my_model

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: 0.2832
• Accuracy: 0.9321
• F1: 0.9320

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: 3e-05
• train_batch_size: 16
• eval_batch_size: 16
• seed: 42
• optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
• lr_scheduler_type: linear
• lr_scheduler_warmup_steps: 500
• num_epochs: 3
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy	F1
0.3153	0.3199	500	0.3317	0.8600	0.8741
0.2909	0.6398	1000	0.2643	0.9093	0.9132
0.2338	0.9597	1500	0.2143	0.9240	0.9251
0.1484	1.2796	2000	0.2642	0.9231	0.9253
0.1666	1.5995	2500	0.2361	0.9278	0.9265
0.1426	1.9194	3000	0.2391	0.9314	0.9316
0.081	2.2393	3500	0.3034	0.9296	0.9298
0.0764	2.5592	4000	0.2832	0.9321	0.9320
0.0927	2.8791	4500	0.2864	0.9297	0.9310

Framework versions

• Transformers 4.46.2
• Pytorch 2.5.1+cu121
• Datasets 3.1.0
• Tokenizers 0.20.3