metadata
license: apache-2.0
base_model: t5-small
tags:
- generated_from_trainer
datasets:
- xsum
metrics:
- rouge
model-index:
- name: T5-XSum-base
results:
- task:
name: Sequence-to-sequence Language Modeling
type: text2text-generation
dataset:
name: xsum
type: xsum
config: default
split: train
args: default
metrics:
- name: Rouge1
type: rouge
value: 0.273
T5-XSum-base
This model is a fine-tuned version of t5-small on the xsum dataset. It achieves the following results on the evaluation set:
- Loss: 2.5491
- Rouge1: 0.273
- Rouge2: 0.0711
- Rougel: 0.2134
- Rougelsum: 0.2134
- Gen Len: 18.8194
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: 3
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum | Gen Len |
|---|---|---|---|---|---|---|---|---|
| 2.8234 | 1.0 | 2041 | 2.5916 | 0.2623 | 0.0647 | 0.2043 | 0.2044 | 18.8152 |
| 2.7742 | 2.0 | 4082 | 2.5577 | 0.2707 | 0.0702 | 0.2118 | 0.2117 | 18.8212 |
| 2.7482 | 3.0 | 6123 | 2.5491 | 0.273 | 0.0711 | 0.2134 | 0.2134 | 18.8194 |
Framework versions
- Transformers 4.35.0
- Pytorch 1.12.0+cu116
- Datasets 2.14.6
- Tokenizers 0.14.1