luisgasco/model_ner_master

output-model

This model is a fine-tuned version of answerdotai/ModernBERT-base on an unknown dataset. It achieves the following results on the evaluation set:

• Loss: 0.1590
• F1: 0.3833

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: 5e-05
• train_batch_size: 8
• eval_batch_size: 8
• seed: 52
• gradient_accumulation_steps: 2
• total_train_batch_size: 16
• optimizer: Use OptimizerNames.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: 2

Training results

Training Loss	Epoch	Step	Validation Loss	F1
0.4165	0.1667	50	0.3038	0.0014
0.3627	0.3333	100	0.2643	0.0043
0.2776	0.5	150	0.2914	0.0146
0.229	0.6667	200	0.1869	0.1883
0.1945	0.8333	250	0.1671	0.2568
0.1574	1.0	300	0.1592	0.3238
0.1056	1.1667	350	0.1710	0.4048
0.1117	1.3333	400	0.1657	0.3649
0.117	1.5	450	0.1692	0.3792
0.1176	1.6667	500	0.1604	0.3802
0.0972	1.8333	550	0.1705	0.3515
0.1086	2.0	600	0.1590	0.3833

Framework versions

• Transformers 4.51.3
• Pytorch 2.6.0+cu124
• Datasets 2.14.4
• Tokenizers 0.21.1