heladepdet-bert-finetuned-classification – AI Model by tadamaen | AlphaNeural AI

You can deploy this model and start earning money today!

tadamaen/
heladepdet-bert-finetuned-classification

like

0

google-bert/bert-base-cased

Views

No views yet

Visualize in Trackio

heladepdet-bert-finetuned-classification

This model is a fine-tuned version of google-bert/bert-base-cased on the None dataset. It achieves the following results on the evaluation set:

Loss: 1.2607
Accuracy: 0.7084

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: 32
eval_batch_size: 32
seed: 42
optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
lr_scheduler_type: linear
num_epochs: 5

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
2.5972	0.5734	250	2.1673	0.5408
1.8338	1.1468	500	1.5411	0.6361
1.5037	1.7202	750	1.4124	0.6670
1.4176	2.2936	1000	1.3331	0.6871
1.3283	2.8670	1250	1.3027	0.6969
1.3123	3.4404	1500	1.2863	0.6940
1.2613	4.0138	1750	1.2653	0.7067
1.2477	4.5872	2000	1.2607	0.7084

Framework versions

PEFT 0.18.1
Transformers 5.0.0
Pytorch 2.10.0+cu128
Datasets 4.8.3
Tokenizers 0.22.2