distilbert-ner

This model is a fine-tuned version of distilbert-base-uncased on an unknown dataset.

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

Training results

Training Loss	Epoch	Step	Validation Loss	Precision	Recall	F1	Accuracy
No log	1.0	45	1.5295	0.2627	0.0223	0.0411	0.6639
No log	2.0	90	1.2463	0.3241	0.2831	0.3022	0.6845
No log	3.0	135	1.0915	0.3560	0.4052	0.3790	0.7005
No log	4.0	180	0.9411	0.5225	0.3180	0.3954	0.7428
No log	5.0	225	0.8653	0.4437	0.5304	0.4832	0.7580
No log	6.0	270	0.7936	0.4913	0.5362	0.5128	0.7798
No log	7.0	315	0.7715	0.4974	0.5623	0.5279	0.7840
No log	8.0	360	0.7545	0.5083	0.5601	0.5329	0.7880
No log	9.0	405	0.7464	0.5125	0.5694	0.5395	0.7921
No log	10.0	450	0.7475	0.5070	0.5725	0.5377	0.7903

Framework versions

• Transformers 4.35.2
• Pytorch 2.1.0+cu121
• Datasets 2.15.0
• Tokenizers 0.15.0