255deb6fb82c3af5e23f0bed3d71e557

This model is a fine-tuned version of facebook/opt-6.7b on the contemmcm/clickbait dataset. It achieves the following results on the evaluation set:

• Loss: 0.0258
• Data Size: 1.0
• Epoch Runtime: 277.1203
• 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	1.2841	0	13.5494	0.4034	0.3782
No log	1	650	0.0273	0.0078	16.4261	0.9921	0.9916
No log	2	1300	0.0684	0.0156	29.2699	0.9863	0.9855
No log	3	1950	0.0596	0.0312	43.0631	0.9932	0.9929
No log	4	2600	0.0257	0.0625	59.3080	0.9952	0.9949
0.0085	5	3250	0.0440	0.125	83.4431	0.9782	0.9772
0.1047	6	3900	0.0519	0.25	93.1005	0.9909	0.9904
0.0124	7	4550	0.0125	0.5	157.6172	0.9981	0.9980
0.0036	8.0	5200	0.0154	1.0	292.2171	0.9983	0.9982
0.0045	9.0	5850	0.0144	1.0	272.7130	0.9983	0.9982
0.0303	10.0	6500	0.1112	1.0	272.8443	0.9958	0.9955
0.0	11.0	7150	0.0258	1.0	277.1203	0.9988	0.9988

Framework versions

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