metadata
tags:
- generated_from_trainer
datasets:
- hotpot_qa
metrics:
- rouge
model-index:
- name: t5-qg-finetuned-hotpotqa
results:
- task:
name: Sequence-to-sequence Language Modeling
type: text2text-generation
dataset:
name: hotpot_qa
type: hotpot_qa
config: distractor
split: train
args: distractor
metrics:
- name: Rouge1
type: rouge
value: 44.4906
t5-qg-finetuned-hotpotqa
This model is a fine-tuned version of p208p2002/t5-squad-qg-hl on the hotpot_qa dataset. It achieves the following results on the evaluation set:
- Loss: 1.2046
- Rouge1: 44.4906
- Rouge2: 26.3193
- Rougel: 39.9929
- Rougelsum: 39.9879
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: 5.6e-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: 3
Training results
| Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum |
|---|---|---|---|---|---|---|---|
| 1.379 | 1.0 | 1875 | 1.2998 | 43.0766 | 24.8898 | 38.4029 | 38.4874 |
| 1.2011 | 2.0 | 3750 | 1.2225 | 44.7538 | 26.1406 | 39.9817 | 39.9714 |
| 1.1027 | 3.0 | 5625 | 1.2046 | 44.4906 | 26.3193 | 39.9929 | 39.9879 |
Framework versions
- Transformers 4.24.0
- Pytorch 1.12.1+cu113
- Datasets 2.7.1
- Tokenizers 0.13.2