d0baa94eb581d1d1a3022ff3c4e22617

This model is a fine-tuned version of facebook/opt-125m on the contemmcm/clickbait dataset. It achieves the following results on the evaluation set:

• Loss: 0.0112
• Data Size: 0.125
• Epoch Runtime: 10.5442
• Accuracy: 0.9983
• F1 Macro: 0.9982

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	0.8769	0	4.8696	0.5461	0.3928
No log	1	650	0.0085	0.0078	5.3183	0.9981	0.9980
No log	2	1300	0.0101	0.0156	5.6256	0.9977	0.9976
No log	3	1950	0.0273	0.0312	6.2685	0.9956	0.9953
No log	4	2600	0.1044	0.0625	7.7756	0.9865	0.9859
0.001	5	3250	0.0112	0.125	10.5442	0.9983	0.9982

Framework versions

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