ner__edgar_all_4-simple-no-valid-roberta-base__roberta-base
This model is a fine-tuned version of roberta-base on the lltala/edgar_all_4-simple-no-valid-roberta-base dataset. It achieves the following results on the evaluation set:
- Loss: 0.0045
- Loc Precision: 0.8614
- Loc Recall: 0.9355
- Loc F1: 0.8969
- Loc Number: 93
- Org Precision: 0.9807
- Org Recall: 0.9880
- Org F1: 0.9844
- Org Number: 669
- Per Precision: 0.9432
- Per Recall: 0.9881
- Per F1: 0.9651
- Per Number: 84
- Overall Precision: 0.9629
- Overall Recall: 0.9823
- Overall F1: 0.9725
- Overall Accuracy: 0.9987
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