bert-small-UnidicBpe2

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

• Loss: 1.5693
• Accuracy: 0.6686

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
2.0974	1.0	69473	1.9746	0.6071
1.9586	2.0	138946	1.8301	0.6284
1.889	3.0	208419	1.7627	0.6383
1.8496	4.0	277892	1.7236	0.6442
1.8188	5.0	347365	1.6924	0.6490
1.7983	6.0	416838	1.6650	0.6535
1.7788	7.0	486311	1.6484	0.6558
1.7623	8.0	555784	1.6328	0.6580
1.7497	9.0	625257	1.6182	0.6605
1.7321	10.0	694730	1.6064	0.6623
1.7225	11.0	764203	1.5908	0.6647
1.707	12.0	833676	1.5859	0.6660
1.7049	13.0	903149	1.5752	0.6672
1.6982	14.0	972622	1.5693	0.6686

Framework versions

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