metadata
license: apache-2.0
base_model: t5-small
tags:
- generated_from_trainer
datasets:
- govreport-summarization
metrics:
- rouge
model-index:
- name: govreport-summarization
results:
- task:
name: Sequence-to-sequence Language Modeling
type: text2text-generation
dataset:
name: govreport-summarization
type: govreport-summarization
config: document
split: train[:17000]
args: document
metrics:
- name: Rouge1
type: rouge
value: 0.1673
govreport-summarization
This model is a fine-tuned version of t5-small on the govreport-summarization dataset. It achieves the following results on the evaluation set:
- Loss: 2.2117
- Rouge1: 0.1673
- Rouge2: 0.0792
- Rougel: 0.1398
- Rougelsum: 0.1398
- Gen Len: 19.0
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: 0.0005
- 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: 4
Training results
Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum | Gen Len |
---|---|---|---|---|---|---|---|---|
2.6565 | 1.0 | 850 | 2.3189 | 0.164 | 0.0744 | 0.1364 | 0.1365 | 19.0 |
2.3913 | 2.0 | 1700 | 2.2522 | 0.1656 | 0.0766 | 0.1379 | 0.138 | 19.0 |
2.2813 | 3.0 | 2550 | 2.2187 | 0.1669 | 0.0779 | 0.1393 | 0.1394 | 19.0 |
2.2273 | 4.0 | 3400 | 2.2117 | 0.1673 | 0.0792 | 0.1398 | 0.1398 | 19.0 |
Framework versions
- Transformers 4.39.3
- Pytorch 2.1.2
- Datasets 2.18.0
- Tokenizers 0.15.2