distilbert-multilingual-uncased-en-de-fr-oct-19

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:

• Loss: 0.0273
• F1: 0.9623

Model description

This was trained off a cased model, but with .lower() applied to each of the records, if you wish for it to work you must lowercase before inferencing

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: 4e-05
• train_batch_size: 16
• eval_batch_size: 16
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 3

Training results

Training Loss	Epoch	Step	Validation Loss	F1
0.0573	1.0	6468	0.0364	0.9402
0.0224	2.0	12936	0.0281	0.9572
0.0108	3.0	19404	0.0273	0.9623

Framework versions

• Transformers 4.23.1
• Pytorch 1.12.1+cu113
• Tokenizers 0.13.1