summarization-base-0
This model is a fine-tuned version of LazarusNLP/IndoNanoT5-base on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.7149
- Rouge1: 0.4331
- Rouge2: 0.0
- Rougel: 0.4333
- Rougelsum: 0.4319
- Gen Len: 1.0
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: 0.001
- train_batch_size: 4
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 5.0
Training results
Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum | Gen Len |
---|---|---|---|---|---|---|---|---|
1.5249 | 1.0 | 3566 | 0.8858 | 0.417 | 0.0 | 0.4187 | 0.414 | 1.0 |
0.8202 | 2.0 | 7132 | 0.7492 | 0.4125 | 0.0 | 0.412 | 0.4102 | 1.0 |
0.6232 | 3.0 | 10698 | 0.6953 | 0.4015 | 0.0 | 0.3971 | 0.3965 | 1.0 |
0.4728 | 4.0 | 14264 | 0.6717 | 0.4319 | 0.0 | 0.4307 | 0.4292 | 1.0 |
0.3238 | 5.0 | 17830 | 0.7149 | 0.4331 | 0.0 | 0.4333 | 0.4319 | 1.0 |
Framework versions
- Transformers 4.40.2
- Pytorch 2.3.0+cu121
- Datasets 2.19.1
- Tokenizers 0.19.1
- Downloads last month
- 26
Model tree for apwic/summarization-base-0
Base model
LazarusNLP/IndoNanoT5-base