---
library_name: transformers
tags:
- generated_from_trainer
metrics:
- rouge
model-index:
- name: gpt22gpt2-gpt2-large-cnn-dailymail-seed42_std_percentile
  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. -->

# gpt22gpt2-gpt2-large-cnn-dailymail-seed42_std_percentile

This model is a fine-tuned version of [](https://huggingface.co/) on an unknown dataset.
It achieves the following results on the evaluation set:
- Loss: 2.0071
- Rouge1: 0.3061
- Rouge2: 0.0939
- Rougel: 0.1780
- Rougelsum: 0.2848

## 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: 5e-05
- train_batch_size: 8
- eval_batch_size: 16
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 32
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 1000
- num_epochs: 3.0

### Training results

| Training Loss | Epoch  | Step  | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum |
|:-------------:|:------:|:-----:|:---------------:|:------:|:------:|:------:|:---------:|
| 2.7029        | 0.2229 | 2000  | 2.5427          | 0.2437 | 0.0532 | 0.1469 | 0.2285    |
| 2.5218        | 0.4458 | 4000  | 2.3777          | 0.2636 | 0.0661 | 0.1578 | 0.2455    |
| 2.4141        | 0.6687 | 6000  | 2.2899          | 0.2683 | 0.0695 | 0.1587 | 0.2506    |
| 2.3452        | 0.8916 | 8000  | 2.2199          | 0.2888 | 0.0814 | 0.1714 | 0.2694    |
| 2.0037        | 1.1145 | 10000 | 2.1817          | 0.2984 | 0.0851 | 0.1729 | 0.2772    |
| 1.9905        | 1.3374 | 12000 | 2.1423          | 0.2907 | 0.0823 | 0.1713 | 0.2719    |
| 1.9711        | 1.5603 | 14000 | 2.0983          | 0.3055 | 0.0915 | 0.1786 | 0.2850    |
| 1.9476        | 1.7832 | 16000 | 2.0547          | 0.3186 | 0.0998 | 0.1858 | 0.2972    |
| 1.8964        | 2.0061 | 18000 | 2.0510          | 0.3032 | 0.0919 | 0.1778 | 0.2826    |
| 1.6389        | 2.2290 | 20000 | 2.0485          | 0.3185 | 0.0997 | 0.1857 | 0.2962    |
| 1.6251        | 2.4519 | 22000 | 2.0328          | 0.2992 | 0.0889 | 0.1743 | 0.2782    |
| 1.6119        | 2.6748 | 24000 | 2.0138          | 0.3045 | 0.0939 | 0.1778 | 0.2832    |
| 1.6093        | 2.8977 | 26000 | 2.0071          | 0.3061 | 0.0939 | 0.1780 | 0.2848    |


### Framework versions

- Transformers 4.44.2
- Pytorch 2.4.0
- Datasets 2.21.0
- Tokenizers 0.19.1