You can deploy this model and start earning money today!

franciscomj0901/
detr-fashionpedia-finetune-francisco

Name: detr-fashionpedia-finetune-francisco
Availability: InStock

generated_from_trainer

franciscomj0901/detr-fashionpedia-finetune-francisco

finetune

apache-2.0

endpoints_compatible

Views

No views yet

detr-fashionpedia-finetune-francisco

This model is a fine-tuned version of franciscomj0901/detr-fashionpedia-finetune-francisco on an unknown dataset. It achieves the following results on the evaluation set:

Loss: 3.5590
Map: 0.0011
Map 50: 0.0033
Map 75: 0.0005
Map Small: 0.001
Map Medium: 0.0017
Map Large: 0.0006
Mar 1: 0.0018
Mar 10: 0.0086
Mar 100: 0.0138
Mar Small: 0.0094
Mar Medium: 0.0181
Mar Large: 0.0231
Map Shirt, blouse: 0.0
Mar 100 Shirt, blouse: 0.0
Map Top, t-shirt, sweatshirt: 0.0
Mar 100 Top, t-shirt, sweatshirt: 0.0
Map Sweater: 0.0
Mar 100 Sweater: 0.0
Map Cardigan: 0.0
Mar 100 Cardigan: 0.0
Map Jacket: 0.0
Mar 100 Jacket: 0.0
Map Vest: 0.0
Mar 100 Vest: 0.0
Map Pants: 0.0
Mar 100 Pants: 0.0
Map Shorts: 0.0
Mar 100 Shorts: 0.0
Map Skirt: 0.0
Mar 100 Skirt: 0.0
Map Coat: 0.0
Mar 100 Coat: 0.0
Map Dress: 0.0
Mar 100 Dress: 0.0
Map Jumpsuit: 0.0
Mar 100 Jumpsuit: 0.0
Map Cape: 0.0
Mar 100 Cape: 0.0
Map Glasses: 0.0
Mar 100 Glasses: 0.0
Map Hat: 0.0
Mar 100 Hat: 0.0
Map Headband, head covering, hair accessory: 0.0
Mar 100 Headband, head covering, hair accessory: 0.0
Map Tie: 0.0
Mar 100 Tie: 0.0
Map Glove: 0.0
Mar 100 Glove: 0.0
Map Watch: 0.0
Mar 100 Watch: 0.0
Map Belt: 0.0
Mar 100 Belt: 0.0
Map Leg warmer: 0.0
Mar 100 Leg warmer: 0.0
Map Tights, stockings: 0.0
Mar 100 Tights, stockings: 0.0
Map Sock: 0.0
Mar 100 Sock: 0.0
Map Shoe: 0.0486
Mar 100 Shoe: 0.3698
Map Bag, wallet: 0.0
Mar 100 Bag, wallet: 0.0
Map Scarf: 0.0
Mar 100 Scarf: 0.0
Map Umbrella: 0.0
Mar 100 Umbrella: 0.0
Map Hood: 0.0
Mar 100 Hood: 0.0
Map Collar: 0.0
Mar 100 Collar: 0.0
Map Lapel: 0.0
Mar 100 Lapel: 0.0
Map Epaulette: 0.0
Mar 100 Epaulette: 0.0
Map Sleeve: 0.0034
Mar 100 Sleeve: 0.253
Map Pocket: 0.0
Mar 100 Pocket: 0.0
Map Neckline: 0.0002
Mar 100 Neckline: 0.0139
Map Buckle: 0.0
Mar 100 Buckle: 0.0
Map Zipper: 0.0
Mar 100 Zipper: 0.0
Map Applique: 0.0
Mar 100 Applique: 0.0
Map Bead: 0.0
Mar 100 Bead: 0.0
Map Bow: 0.0
Mar 100 Bow: 0.0
Map Flower: 0.0
Mar 100 Flower: 0.0
Map Fringe: 0.0
Mar 100 Fringe: 0.0
Map Ribbon: 0.0
Mar 100 Ribbon: 0.0
Map Rivet: 0.0
Mar 100 Rivet: 0.0
Map Ruffle: 0.0
Mar 100 Ruffle: 0.0
Map Sequin: 0.0
Mar 100 Sequin: 0.0
Map Tassel: 0.0
Mar 100 Tassel: 0.0

