metadata
license: apache-2.0
tags:
- text-classification
- generated_from_trainer
datasets:
- paws-x
metrics:
- accuracy
model-index:
- name: paws_x_m_bert_only_zh
results:
- task:
name: Text Classification
type: text-classification
dataset:
name: paws-x
type: paws-x
config: zh
split: train
args: zh
metrics:
- name: Accuracy
type: accuracy
value: 0.835
paws_x_m_bert_only_zh
This model is a fine-tuned version of bert-base-multilingual-cased on the paws-x dataset. It achieves the following results on the evaluation set:
- Loss: 0.7979
- Accuracy: 0.835
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: 2e-05
- train_batch_size: 128
- eval_batch_size: 128
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 100
- num_epochs: 10
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 0.4747 | 1.0 | 386 | 0.4424 | 0.807 |
| 0.2681 | 2.0 | 772 | 0.4185 | 0.829 |
| 0.1883 | 3.0 | 1158 | 0.4540 | 0.8305 |
| 0.1416 | 4.0 | 1544 | 0.4700 | 0.8315 |
| 0.111 | 5.0 | 1930 | 0.5074 | 0.8235 |
| 0.0848 | 6.0 | 2316 | 0.6054 | 0.8325 |
| 0.0696 | 7.0 | 2702 | 0.6651 | 0.8335 |
| 0.0555 | 8.0 | 3088 | 0.6952 | 0.8345 |
| 0.046 | 9.0 | 3474 | 0.8017 | 0.8355 |
| 0.0405 | 10.0 | 3860 | 0.7979 | 0.835 |
Framework versions
- Transformers 4.24.0
- Pytorch 1.13.0
- Datasets 2.6.1
- Tokenizers 0.13.1