---
library_name: peft
license: apache-2.0
base_model: google/long-t5-tglobal-base
tags:
- generated_from_trainer
metrics:
- rouge
- bleu
- precision
- recall
- f1
model-index:
- name: Lora_long_T5_sum_outcome
  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. -->

# Lora_long_T5_sum_outcome

This model is a fine-tuned version of [google/long-t5-tglobal-base](https://huggingface.co/google/long-t5-tglobal-base) on an unknown dataset.
It achieves the following results on the evaluation set:
- Loss: 1.1051
- Rouge1: 0.3789
- Rouge2: 0.1817
- Rougel: 0.3238
- Rougelsum: 0.3256
- Gen Len: 27.8
- Bleu: 0.0865
- Precisions: 0.1534
- Brevity Penalty: 0.8221
- Length Ratio: 0.8362
- Translation Length: 980.0
- Reference Length: 1172.0
- Precision: 0.8937
- Recall: 0.8862
- F1: 0.8898
- Hashcode: roberta-large_L17_no-idf_version=0.3.12(hug_trans=4.53.1)

## 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: 0.002
- train_batch_size: 1
- eval_batch_size: 1
- seed: 42
- gradient_accumulation_steps: 16
- 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: 10

### Training results

| Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum | Gen Len | Bleu   | Precisions | Brevity Penalty | Length Ratio | Translation Length | Reference Length | Precision | Recall | F1     | Hashcode                                                  |
|:-------------:|:-----:|:----:|:---------------:|:------:|:------:|:------:|:---------:|:-------:|:------:|:----------:|:---------------:|:------------:|:------------------:|:----------------:|:---------:|:------:|:------:|:---------------------------------------------------------:|
| 22.0917       | 1.0   | 7    | 5.3855          | 0.0468 | 0.0056 | 0.0416 | 0.0415    | 31.0    | 0.0    | 0.016      | 0.5803          | 0.6476       | 759.0              | 1172.0           | 0.7506    | 0.8197 | 0.7828 | roberta-large_L17_no-idf_version=0.3.12(hug_trans=4.53.1) |
| 6.5733        | 2.0   | 14   | 4.6730          | 0.1909 | 0.0287 | 0.1473 | 0.1475    | 30.88   | 0.0179 | 0.0488     | 0.8856          | 0.8916       | 1045.0             | 1172.0           | 0.8418    | 0.8462 | 0.844  | roberta-large_L17_no-idf_version=0.3.12(hug_trans=4.53.1) |
| 4.2163        | 3.0   | 21   | 3.6942          | 0.2295 | 0.0424 | 0.1634 | 0.1642    | 29.08   | 0.0264 | 0.0695     | 0.8469          | 0.8575       | 1005.0             | 1172.0           | 0.8546    | 0.8582 | 0.8563 | roberta-large_L17_no-idf_version=0.3.12(hug_trans=4.53.1) |
| 3.5683        | 4.0   | 28   | 3.1688          | 0.2805 | 0.0846 | 0.2121 | 0.2134    | 28.98   | 0.0383 | 0.0906     | 0.8469          | 0.8575       | 1005.0             | 1172.0           | 0.8681    | 0.8666 | 0.8672 | roberta-large_L17_no-idf_version=0.3.12(hug_trans=4.53.1) |
| 3.2672        | 5.0   | 35   | 2.8633          | 0.325  | 0.1351 | 0.2652 | 0.2669    | 28.4    | 0.0652 | 0.1242     | 0.8341          | 0.8464       | 992.0              | 1172.0           | 0.8823    | 0.8776 | 0.8799 | roberta-large_L17_no-idf_version=0.3.12(hug_trans=4.53.1) |
| 3.0146        | 6.0   | 42   | 2.4207          | 0.3326 | 0.1431 | 0.2839 | 0.2856    | 28.08   | 0.0788 | 0.1344     | 0.839           | 0.8507       | 997.0              | 1172.0           | 0.8839    | 0.879  | 0.8813 | roberta-large_L17_no-idf_version=0.3.12(hug_trans=4.53.1) |
| 2.4539        | 7.0   | 49   | 1.7916          | 0.3471 | 0.1565 | 0.2932 | 0.2931    | 28.26   | 0.0882 | 0.1431     | 0.839           | 0.8507       | 997.0              | 1172.0           | 0.8863    | 0.882  | 0.884  | roberta-large_L17_no-idf_version=0.3.12(hug_trans=4.53.1) |
| 1.965         | 8.0   | 56   | 1.3215          | 0.3607 | 0.1749 | 0.3113 | 0.3125    | 28.18   | 0.0925 | 0.1498     | 0.8331          | 0.8456       | 991.0              | 1172.0           | 0.889     | 0.8839 | 0.8863 | roberta-large_L17_no-idf_version=0.3.12(hug_trans=4.53.1) |
| 1.7658        | 9.0   | 63   | 1.1630          | 0.3772 | 0.1782 | 0.3211 | 0.3228    | 27.8    | 0.0838 | 0.1518     | 0.813           | 0.8285       | 971.0              | 1172.0           | 0.8937    | 0.8859 | 0.8897 | roberta-large_L17_no-idf_version=0.3.12(hug_trans=4.53.1) |
| 1.5019        | 10.0  | 70   | 1.1051          | 0.3789 | 0.1817 | 0.3238 | 0.3256    | 27.8    | 0.0865 | 0.1534     | 0.8221          | 0.8362       | 980.0              | 1172.0           | 0.8937    | 0.8862 | 0.8898 | roberta-large_L17_no-idf_version=0.3.12(hug_trans=4.53.1) |


### Framework versions

- PEFT 0.15.2
- Transformers 4.53.1
- Pytorch 2.7.0+cu126
- Datasets 3.6.0
- Tokenizers 0.21.1