---
library_name: peft
base_model: saresri/pruned_opt
tags:
- generated_from_trainer
model-index:
- name: opt125m-lora-pruned-wanda-4-8
  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. -->

# opt125m-lora-pruned-wanda-4-8

This model is a fine-tuned version of [saresri/pruned_opt](https://huggingface.co/saresri/pruned_opt) on an unknown dataset.

## 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: 0.0002
- train_batch_size: 4
- eval_batch_size: 8
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 16
- optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 1
- num_epochs: 3
- mixed_precision_training: Native AMP

### Training results

Evaluation Results (Validation): {'rouge1': 0.2974, 'rouge2': 0.08, 'rougeL': 0.19, 'rougeLsum': 0.2186}

Evaluation Results (Test): {'rouge1': 0.3165, 'rouge2': 0.1938, 'rougeL': 0.2721, 'rougeLsum': 0.2794}



### Framework versions

- PEFT 0.14.0
- Transformers 4.47.0
- Pytorch 2.5.1+cu121
- Datasets 3.1.0
- Tokenizers 0.21.0