metadata

license: apache-2.0
base_model: bert-base-multilingual-uncased
tags:
  - generated_from_trainer
metrics:
  - recall
  - accuracy
model-index:
  - name: multibert_seed34_1611
    results: []

multibert_seed34_1611

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: 0.4810
Precisions: 0.8743
Recall: 0.8016
F-measure: 0.8318
Accuracy: 0.9364

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: 16
eval_batch_size: 16
seed: 34
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
0.4954	1.0	236	0.2579	0.8908	0.7174	0.7485	0.9181
0.2427	2.0	472	0.2589	0.8472	0.7340	0.7497	0.9209
0.1427	3.0	708	0.2844	0.8461	0.7830	0.8096	0.9325
0.0916	4.0	944	0.3453	0.8497	0.7804	0.8122	0.9306
0.0616	5.0	1180	0.3281	0.8500	0.7936	0.8160	0.9303
0.0414	6.0	1416	0.3859	0.8494	0.7930	0.8167	0.9337
0.0272	7.0	1652	0.3863	0.8572	0.7894	0.8167	0.9323
0.0207	8.0	1888	0.3998	0.8525	0.7938	0.8195	0.9337
0.0117	9.0	2124	0.4348	0.8555	0.7983	0.8228	0.9330
0.0089	10.0	2360	0.4858	0.8699	0.7708	0.7996	0.9294
0.0054	11.0	2596	0.4676	0.8559	0.7959	0.8197	0.9344
0.0036	12.0	2832	0.4582	0.8665	0.8038	0.8291	0.9364
0.0025	13.0	3068	0.4810	0.8743	0.8016	0.8318	0.9364
0.0018	14.0	3304	0.4801	0.8685	0.8036	0.8309	0.9366

Framework versions

Transformers 4.35.2
Pytorch 2.1.0+cu118
Datasets 2.15.0
Tokenizers 0.15.0