---
library_name: transformers
license: apache-2.0
base_model: allenai/led-large-16384
tags:
- generated_from_trainer
metrics:
- rouge
model-index:
- name: led-large-16384-finetune-paperLedWeSAttG0.1
  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. -->

# led-large-16384-finetune-paperLedWeSAttG0.1

This model is a fine-tuned version of [allenai/led-large-16384](https://huggingface.co/allenai/led-large-16384) on the None dataset.
It achieves the following results on the evaluation set:
- Loss: 2.9013
- Rouge1: 35.4319
- Rouge2: 9.1043
- Rougel: 16.1054
- Rougelsum: 33.675
- Gen Len: 1.0

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

### Training results

| Training Loss | Epoch  | Step | Validation Loss | Rouge1  | Rouge2 | Rougel  | Rougelsum | Gen Len |
|:-------------:|:------:|:----:|:---------------:|:-------:|:------:|:-------:|:---------:|:-------:|
| 2.9556        | 0.9993 | 1128 | 3.0039          | 35.2679 | 8.0717 | 17.8571 | 33.4821   | 1.0     |
| 2.7602        | 1.9993 | 2256 | 2.9080          | 35.0731 | 6.7086 | 17.5365 | 32.9854   | 1.0     |
| 2.63          | 2.9993 | 3384 | 2.9013          | 35.4319 | 9.1043 | 16.1054 | 33.675    | 1.0     |


### Framework versions

- Transformers 4.48.3
- Pytorch 2.6.0+cu124
- Datasets 2.14.4
- Tokenizers 0.21.1