20231008-8-distilbert-base-multilingual-cased-new

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

• Accuracy: 0.5897
• Loss: 1.6732

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: 2e-05
• train_batch_size: 32
• eval_batch_size: 32
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 20

Training results

Training Loss	Epoch	Step	Accuracy	Validation Loss
3.0429	1.82	200	0.3604	2.6666
2.587	3.64	400	0.4161	2.4828
2.3902	5.45	600	0.4649	2.3097
2.2656	7.27	800	0.4621	2.3834
2.1488	9.09	1000	0.5201	1.9849
2.0856	10.91	1200	0.5513	1.9794
2.0031	12.73	1400	0.5919	1.8554
1.9627	14.55	1600	0.6177	1.6912
1.9088	16.36	1800	0.5766	2.0344
1.8993	18.18	2000	0.5435	2.0127
1.8831	20.0	2200	0.5897	1.6732

Framework versions

• Transformers 4.34.0
• Pytorch 2.0.1+cu118
• Datasets 2.14.5
• Tokenizers 0.14.1