nosql-identifier-bert

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: 0.1785
• Accuracy: 0.975

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: 2e-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: 20

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
No log	1.0	40	0.5065	0.9
No log	2.0	80	0.1797	0.975
No log	3.0	120	0.3728	0.8
No log	4.0	160	0.1881	0.925
No log	5.0	200	0.1524	0.95
No log	6.0	240	0.1662	0.9
No log	7.0	280	0.2983	0.9
No log	8.0	320	0.1435	0.975
No log	9.0	360	0.1648	0.975
No log	10.0	400	0.1821	0.975
No log	11.0	440	0.3313	0.95
No log	12.0	480	0.2157	0.95
0.2728	13.0	520	0.3267	0.95
0.2728	14.0	560	0.1715	0.975
0.2728	15.0	600	0.1850	0.975
0.2728	16.0	640	0.2443	0.95
0.2728	17.0	680	0.1755	0.975
0.2728	18.0	720	0.1747	0.975
0.2728	19.0	760	0.1763	0.975
0.2728	20.0	800	0.1785	0.975

Framework versions

• Transformers 4.31.0
• Pytorch 2.0.1+cu118
• Datasets 2.13.1
• Tokenizers 0.11.0