metadata
library_name: transformers
license: apache-2.0
base_model: google/flan-t5-base
tags:
- generated_from_trainer
datasets:
- eli5_category
metrics:
- rouge
model-index:
- name: flan-t5-base-finetuned-t5
results:
- task:
name: Sequence-to-sequence Language Modeling
type: text2text-generation
dataset:
name: eli5_category
type: eli5_category
config: default
split: validation1
args: default
metrics:
- name: Rouge1
type: rouge
value: 10.1877
flan-t5-base-finetuned-t5
This model is a fine-tuned version of google/flan-t5-base on the eli5_category dataset. It achieves the following results on the evaluation set:
- Loss: nan
- Rouge1: 10.1877
- Rouge2: 0.0
- Rougel: 10.1808
- Rougelsum: 10.1824
- Gen Len: 9.366
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: 2e-05
- train_batch_size: 16
- eval_batch_size: 16
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 3
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum | Gen Len |
|---|---|---|---|---|---|---|---|---|
| 0.0 | 1.0 | 5736 | nan | 10.1877 | 0.0 | 10.1808 | 10.1824 | 9.366 |
| 0.0 | 2.0 | 11472 | nan | 10.1877 | 0.0 | 10.1808 | 10.1824 | 9.366 |
| 0.0 | 3.0 | 17208 | nan | 10.1877 | 0.0 | 10.1808 | 10.1824 | 9.366 |
Framework versions
- Transformers 4.44.2
- Pytorch 2.4.1+cu121
- Datasets 3.0.1
- Tokenizers 0.19.1