You can deploy this model and start earning money today!

buddhadeb33/
outputs_dinov3_baseline

Name: outputs_dinov3_baseline
Availability: InStock

Views

No views yet

outputs_dinov3_baseline

This model is a fine-tuned version of facebook/dinov3-vitb16-pretrain-lvd1689m on an unknown dataset. It achieves the following results on the evaluation set:

More information needed

More information needed

More information needed

The following hyperparameters were used during training:

learning_rate: 5e-06
train_batch_size: 4
eval_batch_size: 4
seed: 42
gradient_accumulation_steps: 8
total_train_batch_size: 32
optimizer: Use adamw_torch_fused with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
lr_scheduler_type: linear
lr_scheduler_warmup_steps: 0.1
num_epochs: 10
mixed_precision_training: Native AMP

Training Loss	Epoch	Step	Validation Loss	Precision	Recall	F1
0.4090	1.0	145	0.3883	0.5656	0.6565	0.6077
0.2000	2.0	290	0.2048	0.8247	0.8897	0.8560
0.1257	3.0	435	0.1353	0.9061	0.9422	0.9238
0.1012	4.0	580	0.1013	0.9413	0.9601	0.9506
0.0786	5.0	725	0.0808	0.9481	0.9590	0.9535
0.0676	6.0	870	0.0697	0.9545	0.9706	0.9625
0.0592	7.0	1015	0.0651	0.9553	0.9643	0.9597
0.0486	8.0	1160	0.0599	0.9572	0.9632	0.9602
0.0419	9.0	1305	0.0578	0.9634	0.9664	0.9649
0.0469	10.0	1450	0.0569	0.9613	0.9664	0.9639