efficientvit_b1.r224_in1k_rice-leaf-disease-augmented-v4_v5_fft

This model is a fine-tuned version of timm/efficientvit_b1.r224_in1k on an unknown dataset. It achieves the following results on the evaluation set:

• Loss: 0.3510
• Accuracy: 0.9295

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: 5e-05
• train_batch_size: 64
• eval_batch_size: 64
• 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: cosine_with_restarts
• lr_scheduler_warmup_steps: 256
• num_epochs: 30
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
1.9816	0.5	64	1.6371	0.4664
1.251	1.0	128	0.8895	0.7685
0.5643	1.5	192	0.5637	0.8289
0.2742	2.0	256	0.2996	0.8993
0.0757	2.5	320	0.2959	0.8993
0.0396	3.0	384	0.2903	0.9094
0.0068	3.5	448	0.2773	0.9094
0.006	4.0	512	0.2828	0.9262
0.0013	4.5	576	0.2868	0.9195
0.0011	5.0	640	0.2861	0.9228
0.0007	5.5	704	0.2996	0.9161
0.0007	6.0	768	0.3003	0.9161
0.0006	6.5	832	0.2892	0.9228
0.0005	7.0	896	0.3072	0.9228
0.0004	7.5	960	0.3035	0.9228
0.0004	8.0	1024	0.3225	0.9161
0.0002	8.5	1088	0.3165	0.9228
0.0002	9.0	1152	0.3208	0.9195
0.0002	9.5	1216	0.3189	0.9161
0.0002	10.0	1280	0.3220	0.9228
0.0001	10.5	1344	0.3292	0.9228
0.0001	11.0	1408	0.3099	0.9295
0.0002	11.5	1472	0.3190	0.9262
0.0002	12.0	1536	0.3183	0.9195
0.0001	12.5	1600	0.3278	0.9228
0.0001	13.0	1664	0.3288	0.9228
0.0001	13.5	1728	0.3251	0.9228
0.0001	14.0	1792	0.3113	0.9228
0.0001	14.5	1856	0.3250	0.9228
0.0001	15.0	1920	0.3085	0.9295
0.0001	15.5	1984	0.3237	0.9295
0.0001	16.0	2048	0.3198	0.9228
0.0001	16.5	2112	0.3232	0.9228
0.0001	17.0	2176	0.3397	0.9195
0.0001	17.5	2240	0.3296	0.9195
0.0001	18.0	2304	0.3459	0.9228
0.0001	18.5	2368	0.3340	0.9262
0.0	19.0	2432	0.3309	0.9295
0.0	19.5	2496	0.3254	0.9262
0.0	20.0	2560	0.3333	0.9262
0.0	20.5	2624	0.3261	0.9262
0.0	21.0	2688	0.3238	0.9262
0.0001	21.5	2752	0.3143	0.9295
0.0	22.0	2816	0.3347	0.9262
0.0	22.5	2880	0.3339	0.9295
0.0	23.0	2944	0.3218	0.9295
0.0	23.5	3008	0.3311	0.9262
0.0	24.0	3072	0.3368	0.9262
0.0	24.5	3136	0.3363	0.9262
0.0	25.0	3200	0.3252	0.9295
0.0	25.5	3264	0.3315	0.9262
0.0	26.0	3328	0.3361	0.9262
0.0	26.5	3392	0.3462	0.9262
0.0	27.0	3456	0.3523	0.9262
0.0	27.5	3520	0.3480	0.9262
0.0	28.0	3584	0.3448	0.9262
0.0	28.5	3648	0.3541	0.9262
0.0	29.0	3712	0.3553	0.9262
0.0	29.5	3776	0.3609	0.9262
0.0	30.0	3840	0.3510	0.9295

Framework versions

• Transformers 4.48.3
• Pytorch 2.5.1+cu124
• Datasets 3.3.2
• Tokenizers 0.21.1