---
language:
- en
license: apache-2.0
library_name: transformers
pipeline_tag: text-generation
tags:
- nlp
- agent
---

# ALFWorld-MPO

This model is a fine-tuned version of Llama-3.1-8B-Instruct on the [alfworld-metaplan-preference-pairs](https://huggingface.co/datasets/xwm/Meta_Plan_Optimization/blob/main/alfworld_metaplan_preference_pairs.json) dataset as described in [MPO: Boosting LLM Agents with Meta Plan Optimization](https://hf.co/papers/2503.02682).
It achieves the following results on the evaluation set:
- Loss: 0.8390
- Rewards/chosen: -0.5836
- Rewards/rejected: -1.2646
- Rewards/accuracies: 0.6318
- Rewards/margins: 0.6810
- Logps/chosen: -12.9009
- Logps/rejected: -19.8890
- Logits/chosen: -0.3349
- Logits/rejected: -0.3405

## 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: 1e-05
- train_batch_size: 2
- eval_batch_size: 1
- seed: 42
- distributed_type: multi-GPU
- num_devices: 4
- gradient_accumulation_steps: 4
- total_train_batch_size: 32
- total_eval_batch_size: 4
- optimizer: Use 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: 0.03
- num_epochs: 3.0

### Training results



### Framework versions

- Transformers 4.46.1
- Pytorch 2.5.1+cu124
- Datasets 3.1.0
- Tokenizers 0.20.3

## Code

[https://github.com/WeiminXiong/MPO](https://github.com/WeiminXiong/MPO)