metadata
license: mit
base_model: cointegrated/rut5-base-absum
tags:
- generated_from_trainer
metrics:
- rouge
model-index:
- name: flux-dsum
results: []
flux-dsum
This model is a fine-tuned version of cointegrated/rut5-base-absum on the None dataset. It achieves the following results on the evaluation set:
- Loss: 1.3535
- Rouge1: 0.3631
- Rouge2: 0.1695
- Rougel: 0.325
- Rougelsum: 0.3251
- Gen Len: 18.2008
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: 2
- eval_batch_size: 2
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 4
Training results
| Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum | Gen Len |
|---|---|---|---|---|---|---|---|---|
| 1.7402 | 1.0 | 21753 | 1.4456 | 0.3492 | 0.1601 | 0.3112 | 0.3114 | 18.0104 |
| 1.59 | 2.0 | 43506 | 1.3912 | 0.3569 | 0.1616 | 0.3186 | 0.3187 | 18.1955 |
| 1.5522 | 3.0 | 65259 | 1.3675 | 0.3607 | 0.1682 | 0.3231 | 0.3233 | 18.1123 |
| 1.5162 | 4.0 | 87012 | 1.3535 | 0.3631 | 0.1695 | 0.325 | 0.3251 | 18.2008 |
Framework versions
- Transformers 4.36.0.dev0
- Pytorch 2.1.0+cu121
- Datasets 2.14.6
- Tokenizers 0.14.1