multibert2809_flow / README.md
Tommert25's picture
End of training
11c1427
|
raw
history blame
2.21 kB
metadata
license: apache-2.0
base_model: bert-base-multilingual-uncased
tags:
  - generated_from_trainer
metrics:
  - precision
  - recall
  - f1
  - accuracy
model-index:
  - name: multibert2809_flow
    results: []

multibert2809_flow

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: 0.4534
  • Precision: 0.7055
  • Recall: 0.7076
  • F1: 0.7066
  • Accuracy: 0.8709

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: 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: 8

Training results

Training Loss Epoch Step Validation Loss Precision Recall F1 Accuracy
No log 1.0 118 0.5021 0.6550 0.6229 0.6385 0.8414
No log 2.0 236 0.4534 0.7055 0.7076 0.7066 0.8709
No log 3.0 354 0.4903 0.7455 0.7237 0.7345 0.8752
No log 4.0 472 0.5158 0.7488 0.7327 0.7407 0.8755
0.3074 5.0 590 0.5685 0.7502 0.7434 0.7468 0.8758
0.3074 6.0 708 0.5799 0.7612 0.7530 0.7570 0.8809
0.3074 7.0 826 0.6022 0.7673 0.7494 0.7582 0.8791
0.3074 8.0 944 0.6054 0.7663 0.7554 0.7608 0.8840

Framework versions

  • Transformers 4.33.2
  • Pytorch 2.0.1+cu118
  • Datasets 2.14.5
  • Tokenizers 0.13.3