delivery-range-distilbert-base-uncased

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

• Loss: 0.8847
• Accuracy: 0.7895

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: 70
• eval_batch_size: 70
• 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	Accuracy
No log	1.0	4	0.6916	0.4737
No log	2.0	8	0.6498	0.6711
No log	3.0	12	0.6176	0.6711
No log	4.0	16	0.5565	0.75
No log	5.0	20	0.5144	0.7763
No log	6.0	24	0.5000	0.75
No log	7.0	28	0.4871	0.7763
No log	8.0	32	0.5156	0.7632
No log	9.0	36	0.4752	0.7632
No log	10.0	40	0.5275	0.7763
No log	11.0	44	0.5372	0.7632
No log	12.0	48	0.5400	0.75
No log	13.0	52	0.5988	0.7632
No log	14.0	56	0.5852	0.7763
No log	15.0	60	0.6477	0.8026
No log	16.0	64	0.6769	0.7895
No log	17.0	68	0.7157	0.7895
No log	18.0	72	0.7398	0.7763
No log	19.0	76	0.7651	0.7763
No log	20.0	80	0.7922	0.7895
No log	21.0	84	0.8137	0.7895
No log	22.0	88	0.8256	0.7895
No log	23.0	92	0.8343	0.7763
No log	24.0	96	0.8493	0.7763
No log	25.0	100	0.8650	0.7895
No log	26.0	104	0.8728	0.7895
No log	27.0	108	0.8789	0.7895
No log	28.0	112	0.8826	0.7895
No log	29.0	116	0.8841	0.7895
No log	30.0	120	0.8847	0.7895

Framework versions

• Transformers 4.42.4
• Pytorch 2.3.0
• Datasets 2.20.0
• Tokenizers 0.19.1