16class_all9k_promptcorr_tweet_300other_23nov23_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: 0.0267
• Accuracy: 0.9947

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
1.5225	1.0	721	0.6075	0.8344
0.7164	2.0	1442	0.3430	0.9051
0.3828	3.0	2163	0.2532	0.9271
0.318	4.0	2884	0.1631	0.9572
0.2131	5.0	3605	0.1231	0.9676
0.1728	6.0	4326	0.0822	0.9807
0.1344	7.0	5047	0.0657	0.9849
0.0902	8.0	5768	0.0471	0.9887
0.0842	9.0	6489	0.0383	0.9912
0.0609	10.0	7210	0.0281	0.9941
0.0512	11.0	7931	0.0267	0.9947

Framework versions

• Transformers 4.35.2
• Pytorch 2.1.1+cu121
• Datasets 2.15.0
• Tokenizers 0.15.0