augmented_model_one

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: 1.1943
• Accuracy: 0.5252
• F1: 0.5265
• Precision: 0.5273
• Recall: 0.5261

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-06
• train_batch_size: 16
• eval_batch_size: 8
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• lr_scheduler_warmup_steps: 500
• num_epochs: 2

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy	F1	Precision	Recall
0.6029	0.1566	500	0.8051	0.6862	0.6782	0.6811	0.6790
0.5909	0.3132	1000	0.7965	0.6884	0.6803	0.6833	0.6811
0.5734	0.4698	1500	0.8022	0.6871	0.6778	0.6793	0.6794
0.5704	0.6264	2000	0.7963	0.6923	0.6829	0.6865	0.6843
0.5378	0.7830	2500	0.8157	0.6949	0.6858	0.6890	0.6871
0.5569	0.9396	3000	0.7976	0.6949	0.6856	0.6878	0.6871
0.51	1.0961	3500	0.8257	0.6958	0.6856	0.6895	0.6874
0.5139	1.2527	4000	0.8201	0.6954	0.6847	0.6889	0.6867

Framework versions

• Transformers 4.41.2
• Pytorch 2.3.0+cu121
• Datasets 2.20.0
• Tokenizers 0.19.1