bert-small-unidic-bpe2

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

• Loss: 1.5665
• Accuracy: 0.6690

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: 768
• eval_batch_size: 16
• seed: 42
• 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
2.111	1.0	69473	1.9831	0.6056
1.9667	2.0	138946	1.8334	0.6277
1.8918	3.0	208419	1.7656	0.6376
1.8518	4.0	277892	1.7219	0.6444
1.8202	5.0	347365	1.6904	0.6490
1.7996	6.0	416838	1.6705	0.6524
1.7767	7.0	486311	1.6479	0.6558
1.7663	8.0	555784	1.6339	0.6577
1.7524	9.0	625257	1.6159	0.6611
1.7398	10.0	694730	1.6020	0.6627
1.7229	11.0	764203	1.5920	0.6645
1.7127	12.0	833676	1.5836	0.6658
1.7011	13.0	903149	1.5737	0.6677
1.7	14.0	972622	1.5665	0.6690

Framework versions

• Transformers 4.26.1
• Pytorch 1.13.1+cu117
• Datasets 2.9.0
• Tokenizers 0.13.2