---
base_model: google/pegasus-x-base
tags:
- generated_from_trainer
model-index:
- name: pegasus_x-meeting-summarizer-gpt3.5
  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. -->

# pegasus_x-meeting-summarizer-gpt3.5

This model is a fine-tuned version of [google/pegasus-x-base](https://huggingface.co/google/pegasus-x-base) on the None dataset.
It achieves the following results on the evaluation set:
- Loss: 1.6064

## 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: 1
- eval_batch_size: 1
- seed: 42
- gradient_accumulation_steps: 16
- total_train_batch_size: 16
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: reduce_lr_on_plateau
- num_epochs: 3

### Training results

| Training Loss | Epoch | Step | Validation Loss |
|:-------------:|:-----:|:----:|:---------------:|
| 3.7528        | 0.05  | 10   | 2.5788          |
| 2.7466        | 0.11  | 20   | 2.2694          |
| 2.4032        | 0.16  | 30   | 2.1298          |
| 2.3188        | 0.21  | 40   | 2.0389          |
| 2.1827        | 0.27  | 50   | 1.9788          |
| 2.1284        | 0.32  | 60   | 1.9291          |
| 2.1275        | 0.37  | 70   | 1.9024          |
| 2.0536        | 0.43  | 80   | 1.8587          |
| 1.9901        | 0.48  | 90   | 1.8407          |
| 1.9769        | 0.53  | 100  | 1.8211          |
| 1.9643        | 0.59  | 110  | 1.8048          |
| 1.8846        | 0.64  | 120  | 1.7921          |
| 1.9294        | 0.69  | 130  | 1.7837          |
| 1.903         | 0.75  | 140  | 1.7664          |
| 1.9329        | 0.8   | 150  | 1.7606          |
| 1.865         | 0.85  | 160  | 1.7493          |
| 1.8414        | 0.91  | 170  | 1.7404          |
| 1.8793        | 0.96  | 180  | 1.7310          |
| 1.8519        | 1.01  | 190  | 1.7165          |
| 1.7918        | 1.07  | 200  | 1.7132          |
| 1.7815        | 1.12  | 210  | 1.7087          |
| 1.7503        | 1.17  | 220  | 1.7019          |
| 1.7545        | 1.23  | 230  | 1.6937          |
| 1.7088        | 1.28  | 240  | 1.6905          |
| 1.7231        | 1.33  | 250  | 1.6862          |
| 1.7584        | 1.39  | 260  | 1.6807          |
| 1.7537        | 1.44  | 270  | 1.6762          |
| 1.7867        | 1.49  | 280  | 1.6685          |
| 1.7666        | 1.55  | 290  | 1.6642          |
| 1.7076        | 1.6   | 300  | 1.6580          |
| 1.6894        | 1.65  | 310  | 1.6596          |
| 1.7207        | 1.71  | 320  | 1.6535          |
| 1.6743        | 1.76  | 330  | 1.6565          |
| 1.7197        | 1.81  | 340  | 1.6491          |
| 1.7027        | 1.87  | 350  | 1.6438          |
| 1.7161        | 1.92  | 360  | 1.6388          |
| 1.7256        | 1.97  | 370  | 1.6368          |
| 1.6623        | 2.03  | 380  | 1.6370          |
| 1.6041        | 2.08  | 390  | 1.6402          |
| 1.6308        | 2.13  | 400  | 1.6289          |
| 1.6384        | 2.19  | 410  | 1.6333          |
| 1.6223        | 2.24  | 420  | 1.6291          |
| 1.6163        | 2.29  | 430  | 1.6212          |
| 1.6232        | 2.35  | 440  | 1.6267          |
| 1.6081        | 2.4   | 450  | 1.6302          |
| 1.619         | 2.45  | 460  | 1.6196          |
| 1.5802        | 2.51  | 470  | 1.6215          |
| 1.6313        | 2.56  | 480  | 1.6216          |
| 1.5968        | 2.61  | 490  | 1.6153          |
| 1.589         | 2.67  | 500  | 1.6137          |
| 1.6087        | 2.72  | 510  | 1.6129          |
| 1.5614        | 2.77  | 520  | 1.6085          |
| 1.6109        | 2.83  | 530  | 1.6067          |
| 1.596         | 2.88  | 540  | 1.6097          |
| 1.6343        | 2.93  | 550  | 1.5979          |
| 1.5774        | 2.99  | 560  | 1.6064          |


### Framework versions

- Transformers 4.38.1
- Pytorch 2.1.0+cu121
- Datasets 2.18.0
- Tokenizers 0.15.2