|
--- |
|
license: apache-2.0 |
|
tags: |
|
- generated_from_trainer |
|
model-index: |
|
- name: t5-base-extraction-cnndm_fs0.05-all |
|
results: [] |
|
--- |
|
|
|
<!-- This model card has been generated automatically according to the information the Trainer had access to. You |
|
should probably proofread and complete it, then remove this comment. --> |
|
|
|
# t5-base-extraction-cnndm_fs0.05-all |
|
|
|
This model is a fine-tuned version of [t5-base](https://huggingface.co/t5-base) on the None dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 1.7605 |
|
|
|
## 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: 32 |
|
- eval_batch_size: 32 |
|
- seed: 1799 |
|
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
|
- lr_scheduler_type: linear |
|
- num_epochs: 20 |
|
- mixed_precision_training: Native AMP |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | |
|
|:-------------:|:-----:|:----:|:---------------:| |
|
| 2.3409 | 0.45 | 200 | 1.9264 | |
|
| 2.0082 | 0.9 | 400 | 1.8570 | |
|
| 1.9247 | 1.35 | 600 | 1.8290 | |
|
| 1.8895 | 1.81 | 800 | 1.8162 | |
|
| 1.8625 | 2.26 | 1000 | 1.8015 | |
|
| 1.8354 | 2.71 | 1200 | 1.7894 | |
|
| 1.8013 | 3.16 | 1400 | 1.7824 | |
|
| 1.7901 | 3.61 | 1600 | 1.7796 | |
|
| 1.7769 | 4.06 | 1800 | 1.7807 | |
|
| 1.7661 | 4.51 | 2000 | 1.7646 | |
|
| 1.7536 | 4.97 | 2200 | 1.7605 | |
|
| 1.9045 | 5.42 | 2400 | 2.1358 | |
|
| 2.4322 | 5.87 | 2600 | 2.3688 | |
|
| 2.4809 | 6.32 | 2800 | 2.3622 | |
|
| 2.4628 | 6.77 | 3000 | 2.3625 | |
|
| 2.4676 | 7.22 | 3200 | 2.3639 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.18.0 |
|
- Pytorch 1.10.0+cu111 |
|
- Datasets 2.5.1 |
|
- Tokenizers 0.12.1 |
|
|
