augmented_model_one_no_decay

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: 1.1143
• Accuracy: 0.5579
• F1: 0.5593
• Precision: 0.5630
• Recall: 0.5577

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: 32
• 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
0.7227	0.2088	500	0.7164	0.7085	0.6956	0.7019	0.6986
0.669	0.4175	1000	0.7047	0.7168	0.7060	0.7126	0.7080
0.6417	0.6263	1500	0.7017	0.7146	0.7066	0.7115	0.7077
0.6274	0.8351	2000	0.6977	0.7220	0.7124	0.7172	0.7139
0.6082	1.0438	2500	0.6994	0.7212	0.7134	0.7167	0.7142
0.5766	1.2526	3000	0.7056	0.7168	0.7077	0.7113	0.7090
0.5789	1.4614	3500	0.7004	0.7220	0.7149	0.7185	0.7155
0.578	1.6701	4000	0.7030	0.7247	0.7151	0.7191	0.7165
0.5743	1.8789	4500	0.7008	0.7233	0.7144	0.7174	0.7156

Framework versions

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