metadata
license: apache-2.0
base_model: t5-small
tags:
- generated_from_trainer
metrics:
- rouge
model-index:
- name: T5_small_sum
results: []
T5_small_sum
This model is a fine-tuned version of t5-small on the None dataset. It achieves the following results on the evaluation set:
- Loss: 2.2513
- Rouge1: 0.4054
- Rouge2: 0.235
- Rougel: 0.3672
- Rougelsum: 0.3674
- Gen Len: 17.9888
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 |
|---|---|---|---|---|---|---|---|---|
| No log | 1.0 | 400 | 2.3801 | 0.3823 | 0.2151 | 0.3411 | 0.3409 | 18.2544 |
| 2.7768 | 2.0 | 800 | 2.2951 | 0.3984 | 0.2289 | 0.3602 | 0.3605 | 18.0169 |
| 2.5068 | 3.0 | 1200 | 2.2620 | 0.4033 | 0.2327 | 0.3652 | 0.3656 | 18.0069 |
| 2.4601 | 4.0 | 1600 | 2.2513 | 0.4054 | 0.235 | 0.3672 | 0.3674 | 17.9888 |
Framework versions
- Transformers 4.41.1
- Pytorch 1.13.1+cu117
- Datasets 2.19.1
- Tokenizers 0.19.1