camember_jb

This model is a fine-tuned version of Jean-Baptiste/camembert-ner on the None dataset. It achieves the following results on the evaluation set:

• eval_loss: 0.1450
• eval_overall_precision: 0.7188
• eval_overall_recall: 0.7287
• eval_overall_f1: 0.7238
• eval_overall_accuracy: 0.9703
• eval_HumanProd_f1: 0.1961
• eval_LOC_f1: 0.7492
• eval_ORG_f1: 0.4609
• eval_PER_f1: 0.7763
• eval_runtime: 124.2883
• eval_samples_per_second: 19.704
• eval_steps_per_second: 1.239
• epoch: 2.0
• step: 1226

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: 2e-05
• train_batch_size: 16
• eval_batch_size: 16
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 2

Framework versions

• Transformers 4.25.1
• Pytorch 1.13.0+cpu
• Datasets 2.7.1
• Tokenizers 0.13.2