metadata
license: apache-2.0
tags:
- generated_from_trainer
datasets:
- cnn_dailymail
metrics:
- rouge
model-index:
- name: t5-small-finetuned-t5-summarization_3
results:
- task:
name: Sequence-to-sequence Language Modeling
type: text2text-generation
dataset:
name: cnn_dailymail
type: cnn_dailymail
config: 3.0.0
split: train
args: 3.0.0
metrics:
- name: Rouge1
type: rouge
value: 24.4517
t5-small-finetuned-t5-summarization_3
This model is a fine-tuned version of t5-small on the cnn_dailymail dataset. It achieves the following results on the evaluation set:
- Loss: 1.8102
- Rouge1: 24.4517
- Rouge2: 11.7161
- Rougel: 20.205
- Rougelsum: 23.053
- Gen Len: 18.9999
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: 2
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum | Gen Len |
|---|---|---|---|---|---|---|---|---|
| 2.0073 | 1.0 | 17945 | 1.8144 | 24.4341 | 11.7155 | 20.1969 | 23.0364 | 18.9999 |
| 1.9855 | 2.0 | 35890 | 1.8102 | 24.4517 | 11.7161 | 20.205 | 23.053 | 18.9999 |
Framework versions
- Transformers 4.24.0
- Pytorch 1.12.1+cu113
- Datasets 2.7.1
- Tokenizers 0.13.2