---
license: apache-2.0
base_model: google/long-t5-tglobal-xl
tags:
- generated_from_trainer
datasets:
- learn3r/summ_screen_fd_bp
metrics:
- rouge
model-index:
- name: longt5_xl_sfd_bp_20
  results:
  - task:
      name: Summarization
      type: summarization
    dataset:
      name: learn3r/summ_screen_fd_bp
      type: learn3r/summ_screen_fd_bp
    metrics:
    - name: Rouge1
      type: rouge
      value: 22.11
---

<!-- 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. -->

# longt5_xl_sfd_bp_20

This model is a fine-tuned version of [google/long-t5-tglobal-xl](https://huggingface.co/google/long-t5-tglobal-xl) on the learn3r/summ_screen_fd_bp dataset.
It achieves the following results on the evaluation set:
- Loss: 1.5032
- Rouge1: 22.11
- Rouge2: 7.544
- Rougel: 19.7035
- Rougelsum: 20.2813
- Gen Len: 497.8783

## 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: 0.001
- train_batch_size: 8
- eval_batch_size: 8
- seed: 42
- gradient_accumulation_steps: 32
- total_train_batch_size: 256
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: constant
- num_epochs: 20.0

### Training results

| Training Loss | Epoch | Step | Validation Loss | Rouge1  | Rouge2  | Rougel  | Rougelsum | Gen Len  |
|:-------------:|:-----:|:----:|:---------------:|:-------:|:-------:|:-------:|:---------:|:--------:|
| 2.3973        | 0.97  | 14   | 1.9074          | 10.6164 | 2.4585  | 10.4856 | 9.8193    | 511.0    |
| 1.9188        | 1.95  | 28   | 1.7082          | 17.4258 | 4.2128  | 16.5213 | 15.8377   | 511.0    |
| 1.4297        | 2.99  | 43   | 1.5073          | 18.6504 | 5.4242  | 17.2648 | 17.0203   | 506.7745 |
| 1.2759        | 3.97  | 57   | 1.5032          | 22.11   | 7.544   | 19.7035 | 20.2813   | 497.8783 |
| 1.1421        | 4.94  | 71   | 1.5462          | 20.6049 | 6.7146  | 18.5084 | 19.0876   | 503.6024 |
| 0.9605        | 5.98  | 86   | 1.6233          | 22.6777 | 7.9362  | 18.7936 | 21.41     | 510.2730 |
| 0.8082        | 6.96  | 100  | 1.7575          | 26.5338 | 9.9474  | 20.3789 | 25.0767   | 511.0    |
| 0.664         | 8.0   | 115  | 1.7702          | 35.1918 | 13.7223 | 26.1763 | 33.3997   | 329.7151 |
| 0.5471        | 8.97  | 129  | 1.9383          | 27.0414 | 10.4166 | 20.1803 | 25.6283   | 506.8279 |
| 0.4349        | 9.95  | 143  | 1.9608          | 29.5613 | 11.7633 | 22.7176 | 27.9563   | 454.7033 |
| 0.4338        | 10.99 | 158  | 2.1197          | 31.2004 | 12.8569 | 22.1282 | 29.8827   | 493.3234 |
| 0.2887        | 11.97 | 172  | 2.1205          | 34.9566 | 13.8574 | 25.1764 | 33.2914   | 381.3591 |
| 0.2753        | 12.94 | 186  | 2.4299          | 36.3877 | 13.8584 | 25.7829 | 34.8601   | 338.7240 |
| 0.2114        | 13.98 | 201  | 2.5799          | 39.7535 | 16.1209 | 27.8512 | 37.8553   | 302.4837 |
| 0.1805        | 14.96 | 215  | 2.6123          | 33.3254 | 13.0868 | 23.3214 | 31.7901   | 442.9258 |
| 0.1543        | 16.0  | 230  | 2.5635          | 31.7816 | 13.1085 | 22.9117 | 30.2286   | 463.0801 |
| 0.5166        | 16.97 | 244  | 2.5134          | 30.3969 | 12.1295 | 21.6616 | 28.7606   | 511.0    |
| 0.1117        | 17.95 | 258  | 2.8109          | 35.336  | 14.9492 | 24.1938 | 33.822    | 431.1157 |
| 0.0895        | 18.99 | 273  | 2.7577          | 41.0982 | 16.3935 | 28.1073 | 39.1641   | 240.1365 |
| 0.0779        | 19.48 | 280  | 2.8927          | 32.7788 | 13.9352 | 22.5175 | 31.548    | 488.5134 |


### Framework versions

- Transformers 4.34.1
- Pytorch 2.1.0+cu121
- Datasets 2.14.5
- Tokenizers 0.14.1