metadata

library_name: transformers
license: apache-2.0
base_model: bert-base-multilingual-cased
tags:
  - generated_from_trainer
metrics:
  - accuracy
model-index:
  - name: mBERT-4
    results: []

mBERT-4

This model is a fine-tuned version of bert-base-multilingual-cased on the generator dataset. It achieves the following results on the evaluation set:

Loss: 0.5499
Accuracy: 0.8737
Micro Precision: 0.8737
Micro Recall: 0.8737
Micro F1: 0.8737
Macro Precision: 0.7217
Macro Recall: 0.7435
Macro F1: 0.7211

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: 12
eval_batch_size: 12
seed: 42
optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
lr_scheduler_type: linear
num_epochs: 8

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy	Micro Precision	Micro Recall	Micro F1	Macro Precision	Macro Recall	Macro F1
1.4916	1.0	868	0.6403	0.8	0.8	0.8	0.8	0.4830	0.4893	0.4736
0.7293	2.0	1736	0.4581	0.8684	0.8684	0.8684	0.8684	0.6734	0.6721	0.6634
0.5325	3.0	2604	0.4473	0.8632	0.8632	0.8632	0.8632	0.7108	0.7176	0.7076
0.4271	4.0	3472	0.5030	0.8737	0.8737	0.8737	0.8737	0.7014	0.7087	0.6965
0.29	5.0	4340	0.5381	0.8737	0.8737	0.8737	0.8737	0.7069	0.6907	0.6923
0.2108	6.0	5208	0.5382	0.8895	0.8895	0.8895	0.8895	0.7234	0.7560	0.7216
0.1264	7.0	6076	0.5208	0.8842	0.8842	0.8842	0.8842	0.7110	0.7488	0.7165
0.1054	8.0	6944	0.5499	0.8737	0.8737	0.8737	0.8737	0.7217	0.7435	0.7211

Framework versions

Transformers 4.46.2
Pytorch 2.5.1+cu124
Datasets 3.1.0
Tokenizers 0.20.3