products-ner

This model is a fine-tuned version of distilbert-base-uncased on the ner dataset. It achieves the following results on the evaluation set:

• Loss: 0.1747
• Precision: 0.8187
• Recall: 0.8563
• F1: 0.8371
• Accuracy: 0.9533

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: 8

Training results

Training Loss	Epoch	Step	Validation Loss	Precision	Recall	F1	Accuracy
No log	1.0	30	0.7395	0.3421	0.3736	0.3571	0.7897
No log	2.0	60	0.4036	0.5842	0.6782	0.6277	0.8863
No log	3.0	90	0.2716	0.7105	0.7759	0.7418	0.9174
No log	4.0	120	0.2286	0.7433	0.7989	0.7701	0.9315
No log	5.0	150	0.2093	0.7760	0.8161	0.7955	0.9377
No log	6.0	180	0.1890	0.7796	0.8333	0.8056	0.9455
No log	7.0	210	0.1772	0.8197	0.8621	0.8403	0.9533
No log	8.0	240	0.1747	0.8187	0.8563	0.8371	0.9533

Framework versions

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