838d600dff1f5aa55bca8a8ba06f3f1a

This model is a fine-tuned version of FacebookAI/roberta-base on the contemmcm/clickbait dataset. It achieves the following results on the evaluation set:

• Loss: 0.0080
• Data Size: 1.0
• Epoch Runtime: 52.1097
• Accuracy: 0.9988
• F1 Macro: 0.9988

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: 5e-05
• train_batch_size: 8
• eval_batch_size: 8
• seed: 42
• distributed_type: multi-GPU
• num_devices: 4
• total_train_batch_size: 32
• total_eval_batch_size: 32
• optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
• lr_scheduler_type: constant
• num_epochs: 50

Training results

Training Loss	Epoch	Step	Validation Loss	Data Size	Epoch Runtime	Accuracy	F1 Macro
No log	0	0	0.7261	0	4.4722	0.3870	0.2790
No log	1	650	0.3346	0.0078	5.0886	0.8191	0.7831
No log	2	1300	0.0093	0.0156	5.4533	0.9983	0.9982
No log	3	1950	0.0075	0.0312	6.1815	0.9988	0.9988
No log	4	2600	0.0030	0.0625	7.5568	0.9988	0.9988
0.0025	5	3250	0.0129	0.125	10.6526	0.9977	0.9976
0.0041	6	3900	0.0105	0.25	16.7884	0.9985	0.9984
0.001	7	4550	0.0138	0.5	28.4110	0.9977	0.9976
0.0106	8.0	5200	0.0080	1.0	52.1097	0.9988	0.9988

Framework versions

• Transformers 4.57.0
• Pytorch 2.8.0+cu128
• Datasets 4.3.0
• Tokenizers 0.22.1