textclassifier_requesttype_v1AndAugV1_distilbert-base-uncased

This model is a fine-tuned version of distilbert/distilbert-base-uncased on an unknown dataset. It achieves the following results on the evaluation set:

• Loss: 0.6438
• Accuracy: 0.8803

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: 0.0001
• train_batch_size: 32
• eval_batch_size: 32
• seed: 42
• optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
• lr_scheduler_type: linear
• num_epochs: 20

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
1.7146	1.0	15	1.0728	0.7350
0.8748	2.0	30	0.7251	0.8034
0.5424	3.0	45	0.6366	0.8376
0.3699	4.0	60	0.5454	0.8718
0.295	5.0	75	0.5586	0.8291
0.2477	6.0	90	0.6698	0.8547
0.2415	7.0	105	0.5848	0.8291
0.2208	8.0	120	0.5794	0.8462
0.1951	9.0	135	0.5879	0.8889
0.2019	10.0	150	0.6363	0.8376
0.1861	11.0	165	0.6340	0.8376
0.1717	12.0	180	0.6194	0.8462
0.1742	13.0	195	0.6236	0.8889
0.1518	14.0	210	0.6250	0.8462
0.1607	15.0	225	0.6214	0.8803
0.1561	16.0	240	0.6374	0.8803
0.1408	17.0	255	0.6549	0.8462
0.1427	18.0	270	0.6475	0.8803
0.1318	19.0	285	0.6437	0.8803
0.1383	20.0	300	0.6438	0.8803

Framework versions

• Transformers 4.47.1
• Pytorch 2.5.1+cu121
• Datasets 3.2.0
• Tokenizers 0.21.0