distilbert-base-uncased-finetuned-intro-verizon

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: 0.0400
• Accuracy: 1.0
• F1: 1.0

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: 64
• eval_batch_size: 64
• 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	F1
0.3753	1.0	3	0.2877	1.0	1.0
0.278	2.0	6	0.2253	1.0	1.0
0.2366	3.0	9	0.1788	1.0	1.0
0.1721	4.0	12	0.1433	1.0	1.0
0.1531	5.0	15	0.1173	1.0	1.0
0.117	6.0	18	0.0980	1.0	1.0
0.108	7.0	21	0.0841	1.0	1.0
0.0916	8.0	24	0.0737	1.0	1.0
0.0843	9.0	27	0.0656	1.0	1.0
0.0701	10.0	30	0.0594	1.0	1.0
0.0683	11.0	33	0.0546	1.0	1.0
0.0599	12.0	36	0.0508	1.0	1.0
0.058	13.0	39	0.0478	1.0	1.0
0.0512	14.0	42	0.0454	1.0	1.0
0.0523	15.0	45	0.0437	1.0	1.0
0.0515	16.0	48	0.0423	1.0	1.0
0.0468	17.0	51	0.0413	1.0	1.0
0.0472	18.0	54	0.0406	1.0	1.0
0.0479	19.0	57	0.0401	1.0	1.0
0.0474	20.0	60	0.0400	1.0	1.0

Framework versions

• Transformers 4.16.2
• Pytorch 2.1.0+cu121
• Datasets 2.18.0
• Tokenizers 0.15.2