|
--- |
|
base_model: bert-base-chinese |
|
tags: |
|
- generated_from_trainer |
|
model-index: |
|
- name: ntu_adl_span_selection_bert |
|
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. --> |
|
|
|
# ntu_adl_span_selection_bert |
|
|
|
This model is a fine-tuned version of [bert-base-chinese](https://huggingface.co./bert-base-chinese) on an unknown dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 2.0552 |
|
- Em Accuracy: 0.7607 |
|
|
|
## 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: 3e-05 |
|
- train_batch_size: 1 |
|
- eval_batch_size: 1 |
|
- seed: 42 |
|
- gradient_accumulation_steps: 2 |
|
- total_train_batch_size: 2 |
|
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
|
- lr_scheduler_type: linear |
|
- num_epochs: 5 |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | Em Accuracy | |
|
|:-------------:|:-----:|:-----:|:---------------:|:-----------:| |
|
| 1.161 | 1.0 | 10857 | 1.2192 | 0.7029 | |
|
| 0.7596 | 2.0 | 21714 | 1.3003 | 0.7338 | |
|
| 0.551 | 3.0 | 32571 | 1.5081 | 0.7398 | |
|
| 0.2034 | 4.0 | 43428 | 1.8194 | 0.7474 | |
|
| 0.0762 | 5.0 | 54285 | 2.0552 | 0.7607 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.34.1 |
|
- Pytorch 2.1.0+cu118 |
|
- Datasets 2.14.6 |
|
- Tokenizers 0.14.1 |
|
|
