mobilevitv2_150.cvnets_in22k_ft_in1k_rice-leaf-disease-augmented-v4_v5_fft

This model is a fine-tuned version of timm/mobilevitv2_150.cvnets_in22k_ft_in1k on an unknown dataset. It achieves the following results on the evaluation set:

• Loss: 0.5383
• Accuracy: 0.9430

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
2.055	0.5	64	1.8389	0.3255
1.5749	1.0	128	1.1984	0.6544
0.8615	1.5	192	0.6163	0.8289
0.3932	2.0	256	0.3667	0.8993
0.1421	2.5	320	0.3203	0.9195
0.0692	3.0	384	0.3767	0.9295
0.0191	3.5	448	0.3138	0.9262
0.0134	4.0	512	0.3767	0.9295
0.0051	4.5	576	0.3871	0.9329
0.004	5.0	640	0.3701	0.9362
0.0021	5.5	704	0.3781	0.9295
0.0017	6.0	768	0.3713	0.9396
0.0016	6.5	832	0.3613	0.9396
0.0019	7.0	896	0.3690	0.9396
0.0024	7.5	960	0.3852	0.9295
0.0055	8.0	1024	0.3807	0.9463
0.0023	8.5	1088	0.3909	0.9362
0.0014	9.0	1152	0.3748	0.9362
0.0022	9.5	1216	0.3831	0.9430
0.0015	10.0	1280	0.4128	0.9430
0.0004	10.5	1344	0.4138	0.9430
0.0003	11.0	1408	0.3976	0.9430
0.0005	11.5	1472	0.3969	0.9396
0.0014	12.0	1536	0.4213	0.9463
0.0015	12.5	1600	0.4359	0.9497
0.0026	13.0	1664	0.4548	0.9362
0.0006	13.5	1728	0.4389	0.9396
0.0017	14.0	1792	0.4327	0.9430
0.0002	14.5	1856	0.4323	0.9463
0.0001	15.0	1920	0.4006	0.9463
0.0005	15.5	1984	0.4288	0.9430
0.0004	16.0	2048	0.4273	0.9430
0.0022	16.5	2112	0.4271	0.9329
0.0028	17.0	2176	0.5544	0.9195
0.0055	17.5	2240	0.5780	0.9161
0.0015	18.0	2304	0.4965	0.9329
0.0006	18.5	2368	0.4600	0.9295
0.0006	19.0	2432	0.4678	0.9295
0.0002	19.5	2496	0.4572	0.9329
0.0006	20.0	2560	0.4575	0.9362
0.0001	20.5	2624	0.4355	0.9396
0.0001	21.0	2688	0.4640	0.9329
0.0075	21.5	2752	0.5160	0.9362
0.0021	22.0	2816	0.6803	0.9027
0.0052	22.5	2880	0.5313	0.9228
0.0015	23.0	2944	0.4461	0.9430
0.0011	23.5	3008	0.4712	0.9430
0.0011	24.0	3072	0.4789	0.9463
0.001	24.5	3136	0.4763	0.9430
0.0005	25.0	3200	0.4606	0.9497
0.0001	25.5	3264	0.4239	0.9497
0.0028	26.0	3328	0.4507	0.9497
0.0043	26.5	3392	0.4582	0.9396
0.0052	27.0	3456	0.6447	0.9128
0.0026	27.5	3520	0.4954	0.9396
0.0006	28.0	3584	0.5323	0.9362
0.0003	28.5	3648	0.5115	0.9430
0.0003	29.0	3712	0.5272	0.9430
0.0003	29.5	3776	0.5377	0.9497
0.0001	30.0	3840	0.5383	0.9430

Framework versions

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