xnli_m_bert_only_en_single_gpu

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: 1.0082
• Accuracy: 0.8076

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: 7

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
0.3328	1.0	3068	0.5433	0.8036
0.259	2.0	6136	0.5708	0.8008
0.2023	3.0	9204	0.6475	0.8048
0.1362	4.0	12272	0.7661	0.7972
0.0945	5.0	15340	0.8333	0.8008
0.0665	6.0	18408	0.9312	0.8092
0.0463	7.0	21476	1.0082	0.8076

Framework versions

• Transformers 4.24.0
• Pytorch 1.13.0
• Datasets 2.6.1
• Tokenizers 0.13.1