metadata
tags:
- generated_from_trainer
datasets:
- kp20k
metrics:
- rouge
model-index:
- name: ED_keyphrase/
results:
- task:
name: Sequence-to-sequence Language Modeling
type: text2text-generation
dataset:
name: kp20k
type: kp20k
config: generation
split: train[:15%]
args: generation
metrics:
- name: Rouge1
type: rouge
value: 0.0784
ED_keyphrase/
This model is a fine-tuned version of on the kp20k dataset. It achieves the following results on the evaluation set:
- Loss: 4.4436
- Rouge1: 0.0784
- Rouge2: 0.0159
- Rougel: 0.0732
- Rougelsum: 0.0732
- Gen Len: 70.8515
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: 32
- eval_batch_size: 32
- seed: 42
- gradient_accumulation_steps: 2
- total_train_batch_size: 64
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 5
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum | Gen Len |
|---|---|---|---|---|---|---|---|---|
| 6.1614 | 1.0 | 664 | 5.2825 | 0.0866 | 0.0047 | 0.0767 | 0.0767 | 53.6569 |
| 5.2585 | 2.0 | 1328 | 4.7707 | 0.0551 | 0.0087 | 0.0517 | 0.0518 | 83.1487 |
| 4.8764 | 3.0 | 1992 | 4.5703 | 0.0634 | 0.0117 | 0.0594 | 0.0595 | 81.5616 |
| 4.5709 | 4.0 | 2656 | 4.4749 | 0.0743 | 0.0145 | 0.0695 | 0.0695 | 72.9576 |
| 4.4978 | 5.0 | 3320 | 4.4436 | 0.0784 | 0.0159 | 0.0732 | 0.0732 | 70.8515 |
Framework versions
- Transformers 4.25.1
- Pytorch 1.13.0+cu116
- Datasets 2.8.0
- Tokenizers 0.13.2