---
tags:
- generated_from_trainer
model-index:
- name: fine-tune-Pegasus-large
  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. -->

# fine-tune-Pegasus-large

This model is a fine-tuned version of [google/pegasus-large](https://huggingface.co/google/pegasus-large) on an unknown dataset.
It achieves the following results on the evaluation set:
- Loss: 5.3025

## 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: 6.35e-05
- train_batch_size: 4
- eval_batch_size: 4
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: cosine
- lr_scheduler_warmup_steps: 500
- num_epochs: 1
- mixed_precision_training: Native AMP

### Training results

| Training Loss | Epoch | Step | Validation Loss |
|:-------------:|:-----:|:----:|:---------------:|
| 8.9913        | 0.04  | 100  | 8.5511          |
| 7.6809        | 0.08  | 200  | 7.6830          |
| 7.1888        | 0.12  | 300  | 7.2867          |
| 6.7195        | 0.16  | 400  | 6.5053          |
| 5.9705        | 0.2   | 500  | 5.8202          |
| 5.7288        | 0.24  | 600  | 5.6191          |
| 5.5451        | 0.28  | 700  | 5.5350          |
| 5.5478        | 0.32  | 800  | 5.4733          |
| 5.4734        | 0.36  | 900  | 5.4357          |
| 5.5121        | 0.4   | 1000 | 5.4029          |
| 5.4512        | 0.44  | 1100 | 5.3775          |
| 5.3722        | 0.48  | 1200 | 5.3554          |
| 5.3571        | 0.52  | 1300 | 5.3361          |
| 5.3529        | 0.56  | 1400 | 5.3210          |
| 5.2739        | 0.6   | 1500 | 5.3074          |
| 5.2633        | 0.64  | 1600 | 5.2958          |
| 5.3096        | 0.68  | 1700 | 5.2872          |
| 5.2901        | 0.72  | 1800 | 5.2804          |
| 5.2727        | 0.76  | 1900 | 5.2754          |
| 5.2395        | 0.8   | 2000 | 5.2711          |
| 5.267         | 0.84  | 2100 | 5.2680          |
| 5.2738        | 0.88  | 2200 | 5.2663          |
| 5.2766        | 0.92  | 2300 | 5.2652          |
| 5.2228        | 0.96  | 2400 | 5.2648          |
| 5.3183        | 1.0   | 2500 | 5.2647          |


### Framework versions

- Transformers 4.15.0
- Pytorch 1.10.1
- Datasets 1.17.0
- Tokenizers 0.10.3