45ba03f61c3a313c63f6f8d3e836f016

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

• Loss: 0.6741
• Data Size: 1.0
• Epoch Runtime: 99.6155
• Accuracy: 0.6130
• F1 Macro: 0.3801

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	0.7850	0	7.5705	0.3870	0.2790
No log	1	650	0.3546	0.0078	8.4128	0.6171	0.3914
No log	2	1300	0.0167	0.0156	9.3408	0.9952	0.9949
No log	3	1950	0.0341	0.0312	11.6021	0.9936	0.9933
No log	4	2600	0.0106	0.0625	15.2132	0.9985	0.9984
0.0042	5	3250	0.0077	0.125	20.8617	0.9986	0.9986
0.0116	6	3900	0.0124	0.25	32.6704	0.9985	0.9984
0.6703	7	4550	0.6714	0.5	56.3448	0.6130	0.3801
0.6773	8.0	5200	0.6689	1.0	100.8855	0.6130	0.3801
0.6658	9.0	5850	0.6741	1.0	99.6155	0.6130	0.3801

Framework versions

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