ner-distillbert-ner

This model is a fine-tuned version of distilbert-base-uncased on the None dataset. It achieves the following results on the evaluation set:

• Loss: 0.1179
• Precision: 0.8602
• Recall: 0.8497
• F1: 0.8549
• Accuracy: 0.9707

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: 0.0001
• 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: 10

Training results

Training Loss	Epoch	Step	Validation Loss	Precision	Recall	F1	Accuracy
No log	1.0	13	0.3151	0.3193	0.2684	0.2917	0.8755
No log	2.0	26	0.1966	0.6320	0.4663	0.5366	0.9379
No log	3.0	39	0.1332	0.7932	0.7469	0.7694	0.9608
No log	4.0	52	0.1173	0.8077	0.8313	0.8193	0.9652
No log	5.0	65	0.1093	0.8530	0.8190	0.8357	0.9685
No log	6.0	78	0.1123	0.8383	0.8589	0.8485	0.9676
No log	7.0	91	0.1203	0.8501	0.8436	0.8468	0.9669
No log	8.0	104	0.1165	0.8628	0.8390	0.8507	0.9697
No log	9.0	117	0.1168	0.8585	0.8466	0.8525	0.9701
No log	10.0	130	0.1179	0.8602	0.8497	0.8549	0.9707

Framework versions

• Transformers 4.31.0
• Pytorch 2.0.1+cu118
• Datasets 2.14.4
• Tokenizers 0.13.3