distilbert-base-uncased-finetuned-intro-verizon2

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: 0.0327
• 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
1.3459	1.0	7	1.2548	0.5814	0.4575
1.1898	2.0	14	1.0488	0.7209	0.6261
1.1052	3.0	21	0.7911	0.7442	0.6506
0.7628	4.0	28	0.5534	1.0	1.0
0.6325	5.0	35	0.3608	1.0	1.0
0.303	6.0	42	0.2387	1.0	1.0
0.2297	7.0	49	0.1626	1.0	1.0
0.1663	8.0	56	0.1152	1.0	1.0
0.1232	9.0	63	0.0866	1.0	1.0
0.1056	10.0	70	0.0683	1.0	1.0
0.0802	11.0	77	0.0572	1.0	1.0
0.0589	12.0	84	0.0497	1.0	1.0
0.0561	13.0	91	0.0445	1.0	1.0
0.0567	14.0	98	0.0404	1.0	1.0
0.0457	15.0	105	0.0376	1.0	1.0
0.0417	16.0	112	0.0357	1.0	1.0
0.0412	17.0	119	0.0344	1.0	1.0
0.0389	18.0	126	0.0335	1.0	1.0
0.04	19.0	133	0.0329	1.0	1.0
0.0394	20.0	140	0.0327	1.0	1.0

Framework versions

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