metadata
license: apache-2.0
base_model: buianh0803/Text_Summarization
tags:
- generated_from_trainer
datasets:
- cnn_dailymail
metrics:
- rouge
model-index:
- name: text-sum
results:
- task:
name: Sequence-to-sequence Language Modeling
type: text2text-generation
dataset:
name: cnn_dailymail
type: cnn_dailymail
config: 3.0.0
split: test
args: 3.0.0
metrics:
- name: Rouge1
type: rouge
value: 0.2484
text-sum
This model is a fine-tuned version of buianh0803/Text_Summarization on the cnn_dailymail dataset. It achieves the following results on the evaluation set:
- Loss: 1.6668
- Rouge1: 0.2484
- Rouge2: 0.1187
- Rougel: 0.2056
- Rougelsum: 0.2055
- Gen Len: 18.9986
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: 5
Training results
| Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum | Gen Len |
|---|---|---|---|---|---|---|---|---|
| 1.8345 | 1.0 | 17945 | 1.6835 | 0.2475 | 0.118 | 0.2047 | 0.2047 | 18.998 |
| 1.8152 | 2.0 | 35890 | 1.6720 | 0.2479 | 0.1179 | 0.2048 | 0.2048 | 18.9986 |
| 1.7954 | 3.0 | 53835 | 1.6712 | 0.2477 | 0.1182 | 0.205 | 0.2051 | 18.9981 |
| 1.7975 | 4.0 | 71780 | 1.6680 | 0.2482 | 0.1186 | 0.2054 | 0.2054 | 18.9981 |
| 1.7924 | 5.0 | 89725 | 1.6668 | 0.2484 | 0.1187 | 0.2056 | 0.2055 | 18.9986 |
Framework versions
- Transformers 4.34.0
- Pytorch 2.0.1+cu118
- Datasets 2.14.5
- Tokenizers 0.14.1