metadata
license: apache-2.0
base_model: t5-small
tags:
- generated_from_trainer
datasets:
- arxiv-summarization
metrics:
- rouge
model-index:
- name: my_awesome_billsum_model
results:
- task:
name: Sequence-to-sequence Language Modeling
type: text2text-generation
dataset:
name: arxiv-summarization
type: arxiv-summarization
config: section
split: test
args: section
metrics:
- name: Rouge1
type: rouge
value: 0.1446
my_awesome_billsum_model
This model is a fine-tuned version of t5-small on the arxiv-summarization dataset. It achieves the following results on the evaluation set:
- Loss: 2.8844
- Rouge1: 0.1446
- Rouge2: 0.0426
- Rougel: 0.1172
- Rougelsum: 0.117
- 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: 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: 4
Training results
| Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum | Gen Len |
|---|---|---|---|---|---|---|---|---|
| No log | 1.0 | 63 | 3.0098 | 0.1319 | 0.0348 | 0.105 | 0.1049 | 19.0 |
| No log | 2.0 | 126 | 2.9186 | 0.1383 | 0.0393 | 0.1121 | 0.1119 | 19.0 |
| No log | 3.0 | 189 | 2.8920 | 0.1441 | 0.0424 | 0.1166 | 0.1165 | 19.0 |
| No log | 4.0 | 252 | 2.8844 | 0.1446 | 0.0426 | 0.1172 | 0.117 | 19.0 |
Framework versions
- Transformers 4.33.3
- Pytorch 2.0.1+cpu
- Datasets 2.14.5
- Tokenizers 0.13.3