|
--- |
|
license: apache-2.0 |
|
base_model: facebook/bart-large |
|
tags: |
|
- generated_from_trainer |
|
model-index: |
|
- name: bart-finetuned-eli5_precomputed |
|
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. --> |
|
|
|
# bart-finetuned-eli5_precomputed |
|
|
|
This model is a fine-tuned version of [facebook/bart-large](https://huggingface.co/facebook/bart-large) on an unknown dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 9.6500 |
|
|
|
## 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 |
|
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
|
- lr_scheduler_type: linear |
|
- num_epochs: 2 |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | |
|
|:-------------:|:-----:|:-----:|:---------------:| |
|
| 3.6463 | 0.05 | 500 | 4.7759 | |
|
| 3.4654 | 0.1 | 1000 | 5.9053 | |
|
| 3.4482 | 0.15 | 1500 | 4.4967 | |
|
| 3.565 | 0.2 | 2000 | 5.9963 | |
|
| 3.6668 | 0.25 | 2500 | 7.3841 | |
|
| 3.6065 | 0.3 | 3000 | 5.0156 | |
|
| 3.3743 | 0.35 | 3500 | 4.0016 | |
|
| 3.3529 | 0.4 | 4000 | 7.0397 | |
|
| 3.5418 | 0.45 | 4500 | 9.1284 | |
|
| 3.4724 | 0.5 | 5000 | 5.0625 | |
|
| 3.4167 | 0.55 | 5500 | 6.0408 | |
|
| 3.4061 | 0.6 | 6000 | 7.1911 | |
|
| 3.6455 | 0.65 | 6500 | 5.6523 | |
|
| 3.5153 | 0.7 | 7000 | 5.8586 | |
|
| 3.4019 | 0.75 | 7500 | 6.6155 | |
|
| 3.4094 | 0.8 | 8000 | 6.0468 | |
|
| 3.399 | 0.85 | 8500 | 6.7307 | |
|
| 3.4732 | 0.9 | 9000 | 11.2534 | |
|
| 3.4973 | 0.95 | 9500 | 8.8126 | |
|
| 3.4901 | 1.0 | 10000 | 7.7330 | |
|
| 3.4378 | 1.05 | 10500 | 8.1397 | |
|
| 3.4239 | 1.1 | 11000 | 7.5238 | |
|
| 3.4238 | 1.15 | 11500 | 10.0907 | |
|
| 3.5335 | 1.2 | 12000 | 9.3069 | |
|
| 3.4442 | 1.25 | 12500 | 9.1980 | |
|
| 3.1866 | 1.3 | 13000 | 10.1322 | |
|
| 3.2806 | 1.35 | 13500 | 9.0616 | |
|
| 3.323 | 1.4 | 14000 | 9.7061 | |
|
| 3.3219 | 1.45 | 14500 | 7.5160 | |
|
| 3.5641 | 1.5 | 15000 | 10.6759 | |
|
| 3.2667 | 1.55 | 15500 | 9.1428 | |
|
| 3.4873 | 1.6 | 16000 | 10.4514 | |
|
| 3.4092 | 1.65 | 16500 | 10.0229 | |
|
| 3.4617 | 1.7 | 17000 | 9.6849 | |
|
| 3.3726 | 1.75 | 17500 | 9.7335 | |
|
| 3.2492 | 1.8 | 18000 | 9.0959 | |
|
| 3.3322 | 1.85 | 18500 | 9.4717 | |
|
| 3.3306 | 1.9 | 19000 | 10.2230 | |
|
| 3.3026 | 1.95 | 19500 | 9.9560 | |
|
| 3.2199 | 2.0 | 20000 | 9.6500 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.36.0.dev0 |
|
- Pytorch 2.1.0+cu118 |
|
- Datasets 2.15.0 |
|
- Tokenizers 0.15.0 |
|
|
