bert-file-classifier-v1

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: 0.5040
• Accuracy: 0.8621

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: 16
• eval_batch_size: 16
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 25

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
No log	1.0	73	2.9232	0.2379
No log	2.0	146	2.3616	0.4103
No log	3.0	219	1.9274	0.5724
No log	4.0	292	1.6500	0.6793
No log	5.0	365	1.3585	0.7172
No log	6.0	438	1.1529	0.7448
1.8175	7.0	511	0.9884	0.7690
1.8175	8.0	584	0.8728	0.7966
1.8175	9.0	657	0.7990	0.7966
1.8175	10.0	730	0.7191	0.8379
1.8175	11.0	803	0.7060	0.8069
1.8175	12.0	876	0.6388	0.8207
1.8175	13.0	949	0.6215	0.8241
0.4201	14.0	1022	0.6104	0.8310
0.4201	15.0	1095	0.5726	0.8414
0.4201	16.0	1168	0.6273	0.8138
0.4201	17.0	1241	0.4878	0.8655
0.4201	18.0	1314	0.5040	0.8586
0.4201	19.0	1387	0.4873	0.8655
0.4201	20.0	1460	0.5066	0.8655
0.1063	21.0	1533	0.5139	0.8690
0.1063	22.0	1606	0.5060	0.8655
0.1063	23.0	1679	0.4933	0.8690
0.1063	24.0	1752	0.5140	0.8690
0.1063	25.0	1825	0.5040	0.8621

Framework versions

• Transformers 4.42.4
• Pytorch 2.4.0+cu121
• Datasets 2.21.0
• Tokenizers 0.19.1