metadata
license: apache-2.0
base_model: t5-small
tags:
- generated_from_trainer
metrics:
- rouge
model-index:
- name: t5-small-finetuned-booksum
results: []
t5-small-finetuned-booksum
This model is a fine-tuned version of t5-small on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 3.3114
- Rouge1: 13.4323
- Rouge2: 2.5384
- Rougel: 10.3894
- Rougelsum: 12.3641
- Gen Len: 18.9838
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
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum | Gen Len |
|---|---|---|---|---|---|---|---|---|
| 3.5251 | 1.0 | 600 | 3.3437 | 13.1074 | 2.3866 | 10.2062 | 12.0447 | 18.9879 |
| 3.4929 | 2.0 | 1200 | 3.3240 | 13.3594 | 2.4474 | 10.2984 | 12.3059 | 18.9717 |
| 3.4717 | 3.0 | 1800 | 3.3144 | 13.3894 | 2.5074 | 10.3539 | 12.3039 | 18.9838 |
| 3.453 | 4.0 | 2400 | 3.3114 | 13.4323 | 2.5384 | 10.3894 | 12.3641 | 18.9838 |
Framework versions
- Transformers 4.42.4
- Pytorch 2.3.1+cu121
- Datasets 2.20.0
- Tokenizers 0.19.1