metadata
license: apache-2.0
base_model: t5-small
tags:
- summarization
- generated_from_trainer
datasets:
- billsum
metrics:
- rouge
model-index:
- name: text_summarization_t5_trainer
results:
- task:
name: Sequence-to-sequence Language Modeling
type: text2text-generation
dataset:
name: billsum
type: billsum
config: default
split: ca_test
args: default
metrics:
- name: Rouge1
type: rouge
value: 0.1285
text_summarization_t5_trainer
This model is a fine-tuned version of t5-small on the billsum dataset. It achieves the following results on the evaluation set:
- Loss: 2.9562
- Rouge1: 0.1285
- Rouge2: 0.0396
- Rougel: 0.1104
- Rougelsum: 0.1102
- 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: 64
- eval_batch_size: 64
- 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 | 16 | 3.5925 | 0.1421 | 0.0501 | 0.1208 | 0.1207 | 19.0 |
| No log | 2.0 | 32 | 3.1487 | 0.1339 | 0.0428 | 0.1146 | 0.1145 | 19.0 |
| No log | 3.0 | 48 | 2.9987 | 0.1285 | 0.04 | 0.1101 | 0.1099 | 19.0 |
| No log | 4.0 | 64 | 2.9562 | 0.1285 | 0.0396 | 0.1104 | 0.1102 | 19.0 |
Framework versions
- Transformers 4.34.0
- Pytorch 2.1.0a0+29c30b1
- Datasets 2.14.5
- Tokenizers 0.14.1