jplu-wikiann

This model is a fine-tuned version of jplu/tf-camembert-base on the wikiann dataset. It achieves the following results on the evaluation set:

• precision: 0.8980
• recall: 0.9097
• f1: 0.9038
• accuracy: 0.9464

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:

• num_train_epochs: 5
• train_batch_size: 16
• eval_batch_size: 32
• learning_rate: 2e-05
• weight_decay_rate: 0.01
• num_warmup_steps: 0
• fp16: True

Framework versions

• Transformers 4.15.0
• Pytorch 1.10.0+cu111
• Datasets 1.18.0
• Tokenizers 0.10.3