NLP-HIBA2_DisTEMIST_fine_tuned_DistilBERT-pretrained-model

This model is a fine-tuned version of distilbert-base-multilingual-cased on the None dataset. It achieves the following results on the evaluation set:

• Loss: 0.2224
• Precision: 0.5553
• Recall: 0.5163
• F1: 0.5351
• Accuracy: 0.9502

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: 5e-05
• train_batch_size: 8
• eval_batch_size: 8
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 10

Training results

Training Loss	Epoch	Step	Validation Loss	Precision	Recall	F1	Accuracy
No log	1.0	71	0.1767	0.4612	0.4905	0.4754	0.9399
No log	2.0	142	0.1696	0.5173	0.4400	0.4755	0.9481
No log	3.0	213	0.1782	0.5189	0.5290	0.5239	0.9485
No log	4.0	284	0.1928	0.5275	0.4988	0.5128	0.9475
No log	5.0	355	0.2020	0.5800	0.4782	0.5242	0.9512
No log	6.0	426	0.2091	0.5645	0.4849	0.5217	0.9506
No log	7.0	497	0.2035	0.5608	0.5095	0.5339	0.9511
0.0531	8.0	568	0.2150	0.5282	0.5385	0.5333	0.9484
0.0531	9.0	639	0.2224	0.5639	0.5068	0.5338	0.9507
0.0531	10.0	710	0.2224	0.5553	0.5163	0.5351	0.9502

Framework versions

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