ner__edgar_all_4-no-valid-roberta-base__roberta-base

This model is a fine-tuned version of roberta-base on the lltala/edgar_all_4-no-valid-roberta-base dataset. It achieves the following results on the evaluation set:

• Loss: 0.0074
• Loc Precision: 0.8687
• Loc Recall: 0.8866
• Loc F1: 0.8776
• Loc Number: 97
• Org Precision: 0.9455
• Org Recall: 0.9792
• Org F1: 0.9620
• Org Number: 673
• Per Precision: 0.9438
• Per Recall: 1.0
• Per F1: 0.9711
• Per Number: 84
• Overall Precision: 0.9367
• Overall Recall: 0.9707
• Overall F1: 0.9534
• Overall Accuracy: 0.9982

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: 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: 3.0

Training results

Framework versions

• Transformers 4.35.0.dev0
• Pytorch 2.1.0+cu118
• Datasets 2.14.6
• Tokenizers 0.14.1