README.md

metadata

license: mit
base_model: roberta-base
tags:
  - generated_from_trainer
model-index:
  - name: roberta-base-ner-2
    results: []

roberta-base-ner-2

This model is a fine-tuned version of roberta-base on an unknown dataset. It achieves the following results on the evaluation set:

• Loss: 0.0707
• Overall Precision: 0.7602
• Overall Recall: 0.6756
• Overall F1: 0.7154
• Org Precision: 0.7796
• Org Recall: 0.6360
• Org F1: 0.7005
• Per Precision: 0.8989
• Per Recall: 0.9524
• Per F1: 0.9249
• Loc Precision: 0.5702
• Loc Recall: 0.7113
• Loc F1: 0.6330

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: 5

Training results

Training Loss	Epoch	Step	Validation Loss	Overall Precision	Overall Recall	Overall F1	Org Precision	Org Recall	Org F1	Per Precision	Per Recall	Per F1	Loc Precision	Loc Recall	Loc F1
No log	1.0	53	0.1109	0.4123	0.3852	0.3983	0.4138	0.4889	0.4482	0.0	0.0	0.0	0.0	0.0	0.0
No log	2.0	106	0.0746	0.7003	0.6429	0.6703	0.7180	0.6166	0.6635	0.8571	0.9286	0.8914	0.4870	0.5773	0.5283
No log	3.0	159	0.0707	0.7602	0.6756	0.7154	0.7796	0.6360	0.7005	0.8989	0.9524	0.9249	0.5702	0.7113	0.6330
No log	4.0	212	0.0725	0.7870	0.6967	0.7391	0.7896	0.6523	0.7144	0.9425	0.9762	0.9591	0.6549	0.7629	0.7048
No log	5.0	265	0.0738	0.7874	0.6897	0.7353	0.7909	0.6464	0.7114	0.9425	0.9762	0.9591	0.6486	0.7423	0.6923

Framework versions

• Transformers 4.34.1
• Pytorch 2.1.0+cu118
• Datasets 2.14.6
• Tokenizers 0.14.1