metadata
tags:
- generated_from_trainer
model-index:
- name: longt5_xl_govreport_4096_memsum_e20
results: []
longt5_xl_govreport_4096_memsum_e20
This model was trained from scratch on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 2.4413
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: 0.001
- train_batch_size: 8
- eval_batch_size: 8
- seed: 42
- gradient_accumulation_steps: 32
- total_train_batch_size: 256
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: constant
- num_epochs: 10.0
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 0.4496 | 1.0 | 68 | 1.8158 |
| 0.3462 | 1.99 | 136 | 1.7510 |
| 0.3171 | 2.99 | 204 | 1.8821 |
| 0.2761 | 3.99 | 272 | 2.0322 |
| 0.2338 | 5.0 | 341 | 2.0432 |
| 0.1998 | 6.0 | 409 | 2.2008 |
| 0.1512 | 6.99 | 477 | 2.3444 |
| 0.1618 | 7.99 | 545 | 2.3309 |
| 0.1392 | 8.99 | 613 | 2.4437 |
| 0.1271 | 9.97 | 680 | 2.4413 |
Framework versions
- Transformers 4.34.0.dev0
- Pytorch 2.0.1+cu117
- Datasets 2.14.5
- Tokenizers 0.13.3