---
base_model: google/pegasus-large
tags:
- generated_from_trainer
datasets:
- arrow
model-index:
- name: RoBERTa_Pegasus_dependent_V1
  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. -->

# RoBERTa_Pegasus_dependent_V1

This model is a fine-tuned version of [google/pegasus-large](https://huggingface.co/google/pegasus-large) on the arrow dataset.
It achieves the following results on the evaluation set:
- Loss: 2.1922

## 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: 2
- eval_batch_size: 1
- seed: 42
- distributed_type: multi-GPU
- num_devices: 4
- gradient_accumulation_steps: 2
- total_train_batch_size: 16
- total_eval_batch_size: 4
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 40

### Training results

| Training Loss | Epoch   | Step | Validation Loss |
|:-------------:|:-------:|:----:|:---------------:|
| 5.0795        | 0.9927  | 68   | 3.9061          |
| 3.6946        | 2.0     | 137  | 3.2272          |
| 3.1058        | 2.9927  | 205  | 2.6658          |
| 2.6695        | 4.0     | 274  | 2.4699          |
| 2.511         | 4.9927  | 342  | 2.3796          |
| 2.3613        | 6.0     | 411  | 2.3305          |
| 2.3187        | 6.9927  | 479  | 2.3024          |
| 2.2335        | 8.0     | 548  | 2.2800          |
| 2.2252        | 8.9927  | 616  | 2.2639          |
| 2.1548        | 10.0    | 685  | 2.2515          |
| 2.1536        | 10.9927 | 753  | 2.2412          |
| 2.0982        | 12.0    | 822  | 2.2338          |
| 2.0988        | 12.9927 | 890  | 2.2248          |
| 2.0441        | 14.0    | 959  | 2.2204          |
| 2.0552        | 14.9927 | 1027 | 2.2164          |
| 2.0084        | 16.0    | 1096 | 2.2111          |
| 2.0178        | 16.9927 | 1164 | 2.2076          |
| 1.9719        | 18.0    | 1233 | 2.2051          |
| 1.9901        | 18.9927 | 1301 | 2.2043          |
| 1.9464        | 20.0    | 1370 | 2.2009          |
| 1.9631        | 20.9927 | 1438 | 2.2000          |
| 1.9233        | 22.0    | 1507 | 2.1981          |
| 1.9394        | 22.9927 | 1575 | 2.1961          |
| 1.9012        | 24.0    | 1644 | 2.1947          |
| 1.9213        | 24.9927 | 1712 | 2.1943          |
| 1.8843        | 26.0    | 1781 | 2.1942          |
| 1.9025        | 26.9927 | 1849 | 2.1942          |
| 1.8715        | 28.0    | 1918 | 2.1950          |
| 1.8906        | 28.9927 | 1986 | 2.1936          |
| 1.8559        | 30.0    | 2055 | 2.1939          |
| 1.8774        | 30.9927 | 2123 | 2.1934          |
| 1.8468        | 32.0    | 2192 | 2.1913          |
| 1.8685        | 32.9927 | 2260 | 2.1916          |
| 1.834         | 34.0    | 2329 | 2.1924          |
| 1.8582        | 34.9927 | 2397 | 2.1929          |
| 1.8333        | 36.0    | 2466 | 2.1925          |
| 1.859         | 36.9927 | 2534 | 2.1922          |


### Framework versions

- Transformers 4.40.1
- Pytorch 2.2.1+cu121
- Datasets 2.17.1
- Tokenizers 0.19.1