metadata
license: apache-2.0
base_model: google/flan-t5-base
tags:
- generated_from_trainer
datasets:
- samsum
metrics:
- rouge
model-index:
- name: flan-t5-base-samah
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: 47.4528
flan-t5-base-samah
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: 1.3695
- Rouge1: 47.4528
- Rouge2: 23.6072
- Rougel: 39.9094
- Rougelsum: 43.6038
- Gen Len: 17.3480
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: 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 |
|---|---|---|---|---|---|---|---|---|
| 1.4497 | 1.0 | 1842 | 1.3848 | 46.3027 | 22.627 | 38.6676 | 42.6434 | 17.3223 |
| 1.3474 | 2.0 | 3684 | 1.3718 | 47.1006 | 23.3454 | 39.5336 | 43.373 | 17.2503 |
| 1.2817 | 3.0 | 5526 | 1.3701 | 47.4623 | 23.6266 | 39.9575 | 43.5799 | 17.2503 |
| 1.2287 | 4.0 | 7368 | 1.3695 | 47.4528 | 23.6072 | 39.9094 | 43.6038 | 17.3480 |
| 1.196 | 5.0 | 9210 | 1.3735 | 47.5266 | 23.7604 | 39.7747 | 43.6293 | 17.3028 |
Framework versions
- Transformers 4.31.0
- Pytorch 1.12.1+cu116
- Datasets 2.14.4
- Tokenizers 0.12.1