bert-base-uncased-pp-1000-1e-06-8

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

• Loss: 0.6942

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: 1024
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 30

Training results

Training Loss	Epoch	Step	Validation Loss
No log	1.0	32	0.7053
No log	2.0	64	0.7014
No log	3.0	96	0.6994
No log	4.0	128	0.6983
No log	5.0	160	0.6972
No log	6.0	192	0.6967
0.6995	7.0	224	0.6959
0.6995	8.0	256	0.6955
0.6995	9.0	288	0.6953
0.6995	10.0	320	0.6951
0.6995	11.0	352	0.6949
0.6995	12.0	384	0.6948
0.69	13.0	416	0.6946
0.69	14.0	448	0.6945
0.69	15.0	480	0.6945
0.69	16.0	512	0.6944
0.69	17.0	544	0.6943
0.69	18.0	576	0.6942
0.6839	19.0	608	0.6943
0.6839	20.0	640	0.6943
0.6839	21.0	672	0.6943

Framework versions

• Transformers 4.44.2
• Pytorch 2.4.0+cu121
• Datasets 2.21.0
• Tokenizers 0.19.1