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-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: 47.4613
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: 1.3695
- Rouge1: 47.4613
- Rouge2: 23.5823
- Rougel: 39.9425
- Rougelsum: 43.6377
- Gen Len: 17.3529
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 | 46.3369 | 22.6566 | 38.7074 | 42.6189 | 17.2918 |
| 1.3474 | 2.0 | 3684 | 1.3717 | 47.1073 | 23.2596 | 39.4444 | 43.3601 | 17.2735 |
| 1.2818 | 3.0 | 5526 | 1.3701 | 47.3716 | 23.4942 | 39.8061 | 43.4618 | 17.2479 |
| 1.2285 | 4.0 | 7368 | 1.3695 | 47.4613 | 23.5823 | 39.9425 | 43.6377 | 17.3529 |
| 1.196 | 5.0 | 9210 | 1.3735 | 47.3405 | 23.6223 | 39.6825 | 43.574 | 17.3138 |
Framework versions
- Transformers 4.34.1
- Pytorch 2.1.0+cu118
- Datasets 2.14.5
- Tokenizers 0.14.1