metadata
license: apache-2.0
base_model: t5-small
tags:
- generated_from_trainer
datasets:
- billsum
metrics:
- rouge
model-index:
- name: output
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: 0.1372
output
This model is a fine-tuned version of t5-small on the billsum dataset. It achieves the following results on the evaluation set:
- Loss: 2.5639
- Rouge1: 0.1372
- Rouge2: 0.0474
- Rougel: 0.1123
- Rougelsum: 0.1125
- 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 | 2.8673 | 0.1296 | 0.0367 | 0.1074 | 0.1074 | 19.0 |
| No log | 2.0 | 124 | 2.6480 | 0.1377 | 0.0469 | 0.1135 | 0.1137 | 19.0 |
| No log | 3.0 | 186 | 2.5819 | 0.1368 | 0.0477 | 0.1121 | 0.1123 | 19.0 |
| No log | 4.0 | 248 | 2.5639 | 0.1372 | 0.0474 | 0.1123 | 0.1125 | 19.0 |
Framework versions
- Transformers 4.35.2
- Pytorch 2.1.0+cu121
- Datasets 2.15.0
- Tokenizers 0.15.0