metadata
license: apache-2.0
base_model: t5-small
tags:
- generated_from_trainer
metrics:
- rouge
model-index:
- name: t5-small-checkpoint-finetuned-pav1
results: []
t5-small-checkpoint-finetuned-pav1
This model is a fine-tuned version of t5-small on the None dataset. It achieves the following results on the evaluation set:
- Loss: 2.8461
- Rouge1: 8.8662
- Rouge2: 2.3482
- Rougel: 7.1437
- Rougelsum: 8.1986
- 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: 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: 6
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum | Gen Len |
|---|---|---|---|---|---|---|---|---|
| 3.2493 | 1.0 | 1250 | 2.9730 | 8.6473 | 2.2038 | 6.9787 | 7.9995 | 19.0 |
| 3.1397 | 2.0 | 2500 | 2.9083 | 8.8119 | 2.332 | 7.0958 | 8.1469 | 19.0 |
| 3.0943 | 3.0 | 3750 | 2.8793 | 8.9522 | 2.4215 | 7.21 | 8.2723 | 19.0 |
| 3.0728 | 4.0 | 5000 | 2.8571 | 8.8992 | 2.3688 | 7.174 | 8.2298 | 19.0 |
| 3.0566 | 5.0 | 6250 | 2.8493 | 8.841 | 2.3368 | 7.1312 | 8.1745 | 19.0 |
| 3.0409 | 6.0 | 7500 | 2.8461 | 8.8662 | 2.3482 | 7.1437 | 8.1986 | 19.0 |
Framework versions
- Transformers 4.39.3
- Pytorch 2.1.2
- Datasets 2.18.0
- Tokenizers 0.15.2