vmw-mbert-focal

This model is a fine-tuned version of google-bert/bert-base-multilingual-uncased on an unknown dataset. It achieves the following results on the evaluation set:

• Loss: 7.3491
• F1-micro: 0.2160
• F1-macro: 0.2129

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: 3e-05
• train_batch_size: 32
• eval_batch_size: 8
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• lr_scheduler_warmup_steps: 15
• num_epochs: 4

Training results

Training Loss	Epoch	Step	Validation Loss	F1-micro	F1-macro
59.9673	1.0	39	7.9372	0.1801	0.1498
58.4439	2.0	78	7.6562	0.2115	0.2035
57.2029	3.0	117	7.4439	0.2205	0.2175
54.4624	4.0	156	7.3491	0.2160	0.2129

Framework versions

• Transformers 4.44.2
• Pytorch 2.4.1+cu121
• Datasets 3.2.0
• Tokenizers 0.19.1