---
library_name: peft
license: apache-2.0
base_model: muchad/idt5-base
tags:
- generated_from_trainer
metrics:
- rouge
- bleu
model-index:
- name: idt5-base-ae_adapter_cross
  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. -->

# idt5-base-ae_adapter_cross

This model is a fine-tuned version of [muchad/idt5-base](https://huggingface.co/muchad/idt5-base) on the None dataset.
It achieves the following results on the evaluation set:
- Loss: 1.9144
- Rouge1: 0.1917
- Rouge2: 0.0598
- Rougel: 0.1773
- Rougelsum: 0.1794
- Bleu: 0.0804

## 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: 0.0001
- train_batch_size: 8
- eval_batch_size: 8
- seed: 42
- 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
- num_epochs: 5

### Training results

| Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum | Bleu   |
|:-------------:|:-----:|:----:|:---------------:|:------:|:------:|:------:|:---------:|:------:|
| 6.3356        | 1.0   | 1695 | 2.9181          | 0.0644 | 0.0164 | 0.0616 | 0.0623    | 0.0129 |
| 3.3896        | 2.0   | 3390 | 2.2209          | 0.0596 | 0.0086 | 0.0582 | 0.0582    | 0.0132 |
| 2.8466        | 3.0   | 5085 | 2.0090          | 0.1738 | 0.0470 | 0.1625 | 0.1641    | 0.0657 |
| 2.7054        | 4.0   | 6780 | 1.9374          | 0.1873 | 0.0576 | 0.1740 | 0.1758    | 0.0759 |
| 2.6373        | 5.0   | 8475 | 1.9144          | 0.1917 | 0.0598 | 0.1773 | 0.1794    | 0.0804 |


### Framework versions

- PEFT 0.13.2
- Transformers 4.46.0
- Pytorch 2.4.0a0+f70bd71a48.nv24.06
- Datasets 3.0.2
- Tokenizers 0.20.1