nlp_te_ner_bert

This model is a fine-tuned version of AmedeoBonatti/nlp_te_mlm_bert on the None dataset. It achieves the following results on the evaluation set:

• Loss: 0.0213
• Precision: 0.9772
• Recall: 0.9831
• F1: 0.9802
• Accuracy: 0.9948

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: 50
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Precision	Recall	F1	Accuracy
No log	1.0	21	0.0227	0.9752	0.9811	0.9781	0.9944
No log	2.0	42	0.0213	0.9772	0.9831	0.9802	0.9948
No log	3.0	63	0.0221	0.9735	0.9806	0.9770	0.9943
No log	4.0	84	0.0250	0.9679	0.9803	0.9741	0.9931
No log	5.0	105	0.0209	0.9752	0.9819	0.9785	0.9944
No log	6.0	126	0.0291	0.9636	0.9796	0.9715	0.9918
No log	7.0	147	0.0266	0.9669	0.9801	0.9735	0.9925

Framework versions

• Transformers 4.41.2
• Pytorch 2.2.1
• Datasets 2.19.2
• Tokenizers 0.19.1