distilbert-expense-ner

This model is a fine-tuned version of renjithks/distilbert-cord-ner on an unknown dataset. It achieves the following results on the evaluation set:

• Loss: 0.2930
• Precision: 0.5096
• Recall: 0.4852
• F1: 0.4971
• Accuracy: 0.9275

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: 8
• eval_batch_size: 8
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 10

Training results

Training Loss	Epoch	Step	Validation Loss	Precision	Recall	F1	Accuracy
No log	1.0	22	0.3635	0.2888	0.0945	0.1424	0.8866
No log	2.0	44	0.2795	0.3213	0.3018	0.3113	0.8982
No log	3.0	66	0.2432	0.4243	0.4034	0.4136	0.9161
No log	4.0	88	0.2446	0.4615	0.4654	0.4635	0.9193
No log	5.0	110	0.2410	0.5143	0.4810	0.4971	0.9293
No log	6.0	132	0.2598	0.5283	0.4612	0.4925	0.9305
No log	7.0	154	0.2963	0.5230	0.4485	0.4829	0.9268
No log	8.0	176	0.2753	0.4928	0.4838	0.4883	0.9283
No log	9.0	198	0.2897	0.5194	0.4725	0.4948	0.9295
No log	10.0	220	0.2930	0.5096	0.4852	0.4971	0.9275

Framework versions

• Transformers 4.18.0
• Pytorch 1.11.0
• Datasets 2.1.0
• Tokenizers 0.12.1