|
--- |
|
tags: |
|
- generated_from_trainer |
|
model-index: |
|
- name: baseline |
|
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. --> |
|
|
|
# baseline |
|
|
|
This model is a fine-tuned version of [](https://huggingface.co/) on an unknown dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 2.4466 |
|
- Exact Match: 0.0 |
|
|
|
## 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: 100 |
|
- eval_batch_size: 8 |
|
- seed: 42 |
|
- gradient_accumulation_steps: 4 |
|
- total_train_batch_size: 400 |
|
- optimizer: Adam with betas=(0.98,0.999) and epsilon=1e-08 |
|
- lr_scheduler_type: inverse_sqrt |
|
- lr_scheduler_warmup_steps: 4000 |
|
- num_epochs: 20 |
|
- label_smoothing_factor: 0.1 |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | Exact Match | |
|
|:-------------:|:-----:|:----:|:---------------:|:-----------:| |
|
| 6.3122 | 1.0 | 25 | 5.7364 | 0.0 | |
|
| 5.8177 | 2.0 | 50 | 4.9179 | 0.0 | |
|
| 5.1624 | 3.0 | 75 | 4.4491 | 0.0 | |
|
| 4.7076 | 4.0 | 100 | 4.1395 | 0.0 | |
|
| 4.4358 | 5.0 | 125 | 3.9761 | 0.0 | |
|
| 4.2763 | 6.0 | 150 | 3.8478 | 0.0 | |
|
| 4.1404 | 7.0 | 175 | 3.7119 | 0.0 | |
|
| 3.984 | 8.0 | 200 | 3.5356 | 0.0 | |
|
| 3.8084 | 9.0 | 225 | 3.3644 | 0.0 | |
|
| 3.6421 | 10.0 | 250 | 3.2169 | 0.0 | |
|
| 3.4841 | 11.0 | 275 | 3.0907 | 0.0 | |
|
| 3.3362 | 12.0 | 300 | 2.9754 | 0.0 | |
|
| 3.207 | 13.0 | 325 | 2.8878 | 0.0 | |
|
| 3.0947 | 14.0 | 350 | 2.8081 | 0.0 | |
|
| 3.0028 | 15.0 | 375 | 2.7048 | 0.0 | |
|
| 2.9156 | 16.0 | 400 | 2.6395 | 0.0 | |
|
| 2.8343 | 17.0 | 425 | 2.5716 | 0.0 | |
|
| 2.7597 | 18.0 | 450 | 2.5290 | 0.0 | |
|
| 2.6895 | 19.0 | 475 | 2.4916 | 0.0 | |
|
| 2.619 | 20.0 | 500 | 2.4466 | 0.0 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.35.2 |
|
- Pytorch 2.1.0+cu118 |
|
- Datasets 2.15.0 |
|
- Tokenizers 0.15.0 |
|
|
