|
--- |
|
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: 2.4307 |
|
- 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 | |
|
|:-------------:|:-----:|:----:|:---------------:|:-----------:| |
|
| 6.3427 | 1.0 | 25 | 5.7961 | 0.0 | |
|
| 5.7757 | 2.0 | 50 | 4.8370 | 0.0 | |
|
| 5.0702 | 3.0 | 75 | 4.3284 | 0.0 | |
|
| 4.6064 | 4.0 | 100 | 4.0447 | 0.0 | |
|
| 4.3415 | 5.0 | 125 | 3.8892 | 0.0 | |
|
| 4.1863 | 6.0 | 150 | 3.7803 | 0.0 | |
|
| 4.0684 | 7.0 | 175 | 3.6724 | 0.0 | |
|
| 3.9449 | 8.0 | 200 | 3.5356 | 0.0 | |
|
| 3.7922 | 9.0 | 225 | 3.3716 | 0.0 | |
|
| 3.6343 | 10.0 | 250 | 3.2232 | 0.0 | |
|
| 3.4833 | 11.0 | 275 | 3.0938 | 0.0 | |
|
| 3.3374 | 12.0 | 300 | 2.9880 | 0.0 | |
|
| 3.2006 | 13.0 | 325 | 2.8960 | 0.0 | |
|
| 3.0796 | 14.0 | 350 | 2.8199 | 0.0 | |
|
| 2.9739 | 15.0 | 375 | 2.7270 | 0.0 | |
|
| 2.8824 | 16.0 | 400 | 2.6369 | 0.0 | |
|
| 2.8 | 17.0 | 425 | 2.5811 | 0.0 | |
|
| 2.7323 | 18.0 | 450 | 2.5184 | 0.0 | |
|
| 2.6596 | 19.0 | 475 | 2.4946 | 0.0 | |
|
| 2.5931 | 20.0 | 500 | 2.4307 | 0.0 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.35.2 |
|
- Pytorch 2.1.0+cu118 |
|
- Datasets 2.15.0 |
|
- Tokenizers 0.15.0 |
|
|
