bert-small-IpadicUnigram2

This model is a fine-tuned version of on an unknown dataset. It achieves the following results on the evaluation set:

• Loss: 1.2725
• Accuracy: 0.7233

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: 14.0

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
1.7647	1.0	69473	1.6172	0.6646
1.6381	2.0	138946	1.4902	0.6853
1.5804	3.0	208419	1.4355	0.6951
1.5448	4.0	277892	1.4004	0.7008
1.52	5.0	347365	1.3740	0.7058
1.4963	6.0	416838	1.3564	0.7089
1.485	7.0	486311	1.3398	0.7113
1.4665	8.0	555784	1.3252	0.7138
1.454	9.0	625257	1.3145	0.7158
1.4447	10.0	694730	1.3027	0.7182
1.4341	11.0	764203	1.2949	0.7192
1.4266	12.0	833676	1.2861	0.7205
1.4191	13.0	903149	1.2764	0.7224
1.4118	14.0	972622	1.2725	0.7233

Framework versions

• Transformers 4.19.2
• Pytorch 1.12.0+cu116
• Datasets 2.9.0
• Tokenizers 0.12.1