weed_hybrid_transformer

This model is a fine-tuned version of on the imagefolder dataset. It achieves the following results on the evaluation set:

• Loss: 0.1026
• Accuracy: 0.9667

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
• gradient_accumulation_steps: 8
• total_train_batch_size: 16
• 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: 10
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
8.3274	1.0	150	0.8170	0.8233
2.734	2.0	300	0.3290	0.9
2.6813	3.0	450	0.2720	0.9167
1.7794	4.0	600	0.2369	0.9067
1.6344	5.0	750	0.1589	0.9567
1.394	6.0	900	0.1484	0.9533
1.2546	7.0	1050	0.1382	0.9567
1.2253	8.0	1200	0.1565	0.9567
0.7844	9.0	1350	0.1721	0.9433
0.4964	10.0	1500	0.1026	0.9667

Framework versions

• Transformers 4.46.1
• Pytorch 2.5.0+cu124
• Datasets 3.0.2
• Tokenizers 0.20.1