20231008-7-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: 0.5624
• Loss: 2.0343

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
3.0373	1.82	200	0.425	2.7059
2.5655	3.64	400	0.4379	2.4156
2.364	5.45	600	0.5187	2.3751
2.2438	7.27	800	0.5045	2.3905
2.1557	9.09	1000	0.5546	2.0966
2.0335	10.91	1200	0.5535	2.0374
2.0174	12.73	1400	0.5431	2.0796
1.9409	14.55	1600	0.5352	2.0956
1.9439	16.36	1800	0.5240	2.1130
1.8895	18.18	2000	0.5662	2.0468
1.875	20.0	2200	0.5624	2.0343

Framework versions

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