metadata
license: apache-2.0
base_model: t5-small
tags:
- generated_from_trainer
metrics:
- rouge
model-index:
- name: news_model
results: []
news_model
This model is a fine-tuned version of t5-small on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 2.6746
- Rouge1: 0.1497
- Rouge2: 0.0486
- Rougel: 0.1145
- Rougelsum: 0.1145
- Gen Len: 18.9964
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 |
|---|---|---|---|---|---|---|---|---|
| 2.9581 | 1.0 | 2249 | 2.7274 | 0.1472 | 0.0469 | 0.1125 | 0.1125 | 18.996 |
| 2.9039 | 2.0 | 4498 | 2.6915 | 0.149 | 0.048 | 0.114 | 0.114 | 18.996 |
| 2.882 | 3.0 | 6747 | 2.6782 | 0.1494 | 0.0483 | 0.1144 | 0.1144 | 18.996 |
| 2.8737 | 4.0 | 8996 | 2.6746 | 0.1497 | 0.0486 | 0.1145 | 0.1145 | 18.9964 |
Framework versions
- Transformers 4.41.0.dev0
- Pytorch 2.2.1+cu121
- Datasets 2.19.1
- Tokenizers 0.19.1