|
|
--- |
|
|
tags: |
|
|
- generated_from_trainer |
|
|
model-index: |
|
|
- name: ossp-v0_3 |
|
|
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. --> |
|
|
|
|
|
# ossp-v0_3 |
|
|
|
|
|
This model is a fine-tuned version of [leadawon/ossp-v0_2](https://huggingface.co/leadawon/ossp-v0_2) on an unknown dataset. |
|
|
It achieves the following results on the evaluation set: |
|
|
- Loss: 0.3451 |
|
|
|
|
|
## 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: 24 |
|
|
- eval_batch_size: 24 |
|
|
- seed: 42 |
|
|
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
|
|
- lr_scheduler_type: linear |
|
|
- lr_scheduler_warmup_ratio: 0.1 |
|
|
- num_epochs: 4 |
|
|
- mixed_precision_training: Native AMP |
|
|
|
|
|
### Training results |
|
|
|
|
|
| Training Loss | Epoch | Step | Validation Loss | |
|
|
|:-------------:|:-----:|:------:|:---------------:| |
|
|
| 0.3999 | 0.2 | 10000 | 0.4079 | |
|
|
| 0.4441 | 0.39 | 20000 | 0.4555 | |
|
|
| 0.4361 | 0.59 | 30000 | 0.4378 | |
|
|
| 0.4302 | 0.79 | 40000 | 0.4255 | |
|
|
| 0.4392 | 0.98 | 50000 | 0.4076 | |
|
|
| 0.3714 | 1.18 | 60000 | 0.4006 | |
|
|
| 0.3694 | 1.38 | 70000 | 0.3908 | |
|
|
| 0.3591 | 1.57 | 80000 | 0.3810 | |
|
|
| 0.3594 | 1.77 | 90000 | 0.3762 | |
|
|
| 0.3567 | 1.97 | 100000 | 0.3667 | |
|
|
| 0.3041 | 2.16 | 110000 | 0.3663 | |
|
|
| 0.299 | 2.36 | 120000 | 0.3603 | |
|
|
| 0.2972 | 2.56 | 130000 | 0.3569 | |
|
|
| 0.2892 | 2.75 | 140000 | 0.3519 | |
|
|
| 0.2844 | 2.95 | 150000 | 0.3463 | |
|
|
| 0.2372 | 3.15 | 160000 | 0.3522 | |
|
|
| 0.2367 | 3.34 | 170000 | 0.3508 | |
|
|
| 0.2295 | 3.54 | 180000 | 0.3489 | |
|
|
| 0.2281 | 3.74 | 190000 | 0.3468 | |
|
|
| 0.2233 | 3.93 | 200000 | 0.3451 | |
|
|
|
|
|
|
|
|
### Framework versions |
|
|
|
|
|
- Transformers 4.28.1 |
|
|
- Pytorch 2.0.0+cu118 |
|
|
- Tokenizers 0.13.3 |
|
|
|
