metadata

license: apache-2.0
base_model: bert-base-multilingual-uncased
tags:
  - generated_from_trainer
metrics:
  - recall
  - accuracy
model-index:
  - name: multibert1110_lrate7.5b8
    results: []

multibert1110_lrate7.5b8

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

Loss: 0.6124
Precisions: 0.8795
Recall: 0.7898
F-measure: 0.8228
Accuracy: 0.9026

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: 7.5e-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: 14

Training results

Training Loss	Epoch	Step	Validation Loss	Precisions	Recall	F-measure	Accuracy
0.6395	1.0	471	0.4532	0.8345	0.6789	0.6899	0.8619
0.3636	2.0	942	0.3956	0.8284	0.7491	0.7766	0.8853
0.2471	3.0	1413	0.5037	0.8053	0.6950	0.7258	0.8821
0.1785	4.0	1884	0.5098	0.8444	0.7522	0.7755	0.8936
0.1279	5.0	2355	0.5574	0.8751	0.7735	0.8077	0.8973
0.097	6.0	2826	0.6124	0.8795	0.7898	0.8228	0.9026
0.071	7.0	3297	0.5377	0.8621	0.7836	0.8157	0.9044
0.0494	8.0	3768	0.5842	0.8705	0.7725	0.8109	0.9029
0.0344	9.0	4239	0.6835	0.8705	0.7506	0.7912	0.9010
0.0276	10.0	4710	0.6916	0.8226	0.7864	0.7999	0.9048
0.0174	11.0	5181	0.7412	0.8646	0.7491	0.7905	0.8994
0.0112	12.0	5652	0.7701	0.8258	0.7647	0.7866	0.9018
0.0084	13.0	6123	0.7811	0.8331	0.7593	0.7899	0.9058
0.0063	14.0	6594	0.7682	0.8636	0.7763	0.8112	0.9064

Framework versions

Transformers 4.34.0
Pytorch 2.0.1+cu118
Datasets 2.14.5
Tokenizers 0.14.1