metadata
library_name: transformers
license: apache-2.0
base_model: t5-small
tags:
- summarization
- generated_from_trainer
datasets:
- multi_news
metrics:
- rouge
model-index:
- name: t5-small-Abstractive-Summarizer
results:
- task:
name: Sequence-to-sequence Language Modeling
type: text2text-generation
dataset:
name: multi_news
type: multi_news
config: default
split: validation
args: default
metrics:
- name: Rouge1
type: rouge
value: 15.0486
t5-small-Abstractive-Summarizer
This model is a fine-tuned version of t5-small on the multi_news dataset. It achieves the following results on the evaluation set:
- Loss: 2.8162
- Rouge1: 15.0486
- Rouge2: 5.1197
- Rougel: 12.0288
- Rougelsum: 13.4434
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: 0.00056
- train_batch_size: 8
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 5
Training results
| Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum |
|---|---|---|---|---|---|---|---|
| 2.7895 | 1.0 | 113 | 2.7479 | 15.6051 | 5.1347 | 12.2224 | 13.8875 |
| 2.6034 | 2.0 | 226 | 2.7745 | 15.2054 | 4.7334 | 11.7555 | 13.436 |
| 2.4515 | 3.0 | 339 | 2.7820 | 15.008 | 4.6612 | 11.5993 | 13.3788 |
| 2.3439 | 4.0 | 452 | 2.8056 | 15.2475 | 4.9304 | 11.8552 | 13.4615 |
| 2.2803 | 5.0 | 565 | 2.8162 | 15.0486 | 5.1197 | 12.0288 | 13.4434 |
Framework versions
- Transformers 4.44.2
- Pytorch 2.4.0+cu121
- Datasets 2.21.0
- Tokenizers 0.19.1