16class_combo_vth_new_pp_full_updated_tweet_13nov23_v1

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

• Loss: 0.0420
• Accuracy: 0.9908

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: 1e-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: 11

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
1.5945	1.0	735	0.7331	0.7813
0.8273	2.0	1470	0.4370	0.8743
0.4943	3.0	2205	0.3176	0.9061
0.3995	4.0	2940	0.2252	0.9335
0.2712	5.0	3675	0.1714	0.9517
0.2352	6.0	4410	0.1183	0.9690
0.1794	7.0	5145	0.0823	0.9795
0.1361	8.0	5880	0.0634	0.9861
0.1111	9.0	6615	0.0514	0.9885
0.0891	10.0	7350	0.0440	0.9900
0.0675	11.0	8085	0.0420	0.9908

Framework versions

• Transformers 4.35.0
• Pytorch 2.1.0+cu121
• Datasets 2.14.6
• Tokenizers 0.14.1