metadata
license: apache-2.0
tags:
- generated_from_trainer
datasets:
- samsum
metrics:
- rouge
model-index:
- name: flan-t5-base-samsum
results:
- task:
name: Sequence-to-sequence Language Modeling
type: text2text-generation
dataset:
name: samsum
type: samsum
config: samsum
split: test
args: samsum
metrics:
- name: Rouge1
type: rouge
value: 47.6671
flan-t5-base-samsum
This model is a fine-tuned version of google/flan-t5-base on the samsum dataset. It achieves the following results on the evaluation set:
- Loss: 1.3721
- Rouge1: 47.6671
- Rouge2: 23.7549
- Rougel: 40.1406
- Rougelsum: 43.7192
- Gen Len: 17.2759
Model description
google/flan-t5-base model
Intended uses & limitations
Extracting a summary from a conversation
Training and evaluation data
samsum
Training procedure
Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 5e-05
- 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 | Gen Len |
|---|---|---|---|---|---|---|---|---|
| 1.4403 | 1.0 | 1842 | 1.3822 | 47.2861 | 23.7484 | 39.7604 | 43.5177 | 17.0256 |
| 1.3572 | 2.0 | 3684 | 1.3747 | 47.5573 | 23.5406 | 39.8444 | 43.6338 | 17.4347 |
| 1.2822 | 3.0 | 5526 | 1.3721 | 47.6671 | 23.7549 | 40.1406 | 43.7192 | 17.2759 |
| 1.2375 | 4.0 | 7368 | 1.3764 | 47.7917 | 24.0868 | 40.201 | 43.8991 | 17.2943 |
| 1.1935 | 5.0 | 9210 | 1.3781 | 47.6351 | 23.6749 | 39.8766 | 43.6734 | 17.3077 |
Framework versions
- Transformers 4.27.4
- Pytorch 1.13.1+cu116
- Datasets 2.11.0
- Tokenizers 0.13.2