metadata
license: apache-2.0
tags:
- generated_from_trainer
datasets:
- arxiv-summarization
metrics:
- rouge
model-index:
- name: t5-base-axriv-to-abstract-3
results:
- task:
name: Sequence-to-sequence Language Modeling
type: text2text-generation
dataset:
name: arxiv-summarization
type: arxiv-summarization
config: section
split: validation
args: section
metrics:
- name: Rouge1
type: rouge
value: 0.1301
t5-base-axriv-to-abstract-3
This model is a fine-tuned version of t5-base on the arxiv-summarization dataset. It achieves the following results on the evaluation set:
- Loss: 2.6588
- Rouge1: 0.1301
- Rouge2: 0.0481
- Rougel: 0.1047
- Rougelsum: 0.1047
- 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: 4
- eval_batch_size: 4
- 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 |
|---|---|---|---|---|---|---|---|---|
| 2.5634 | 0.61 | 4000 | 2.4010 | 0.1339 | 0.0519 | 0.1074 | 0.1075 | 19.0 |
| 2.4533 | 1.21 | 8000 | 2.3582 | 0.1318 | 0.0517 | 0.1067 | 0.1067 | 19.0 |
| 3.0109 | 1.82 | 12000 | 2.7488 | 0.1366 | 0.0509 | 0.1096 | 0.1095 | 18.9963 |
| 2.9063 | 2.42 | 16000 | 2.6588 | 0.1301 | 0.0481 | 0.1047 | 0.1047 | 19.0 |
Framework versions
- Transformers 4.28.0
- Pytorch 2.0.0+cu118
- Datasets 2.11.0
- Tokenizers 0.13.3