This model is a fine-tuned version of google-bert/bert-base-uncased on the biobert_json dataset. It achieves the following results on the evaluation set:

Loss: 0.1111
Precision: 0.9299
Recall: 0.9513
F1: 0.9405
Accuracy: 0.9771

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: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
lr_scheduler_type: linear
num_epochs: 10

Training results

Training Loss	Epoch	Step	Validation Loss	Precision	Recall	F1	Accuracy
0.4331	1.0	612	0.1091	0.8914	0.9413	0.9156	0.9713
0.1313	2.0	1224	0.1077	0.8941	0.9494	0.9209	0.9718
0.0869	3.0	1836	0.0888	0.9308	0.9555	0.9430	0.9786
0.0726	4.0	2448	0.0957	0.9253	0.9578	0.9413	0.9767
0.0507	5.0	3060	0.0936	0.9287	0.9554	0.9419	0.9770
0.0451	6.0	3672	0.1051	0.9276	0.9538	0.9405	0.9762
0.0383	7.0	4284	0.1038	0.9218	0.9576	0.9394	0.9760
0.036	8.0	4896	0.1094	0.9245	0.9533	0.9387	0.9765
0.0284	9.0	5508	0.1082	0.9296	0.9516	0.9404	0.9768
0.0256	10.0	6120	0.1111	0.9299	0.9513	0.9405	0.9771

Framework versions

Transformers 4.46.2
Pytorch 2.5.1+cu121
Datasets 3.1.0
Tokenizers 0.20.3

cristianmanosalva/NER-finetuning-BBU-CM-V1

NER-finetuning-BBU-CM-V1

Model description

Intended uses & limitations

Training and evaluation data

Training procedure

Training hyperparameters

Training results

Framework versions

cristianmanosalva/
NER-finetuning-BBU-CM-V1