bert-small-ipadic_bpe

This model is a fine-tuned version of on the None dataset. It achieves the following results on the evaluation set:

• Loss: 1.6777
• Accuracy: 0.6519

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: 0.0001
• train_batch_size: 256
• eval_batch_size: 8
• seed: 42
• distributed_type: multi-GPU
• num_devices: 3
• total_train_batch_size: 768
• total_eval_batch_size: 24
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• lr_scheduler_warmup_ratio: 0.01
• num_epochs: 14
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
2.2548	1.0	69473	2.1163	0.5882
2.0904	2.0	138946	1.9562	0.6101
2.0203	3.0	208419	1.8848	0.6208
1.978	4.0	277892	1.8408	0.6272
1.937	5.0	347365	1.8080	0.6320
1.9152	6.0	416838	1.7818	0.6361
1.8982	7.0	486311	1.7575	0.6395
1.8808	8.0	555784	1.7413	0.6421
1.8684	9.0	625257	1.7282	0.6440
1.8517	10.0	694730	1.7140	0.6464
1.8353	11.0	764203	1.7022	0.6481
1.8245	12.0	833676	1.6877	0.6504
1.8191	13.0	903149	1.6829	0.6515
1.8122	14.0	972622	1.6777	0.6519

Framework versions

• Transformers 4.19.2
• Pytorch 1.12.0+cu116
• Datasets 2.2.2
• Tokenizers 0.12.1