metadata
license: apache-2.0
tags:
- generated_from_trainer
datasets:
- billsum
metrics:
- rouge
model-index:
- name: txt_summary_model
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: 0.1389
txt_summary_model
This model is a fine-tuned version of t5-small on the billsum dataset. It achieves the following results on the evaluation set:
- Loss: 2.5514
- Rouge1: 0.1389
- Rouge2: 0.0536
- Rougel: 0.1181
- Rougelsum: 0.1176
- 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
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum | Gen Len |
|---|---|---|---|---|---|---|---|---|
| No log | 1.0 | 62 | 2.8496 | 0.1231 | 0.0345 | 0.1031 | 0.103 | 19.0 |
| No log | 2.0 | 124 | 2.6339 | 0.1302 | 0.0452 | 0.1107 | 0.1105 | 19.0 |
| No log | 3.0 | 186 | 2.5686 | 0.1373 | 0.0518 | 0.1163 | 0.1158 | 19.0 |
| No log | 4.0 | 248 | 2.5514 | 0.1389 | 0.0536 | 0.1181 | 0.1176 | 19.0 |
Framework versions
- Transformers 4.29.2
- Pytorch 2.0.1+cu118
- Datasets 2.12.0
- Tokenizers 0.13.3