robbert2809_lrate7.5

This model is a fine-tuned version of pdelobelle/robbert-v2-dutch-base on an unknown dataset. It achieves the following results on the evaluation set:

  • Loss: 0.3477
  • Precision: 0.7368
  • Recall: 0.7716
  • F1: 0.7538
  • Accuracy: 0.9017

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: 8

Training results

Training Loss Epoch Step Validation Loss Precision Recall F1 Accuracy
No log 1.0 118 0.3855 0.6721 0.6533 0.6625 0.8795
No log 2.0 236 0.3511 0.6921 0.7284 0.7098 0.8880
No log 3.0 354 0.3477 0.7368 0.7716 0.7538 0.9017
No log 4.0 472 0.4055 0.7489 0.7628 0.7558 0.9019
0.3159 5.0 590 0.3930 0.7506 0.7488 0.7497 0.9035
0.3159 6.0 708 0.4131 0.7684 0.7716 0.7700 0.9082
0.3159 7.0 826 0.4382 0.7714 0.7786 0.7749 0.9093
0.3159 8.0 944 0.4478 0.7817 0.7698 0.7757 0.9097

Framework versions

  • Transformers 4.33.3
  • Pytorch 2.0.1+cu118
  • Datasets 2.14.5
  • Tokenizers 0.13.3
Downloads last month
5
Inference Providers NEW
This model is not currently available via any of the supported Inference Providers.

Model tree for Tommert25/robbert2809_lrate7.5

Finetuned
(41)
this model