distilbert-base-multilingual-cased-en

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: 0.3298
• Accuracy: 0.8909
• F1: 0.8908

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: 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	Accuracy	F1
0.7829	0.3524	500	0.4586	0.8596	0.8473
0.4282	0.7047	1000	0.3733	0.8759	0.8709
0.3631	1.0571	1500	0.3518	0.8826	0.8810
0.3082	1.4094	2000	0.3330	0.8854	0.8827
0.2862	1.7618	2500	0.3304	0.8890	0.8885
0.2545	2.1142	3000	0.3342	0.8901	0.8887
0.2307	2.4665	3500	0.3298	0.8909	0.8908
0.2246	2.8189	4000	0.3253	0.8907	0.8910

Framework versions

• Transformers 4.44.2
• Pytorch 2.4.1+cu121
• Datasets 3.0.1
• Tokenizers 0.19.1