nosql-identifier-distilbert

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

• Loss: 0.1660
• Accuracy: 0.95

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: 15

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
No log	1.0	40	0.4882	0.875
No log	2.0	80	0.2036	0.975
No log	3.0	120	0.1521	0.975
No log	4.0	160	0.2719	0.875
No log	5.0	200	0.0980	0.975
No log	6.0	240	0.1752	0.95
No log	7.0	280	0.3715	0.9
No log	8.0	320	0.1640	0.95
No log	9.0	360	0.1756	0.95
No log	10.0	400	0.1386	0.975
No log	11.0	440	0.2747	0.95
No log	12.0	480	0.2302	0.95
0.2758	13.0	520	0.2518	0.95
0.2758	14.0	560	0.1722	0.95
0.2758	15.0	600	0.1660	0.95

Framework versions

• Transformers 4.31.0
• Pytorch 1.12.1+cu113
• Datasets 2.13.1
• Tokenizers 0.11.0