distilbert-sql-timeout-classifier-with-trained-tokenizer

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

• Loss: 0.4898
• Recall: 0.7370
• Precision: 0.1526
• Affect Rate: 0.1164
• Accuracy: 0.8761

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: 4
• eval_batch_size: 4
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 3

Training results

Training Loss	Epoch	Step	Validation Loss	Recall	Precision	Affect Rate	Accuracy
0.5018	1.0	1946	0.3744	0.6929	0.1758	0.0924	0.8988
0.3196	2.0	3892	0.4938	0.7390	0.1294	0.1414	0.8512
0.2219	3.0	5838	0.4898	0.7370	0.1526	0.1164	0.8761

Framework versions

• Transformers 4.38.1
• Pytorch 2.2.1+cu121
• Datasets 2.17.1
• Tokenizers 0.15.2