20231008-6-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: 0.5455
• Loss: 1.8971

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
2.986	1.82	200	0.4025	2.5695
2.5918	3.64	400	0.4226	2.7134
2.3791	5.45	600	0.4910	2.2179
2.2254	7.27	800	0.5318	2.1007
2.1229	9.09	1000	0.5120	2.1417
2.0372	10.91	1200	0.5850	1.7700
1.9785	12.73	1400	0.4904	2.1310
1.9538	14.55	1600	0.5392	1.8208
1.8633	16.36	1800	0.5880	1.9510
1.8488	18.18	2000	0.5667	1.9505
1.8494	20.0	2200	0.5455	1.8971

Framework versions

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