celebrity-classifier-alpha-2

This model was trained on tonyassi/celebrity-1000 dataset using flxowens/celebrity-classifier-alpha-1 as a base. It achieves the following results on the evaluation set:

• Loss: 1.1460
• Accuracy: 0.8155

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: 0.0001
• train_batch_size: 64
• eval_batch_size: 64
• seed: 42
• gradient_accumulation_steps: 4
• total_train_batch_size: 256
• optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
• lr_scheduler_type: linear
• lr_scheduler_warmup_ratio: 0.1
• num_epochs: 30

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
3.1688	1.0	57	3.2075	0.6368
3.1011	2.0	114	3.1265	0.6516
2.9635	3.0	171	2.9998	0.6582
2.7566	4.0	228	2.8278	0.6483
2.627	5.0	285	2.6790	0.6714
2.4471	6.0	342	2.5465	0.6761
2.2209	7.0	399	2.3950	0.6915
2.065	8.0	456	2.2217	0.7182
1.8663	9.0	513	2.1201	0.7190
1.7552	10.0	570	2.0301	0.7239
1.6236	11.0	627	1.9579	0.7294
1.4972	12.0	684	1.8372	0.7435
1.4122	13.0	741	1.7470	0.7503
1.3002	14.0	798	1.6856	0.7534
1.2374	15.0	855	1.5974	0.7718
1.1495	16.0	912	1.5241	0.7787
1.103	17.0	969	1.4876	0.7721
1.0296	18.0	1026	1.4428	0.7789
1.0221	19.0	1083	1.3996	0.7899
0.9271	20.0	1140	1.3016	0.8084
0.8718	21.0	1197	1.3076	0.7998
0.8373	22.0	1254	1.3225	0.7891
0.8346	23.0	1311	1.2529	0.8007
0.7973	24.0	1368	1.1711	0.8188
0.794	25.0	1425	1.1997	0.8084
0.7688	26.0	1482	1.1541	0.8174
0.7452	27.0	1539	1.1727	0.8133
0.7457	28.0	1596	1.1591	0.8122
0.7496	29.0	1653	1.1205	0.8177
0.707	30.0	1710	1.1460	0.8155

Framework versions

• Transformers 4.46.3
• Pytorch 2.5.1+cu124
• Datasets 3.1.0
• Tokenizers 0.20.3