distilbert-classn-baseline – AI Model by Heather-Driver | AlphaNeural AI

You can deploy this model and start earning money today!

Heather-Driver/
distilbert-classn-baseline

like

0

generated_from_trainer

dslim/distilbert-NER

endpoints_compatible

Views

No views yet

distilbert-classn-baseline

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

Loss: 2.4487
Accuracy: 0.1190
F1: 0.0535
Precision: 0.0637
Recall: 0.1190

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: 1e-06
train_batch_size: 32
eval_batch_size: 32
seed: 42
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
lr_scheduler_warmup_steps: 2000
num_epochs: 25
mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy	F1	Precision	Recall
2.4574	5.0	50	2.4781	0.0952	0.0236	0.0157	0.0952
2.4705	10.0	100	2.4746	0.0952	0.0236	0.0157	0.0952
2.4716	15.0	150	2.4685	0.0952	0.0241	0.0168	0.0952
2.4688	20.0	200	2.4597	0.1111	0.0451	0.0452	0.1111
2.4659	25.0	250	2.4487	0.1190	0.0535	0.0637	0.1190

Framework versions

Transformers 4.48.3
Pytorch 2.5.1+cu124
Datasets 3.3.2
Tokenizers 0.21.0