metadata
license: apache-2.0
base_model: t5-small
tags:
- generated_from_trainer
metrics:
- rouge
model-index:
- name: my_summarize_vi
results: []
my_summarize_vi
This model is a fine-tuned version of t5-small on the None dataset. It achieves the following results on the evaluation set:
- Loss: 1.4318
- Rouge1: 0.1529
- Rouge2: 0.0521
- Rougel: 0.1315
- Rougelsum: 0.1315
- Gen Len: 18.9997
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: 4
Training results
| Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum | Gen Len |
|---|---|---|---|---|---|---|---|---|
| 1.6652 | 1.0 | 4195 | 1.5465 | 0.1466 | 0.0468 | 0.1246 | 0.1246 | 18.9991 |
| 1.5757 | 2.0 | 8390 | 1.4740 | 0.1509 | 0.0503 | 0.1291 | 0.1292 | 18.9997 |
| 1.5398 | 3.0 | 12585 | 1.4414 | 0.1524 | 0.0517 | 0.1306 | 0.1306 | 18.9997 |
| 1.5271 | 4.0 | 16780 | 1.4318 | 0.1529 | 0.0521 | 0.1315 | 0.1315 | 18.9997 |
Framework versions
- Transformers 4.32.0
- Pytorch 2.0.0
- Datasets 2.14.4
- Tokenizers 0.13.3