bert-base-cased-frozen-products

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

• Loss: 2.0238

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: 4e-05
• train_batch_size: 8
• eval_batch_size: 8
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 24

Training results

Training Loss	Epoch	Step	Validation Loss
7.3395	1.0	7595	6.7409
6.2816	2.0	15190	5.7289
5.312	3.0	22785	4.7987
4.4559	4.0	30380	4.0777
3.7808	5.0	37975	3.5203
3.2595	6.0	45570	3.1239
2.8609	7.0	53165	2.8283
2.5543	8.0	60760	2.6288
2.3194	9.0	68355	2.4725
2.1317	10.0	75950	2.3666
1.9875	11.0	83545	2.2859
1.8649	12.0	91140	2.2228
1.768	13.0	98735	2.1756
1.6863	14.0	106330	2.1330
1.6149	15.0	113925	2.1085
1.5559	16.0	121520	2.0842
1.5044	17.0	129115	2.0717
1.4593	18.0	136710	2.0534
1.4245	19.0	144305	2.0440
1.3923	20.0	151900	2.0365
1.3629	21.0	159495	2.0314
1.3446	22.0	167090	2.0271
1.3275	23.0	174685	2.0237
1.316	24.0	182280	2.0238

Framework versions

• Transformers 4.41.2
• Pytorch 2.3.0.post100
• Datasets 2.19.1
• Tokenizers 0.19.1