metadata
license: apache-2.0
tags:
- text-classification
- generated_from_trainer
datasets:
- paws-x
metrics:
- accuracy
model-index:
- name: paws_x_m_bert_only_de
results:
- task:
name: Text Classification
type: text-classification
dataset:
name: paws-x
type: paws-x
config: de
split: train
args: de
metrics:
- name: Accuracy
type: accuracy
value: 0.842
paws_x_m_bert_only_de
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: 0.7211
- Accuracy: 0.842
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 |
|---|---|---|---|---|
| 0.4287 | 1.0 | 386 | 0.4346 | 0.797 |
| 0.2188 | 2.0 | 772 | 0.4121 | 0.84 |
| 0.1515 | 3.0 | 1158 | 0.4299 | 0.837 |
| 0.1143 | 4.0 | 1544 | 0.4907 | 0.8355 |
| 0.0899 | 5.0 | 1930 | 0.4714 | 0.8405 |
| 0.0686 | 6.0 | 2316 | 0.5606 | 0.832 |
| 0.0585 | 7.0 | 2702 | 0.5846 | 0.8445 |
| 0.047 | 8.0 | 3088 | 0.6634 | 0.841 |
| 0.0399 | 9.0 | 3474 | 0.6921 | 0.8385 |
| 0.0351 | 10.0 | 3860 | 0.7211 | 0.842 |
Framework versions
- Transformers 4.24.0
- Pytorch 1.13.0
- Datasets 2.6.1
- Tokenizers 0.13.1