metadata
license: apache-2.0
tags:
- summarization
- generated_from_trainer
model-index:
- name: t5-small-salidaLarga-tfg
results: []
t5-small-salidaLarga-tfg
This model is a fine-tuned version of t5-small on the None dataset. It achieves the following results on the evaluation set:
- Loss: 3.3428
- Rouge2 Precision: 0.0633
- Rouge2 Recall: 0.1234
- Rouge2 Fmeasure: 0.0835
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: 5e-05
- train_batch_size: 1
- eval_batch_size: 1
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 4
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 2
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Rouge2 Precision | Rouge2 Recall | Rouge2 Fmeasure |
|---|---|---|---|---|---|---|
| 7.2339 | 0.27 | 10 | 4.7620 | 0.0337 | 0.0321 | 0.0327 |
| 4.3192 | 0.53 | 20 | 4.0073 | 0.0427 | 0.05 | 0.046 |
| 3.9608 | 0.8 | 30 | 3.6537 | 0.0589 | 0.0922 | 0.0717 |
| 3.7992 | 1.07 | 40 | 3.4747 | 0.0626 | 0.1114 | 0.08 |
| 3.7694 | 1.33 | 50 | 3.3968 | 0.0618 | 0.1145 | 0.0801 |
| 3.5839 | 1.6 | 60 | 3.3600 | 0.0654 | 0.1248 | 0.0856 |
| 3.5573 | 1.87 | 70 | 3.3428 | 0.0633 | 0.1234 | 0.0835 |
Framework versions
- Transformers 4.27.4
- Pytorch 1.13.1+cu116
- Datasets 2.11.0
- Tokenizers 0.13.2