---
base_model: meta-llama/Llama-2-7b-hf
tags:
- generated_from_trainer
model-index:
- name: llama2-7bn-xsum-cnn-adapter
  results: []
datasets:
- cnn_dailymail
- EdinburghNLP/xsum
language:
- en
library_name: adapter-transformers
---

<!-- 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. -->

# llama2-7bn-xsum-cnn-adapter

This model is a fine-tuned version of [meta-llama/Llama-2-7b-hf](https://huggingface.co/meta-llama/Llama-2-7b-hf) on XSum and CNN/DM. LoRA adapter model based on LLama2 7bn. You can view all the implementation details on the [GitHub project](https://github.com/ernlavr/llamarizer)

## Weights and Biases Documentation: Training and Eval

See [Weights and Biases](https://wandb.ai/ernlavr/adv_nlp2023/runs/t8icitt1) for training details.

## Training procedure
- Input source document wrapped in a prompt: "Summarize the following article:\<INPUT\>; Summary: \<OUTPUT\>"
- Trained using cross-entropy on CausalLM task
- Data splits consist of sequences up to 512 tokens:
  - Training n-datapoints: 115'354 XSum; 27494 CNN
  - Val n-datapoints: 3928 XSum; 1211 CNN

### Training hyperparameters

The following hyperparameters were used during training:
- learning_rate: 0.001
- train_batch_size: 16
- eval_batch_size: 16
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_ratio: 0.1
- lr_scheduler_warmup_steps: 558.0
- num_epochs: 2
- mixed_precision_training: Native AMP

### Training results

Achieves loss=2.021 on valdiation split, see W&B run (link above) for more details.



### Framework versions

- Transformers 4.35.0
- Pytorch 2.0.1
- Datasets 2.14.6
- Tokenizers 0.14.1