metadata

license: apache-2.0
tags:
  - text-classification
  - generated_from_trainer
datasets:
  - xnli
metrics:
  - accuracy
model-index:
  - name: xnli_m_bert_only_vi
    results:
      - task:
          name: Text Classification
          type: text-classification
        dataset:
          name: xnli
          type: xnli
          config: vi
          split: train
          args: vi
        metrics:
          - name: Accuracy
            type: accuracy
            value: 0.7401606425702811

xnli_m_bert_only_vi

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: 1.2539
Accuracy: 0.7402

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
0.6634	1.0	3068	0.7030	0.7016
0.5848	2.0	6136	0.6031	0.7518
0.5003	3.0	9204	0.6296	0.7418
0.4159	4.0	12272	0.6398	0.7482
0.3395	5.0	15340	0.7042	0.7438
0.2648	6.0	18408	0.9274	0.7345
0.2062	7.0	21476	0.9433	0.7373
0.1544	8.0	24544	1.0372	0.7378
0.1164	9.0	27612	1.1879	0.7357
0.0882	10.0	30680	1.2539	0.7402

Framework versions

Transformers 4.24.0
Pytorch 1.13.0
Datasets 2.6.1
Tokenizers 0.13.1