Edit model card

multibert1010_lrate7.5b32

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: 0.5515
  • Precisions: 0.8551
  • Recall: 0.8069
  • F-measure: 0.8283
  • Accuracy: 0.9171

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: 32
  • eval_batch_size: 32
  • 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
0.6054 1.0 118 0.4021 0.8661 0.6558 0.6767 0.8698
0.316 2.0 236 0.4039 0.8167 0.6935 0.7317 0.8800
0.1896 3.0 354 0.3480 0.8183 0.7792 0.7780 0.9003
0.1318 4.0 472 0.3930 0.8529 0.7703 0.7983 0.8965
0.0846 5.0 590 0.4027 0.8348 0.8010 0.8141 0.9047
0.0652 6.0 708 0.4824 0.8298 0.7555 0.7855 0.9002
0.0398 7.0 826 0.5446 0.8697 0.7766 0.8110 0.9017
0.0335 8.0 944 0.4761 0.8402 0.8013 0.8192 0.9054
0.0228 9.0 1062 0.5232 0.8547 0.7921 0.8156 0.9085
0.0181 10.0 1180 0.5477 0.8560 0.7968 0.8226 0.9133
0.0106 11.0 1298 0.5207 0.8370 0.8050 0.8199 0.9142
0.0075 12.0 1416 0.5381 0.8469 0.8025 0.8229 0.9156
0.0038 13.0 1534 0.5573 0.8538 0.8061 0.8269 0.9165
0.0047 14.0 1652 0.5515 0.8551 0.8069 0.8283 0.9171

Framework versions

  • Transformers 4.34.0
  • Pytorch 2.0.1+cu118
  • Datasets 2.14.5
  • Tokenizers 0.14.1
Downloads last month
2
Inference Examples
This model does not have enough activity to be deployed to Inference API (serverless) yet. Increase its social visibility and check back later, or deploy to Inference Endpoints (dedicated) instead.

Model tree for Tommert25/multibert1010_lrate7.5b32

Finetuned
(104)
this model