distilbert-base-uncased-finetuned-intro2-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: 0.0215
• 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
0.6826	1.0	3	0.6074	1.0	1.0
0.5609	2.0	6	0.4800	1.0	1.0
0.4792	3.0	9	0.3545	1.0	1.0
0.3244	4.0	12	0.2644	1.0	1.0
0.2651	5.0	15	0.1861	1.0	1.0
0.1719	6.0	18	0.1314	1.0	1.0
0.1361	7.0	21	0.0975	1.0	1.0
0.092	8.0	24	0.0748	1.0	1.0
0.0714	9.0	27	0.0599	1.0	1.0
0.0487	10.0	30	0.0489	1.0	1.0
0.0425	11.0	33	0.0407	1.0	1.0
0.0341	12.0	36	0.0347	1.0	1.0
0.0304	13.0	39	0.0303	1.0	1.0
0.0262	14.0	42	0.0273	1.0	1.0
0.0244	15.0	45	0.0252	1.0	1.0
0.022	16.0	48	0.0237	1.0	1.0
0.0213	17.0	51	0.0227	1.0	1.0
0.0204	18.0	54	0.0220	1.0	1.0
0.0207	19.0	57	0.0216	1.0	1.0
0.0184	20.0	60	0.0215	1.0	1.0

Framework versions

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