metadata
license: apache-2.0
base_model: google-t5/t5-small
tags:
- generated_from_trainer
metrics:
- rouge
model-index:
- name: my_summarization_model
results: []
my_summarization_model
This model is a fine-tuned version of google-t5/t5-small on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 2.1956
- Rouge1: 0.2007
- Rouge2: 0.1006
- Rougel: 0.1699
- Rougelsum: 0.1695
- 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: 3e-05
- train_batch_size: 8
- eval_batch_size: 8
- seed: 42
- gradient_accumulation_steps: 2
- total_train_batch_size: 16
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 10
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum | Gen Len |
|---|---|---|---|---|---|---|---|---|
| No log | 1.0 | 62 | 2.3847 | 0.1952 | 0.0958 | 0.1639 | 0.1635 | 19.0 |
| No log | 2.0 | 124 | 2.3171 | 0.1997 | 0.0994 | 0.1688 | 0.1685 | 19.0 |
| No log | 3.0 | 186 | 2.2786 | 0.1985 | 0.0992 | 0.1688 | 0.1685 | 19.0 |
| No log | 4.0 | 248 | 2.2493 | 0.2004 | 0.1005 | 0.1695 | 0.1693 | 19.0 |
| No log | 5.0 | 310 | 2.2326 | 0.1995 | 0.1018 | 0.1703 | 0.17 | 19.0 |
| No log | 6.0 | 372 | 2.2189 | 0.1994 | 0.1001 | 0.1692 | 0.1688 | 19.0 |
| No log | 7.0 | 434 | 2.2074 | 0.1999 | 0.1009 | 0.1692 | 0.1689 | 19.0 |
| No log | 8.0 | 496 | 2.2018 | 0.1995 | 0.1003 | 0.1689 | 0.1685 | 19.0 |
| 2.4776 | 9.0 | 558 | 2.1969 | 0.2007 | 0.1003 | 0.1696 | 0.1693 | 19.0 |
| 2.4776 | 10.0 | 620 | 2.1956 | 0.2007 | 0.1006 | 0.1699 | 0.1695 | 19.0 |
Framework versions
- Transformers 4.42.4
- Pytorch 2.4.0+cu121
- Datasets 2.21.0
- Tokenizers 0.19.1