summarization-seq_bn-1
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: 0.4996
- Rouge1: 0.4422
- Rouge2: 0.0
- Rougel: 0.4417
- Rougelsum: 0.4403
- 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: 16
- eval_batch_size: 32
- 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 |
---|---|---|---|---|---|---|---|---|
0.7745 | 1.0 | 892 | 0.5559 | 0.7822 | 0.0 | 0.7815 | 0.7779 | 1.0 |
0.604 | 2.0 | 1784 | 0.5500 | 0.7671 | 0.0 | 0.7671 | 0.7636 | 1.0 |
0.5554 | 3.0 | 2676 | 0.5186 | 0.7816 | 0.0 | 0.7796 | 0.7794 | 1.0 |
0.5189 | 4.0 | 3568 | 0.5018 | 0.7767 | 0.0 | 0.7758 | 0.7718 | 1.0 |
0.4887 | 5.0 | 4460 | 0.4996 | 0.756 | 0.0 | 0.7531 | 0.7521 | 1.0 |
Framework versions
- Transformers 4.40.2
- Pytorch 2.3.1+cu121
- Datasets 2.20.0
- Tokenizers 0.19.1
Model tree for apwic/summarization-seq_bn-1
Base model
LazarusNLP/IndoNanoT5-base
Finetuned
this model