metadata
license: apache-2.0
tags:
- text-classification
- generated_from_trainer
datasets:
- xnli
metrics:
- accuracy
model-index:
- name: xnli_m_bert_only_ar
results:
- task:
name: Text Classification
type: text-classification
dataset:
name: xnli
type: xnli
config: ar
split: train
args: ar
metrics:
- name: Accuracy
type: accuracy
value: 0.7080321285140563
xnli_m_bert_only_ar
This model is a fine-tuned version of bert-base-multilingual-cased on the xnli dataset. It achieves the following results on the evaluation set:
- Loss: 1.3353
- Accuracy: 0.7080
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: 128
- eval_batch_size: 128
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 10
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 0.7262 | 1.0 | 3068 | 0.7710 | 0.6715 |
| 0.6461 | 2.0 | 6136 | 0.7109 | 0.6984 |
| 0.563 | 3.0 | 9204 | 0.7325 | 0.7052 |
| 0.4802 | 4.0 | 12272 | 0.7542 | 0.7100 |
| 0.3985 | 5.0 | 15340 | 0.7598 | 0.7072 |
| 0.325 | 6.0 | 18408 | 0.9285 | 0.6932 |
| 0.2554 | 7.0 | 21476 | 0.9771 | 0.7040 |
| 0.202 | 8.0 | 24544 | 1.0835 | 0.7100 |
| 0.1594 | 9.0 | 27612 | 1.2160 | 0.7056 |
| 0.1273 | 10.0 | 30680 | 1.3353 | 0.7080 |
Framework versions
- Transformers 4.24.0
- Pytorch 1.13.0
- Datasets 2.6.1
- Tokenizers 0.13.1