0

### Training results

| Training Loss | Epoch | Step | Validation Loss |         |
|:-------------:|:-----:|:----:|:---------------:|:-------:|
| 0.5679        | 0.96  | 12   | 0.6448          | 20.8699 |
| 0.5325        | 2.0   | 25   | 0.6455          | 26.6031 |
| 0.3496        | 2.96  | 37   | 0.6709          | 45.2104 |
| 0.3441        | 4.0   | 50   | 0.6451          | 43.6726 |
| 0.301         | 4.96  | 62   | 0.6455          | 43.6419 |
| 0.2008        | 5.76  | 72   | 0.6455          | 43.6119 |


### Framework versions

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