519aa19bb7de7eeecc1d503e2d29ac3f

This model is a fine-tuned version of facebook/opt-1.3b on the contemmcm/clickbait dataset. It achieves the following results on the evaluation set:

• Loss: 0.0692
• Data Size: 0.125
• Epoch Runtime: 25.5774
• Accuracy: 0.9882
• F1 Macro: 0.9877

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	1.4096	0	8.4030	0.2604	0.2219
No log	1	650	0.0089	0.0078	9.0860	0.9971	0.9969
No log	2	1300	0.0132	0.0156	11.5094	0.9977	0.9976
No log	3	1950	0.1661	0.0312	14.2996	0.9693	0.9681
No log	4	2600	0.5877	0.0625	19.0070	0.9504	0.9488
0.0051	5	3250	0.0692	0.125	25.5774	0.9882	0.9877

Framework versions

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