segformer-head-o1

This model is a fine-tuned version of nvidia/mit-b0 on the adwardnguyen/face-ds dataset. It achieves the following results on the evaluation set:

• Loss: 0.3261

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: 2e-05
• train_batch_size: 2
• eval_batch_size: 2
• 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
• num_epochs: 100

Training results

Training Loss	Epoch	Step	Validation Loss
0.3651	20.0	20	0.3729
0.3151	40.0	40	0.3654
0.3046	60.0	60	0.3283
0.2971	80.0	80	0.3217
0.3179	100.0	100	0.3261

Framework versions

• Transformers 4.48.3
• Pytorch 2.6.0
• Datasets 3.2.0
• Tokenizers 0.21.0