distilbert-q-classifier-2

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

• Loss: 0.2779
• Accuracy: 0.9421
• Precision Weighted: 0.9429
• Recall Weighted: 0.9421
• F1 Weighted: 0.9421
• Precision Macro: 0.9429
• Recall Macro: 0.9421
• F1 Macro: 0.9421

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: 32
• eval_batch_size: 32
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 10

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy	Precision Weighted	Recall Weighted	F1 Weighted	Precision Macro	Recall Macro	F1 Macro
No log	1.0	48	0.2252	0.9144	0.9144	0.9144	0.9144	0.9144	0.9144	0.9144
No log	2.0	96	0.1682	0.9329	0.9333	0.9329	0.9329	0.9333	0.9329	0.9329
No log	3.0	144	0.2251	0.9236	0.9269	0.9236	0.9235	0.9269	0.9236	0.9235
No log	4.0	192	0.2421	0.9352	0.9376	0.9352	0.9351	0.9376	0.9352	0.9351
No log	5.0	240	0.2138	0.9375	0.9383	0.9375	0.9375	0.9383	0.9375	0.9375
No log	6.0	288	0.2165	0.9398	0.9399	0.9398	0.9398	0.9399	0.9398	0.9398
No log	7.0	336	0.2470	0.9398	0.9408	0.9398	0.9398	0.9408	0.9398	0.9398
No log	8.0	384	0.2509	0.9352	0.9353	0.9352	0.9352	0.9353	0.9352	0.9352
No log	9.0	432	0.2686	0.9352	0.9355	0.9352	0.9352	0.9355	0.9352	0.9352
No log	10.0	480	0.2779	0.9421	0.9429	0.9421	0.9421	0.9429	0.9421	0.9421

Framework versions

• Transformers 4.43.3
• Pytorch 2.3.1
• Datasets 2.20.0
• Tokenizers 0.19.1