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: 1e-05
train_batch_size: 4
eval_batch_size: 4
seed: 42
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
training_steps: 500
mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Map	Map 50	Map 75	Map Small	Map Medium	Map Large	Mar 1	Mar 10	Mar 100	Mar Small	Mar Medium	Mar Large	Map Shorts	Mar 100 Shorts	Map Dress	Mar 100 Dress	Map Shoe	Mar 100 Shoe	Map Sleeve	Mar 100 Sleeve	Map Neckline	Mar 100 Neckline
5.5311	0.0044	50	3.9850	0.0005	0.0018	0.0001	0.0006	0.0006	0.0004	0.0008	0.006	0.011	0.0065	0.0149	0.0152	0.0	0.0	0.0	0.0	0.0204	0.3288	0.0027	0.1688	0.0001	0.0066
3.7041	0.0088	100	3.8513	0.0006	0.0018	0.0002	0.0006	0.0008	0.001	0.0009	0.0067	0.0118	0.0091	0.0153	0.0168	0.0001	0.0048	0.0002	0.0002	0.0243	0.3702	0.0027	0.1518	0.0002	0.017
4.358	0.0132	150	3.7499	0.0009	0.0026	0.0005	0.0008	0.001	0.0008	0.0012	0.0074	0.012	0.0085	0.0159	0.0168	0.0	0.0	0.0	0.0	0.0333	0.3502	0.0077	0.1803	0.0002	0.0237
3.9409	0.0175	200	3.6568	0.0008	0.0025	0.0004	0.0008	0.0011	0.0004	0.0011	0.0079	0.0133	0.0096	0.0172	0.02	0.0	0.0	0.0	0.0	0.0334	0.3621	0.0038	0.2232	0.0003	0.025
4.3598	0.0219	250	3.6445	0.0009	0.0028	0.0004	0.001	0.0013	0.0003	0.0013	0.0082	0.0129	0.0095	0.0168	0.0188	0.0	0.0	0.0	0.0	0.0392	0.3739	0.0024	0.2027	0.0005	0.0186
3.8139	0.0263	300	3.6136	0.0011	0.0033	0.0004	0.0011	0.0014	0.0006	0.0017	0.0087	0.0134	0.0092	0.0176	0.0212	0.0	0.0	0.0	0.0	0.0457	0.362	0.0034	0.2283	0.0005	0.0244
3.5465	0.0307	350	3.6114	0.0012	0.0034	0.0005	0.0011	0.0017	0.001	0.0019	0.0082	0.0129	0.0085	0.0171	0.0248	0.0	0.0	0.0	0.0	0.0487	0.3562	0.0046	0.2233	0.0003	0.0137
3.1327	0.0351	400	3.5889	0.0012	0.0035	0.0005	0.0011	0.0017	0.0014	0.0019	0.0085	0.0133	0.0089	0.0175	0.0256	0.0	0.0	0.0	0.0	0.0501	0.3647	0.0034	0.231	0.0003	0.0168
3.8889	0.0395	450	3.5696	0.0011	0.0033	0.0005	0.001	0.0017	0.0006	0.0018	0.0085	0.0137	0.0092	0.018	0.022	0.0	0.0	0.0	0.0	0.0482	0.3676	0.0036	0.2483	0.0002	0.0147
3.9952	0.0438	500	3.5590	0.0011	0.0033	0.0005	0.001	0.0017	0.0006	0.0018	0.0086	0.0138	0.0094	0.0181	0.0231	0.0	0.0	0.0	0.0	0.0486	0.3698	0.0034	0.253	0.0002	0.0139

Framework versions

Transformers 4.51.1
Pytorch 2.6.0+cu124
Datasets 3.5.0
Tokenizers 0.21.1