---
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: 0.7265
- Eval/rewards/chosen: 3.6123
- Eval/logps/chosen: -167.4125
- Eval/rewards/rejected: 3.7149
- Eval/logps/rejected: -178.0628
- Eval/rewards/margins: -0.1026
- Eval/kl: 33.2160

## 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: 4.0

### Training results

| Training Loss | Epoch | Step | Validation Loss |         |
|:-------------:|:-----:|:----:|:---------------:|:-------:|
| 0.5619        | 0.96  | 12   | 0.6911          | 17.2746 |
| 0.5748        | 2.0   | 25   | 0.7189          | 25.3931 |
| 0.3537        | 2.96  | 37   | 0.7288          | 32.8920 |
| 0.0845        | 3.84  | 48   | 0.7265          | 33.2160 |


### Framework versions

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