|
|
--- |
|
|
license: apache-2.0 |
|
|
tags: |
|
|
- generated_from_trainer |
|
|
datasets: |
|
|
- xsum |
|
|
model-index: |
|
|
- name: model |
|
|
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. --> |
|
|
|
|
|
# model |
|
|
|
|
|
This model is a fine-tuned version of [facebook/bart-large](https://huggingface.co/facebook/bart-large) on the xsum dataset. |
|
|
It achieves the following results on the evaluation set: |
|
|
- Loss: 1.5537 |
|
|
|
|
|
## 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: 5e-05 |
|
|
- train_batch_size: 2 |
|
|
- eval_batch_size: 2 |
|
|
- seed: 42 |
|
|
- gradient_accumulation_steps: 16 |
|
|
- total_train_batch_size: 32 |
|
|
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
|
|
- lr_scheduler_type: linear |
|
|
- lr_scheduler_warmup_steps: 500 |
|
|
- num_epochs: 1 |
|
|
|
|
|
### Training results |
|
|
|
|
|
| Training Loss | Epoch | Step | Validation Loss | |
|
|
|:-------------:|:-----:|:----:|:---------------:| |
|
|
| 1.9566 | 0.08 | 500 | 1.7765 | |
|
|
| 1.9288 | 0.16 | 1000 | 1.7549 | |
|
|
| 1.8561 | 0.24 | 1500 | 1.7462 | |
|
|
| 1.7802 | 0.31 | 2000 | 1.6921 | |
|
|
| 1.8444 | 0.39 | 2500 | 1.6699 | |
|
|
| 1.8145 | 0.47 | 3000 | 1.6525 | |
|
|
| 1.7736 | 0.55 | 3500 | 1.6313 | |
|
|
| 1.7259 | 0.63 | 4000 | 1.6234 | |
|
|
| 1.7028 | 0.71 | 4500 | 1.6217 | |
|
|
| 1.7235 | 0.78 | 5000 | 1.5750 | |
|
|
| 1.6534 | 0.86 | 5500 | 1.5749 | |
|
|
| 1.6392 | 0.94 | 6000 | 1.5537 | |
|
|
|
|
|
|
|
|
### Framework versions |
|
|
|
|
|
- Transformers 4.26.1 |
|
|
- Pytorch 1.13.1+cu117 |
|
|
- Datasets 2.10.1 |
|
|
- Tokenizers 0.13.2 |
|
|
|
