efficientformerv2_s2.snap_dist_in1k_rice-leaf-disease-augmented-v4_v5_fft

This model is a fine-tuned version of timm/efficientformerv2_s2.snap_dist_in1k on an unknown dataset. It achieves the following results on the evaluation set:

• Loss: nan
• Accuracy: 0.8993

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
2.0995	0.5	64	2.0753	0.1174
2.0825	1.0	128	2.0116	0.2013
2.0406	1.5	192	1.8152	0.3423
1.9782	2.0	256	1.5436	0.4597
1.8312	2.5	320	1.3972	0.4765
1.6587	3.0	384	1.0460	0.5940
1.4276	3.5	448	0.8714	0.6376
1.2866	4.0	512	0.5099	0.7148
1.1507	4.5	576	0.3888	0.7752
1.0403	5.0	640	0.3584	0.7651
0.9713	5.5	704	0.3522	0.7785
0.9401	6.0	768	0.3506	0.7819
0.925	6.5	832	0.3350	0.7752
0.896	7.0	896	0.3345	0.7785
0.7789	7.5	960	0.3356	0.7987
0.639	8.0	1024	0.3140	0.8255
0.5212	8.5	1088	0.3001	0.8221
0.4837	9.0	1152	0.3199	0.8356
0.3967	9.5	1216	0.3303	0.8691
0.3852	10.0	1280	0.3323	0.8591
0.3442	10.5	1344	0.3377	0.8624
0.3496	11.0	1408	0.3329	0.8691
0.3327	11.5	1472	0.3660	0.8624
0.3082	12.0	1536	0.3451	0.8691
0.25	12.5	1600	0.3837	0.8792
0.2132	13.0	1664	0.3951	0.8926
0.1665	13.5	1728	0.4049	0.8826
0.1471	14.0	1792	0.3848	0.8758
0.1201	14.5	1856	0.3778	0.8792
0.1093	15.0	1920	0.3634	0.8792
0.1067	15.5	1984	0.3815	0.8826
0.1031	16.0	2048	0.3750	0.8826
0.0947	16.5	2112	0.3782	0.8926
0.0884	17.0	2176	0.4048	0.8926
0.0694	17.5	2240	0.3917	0.8792
0.0586	18.0	2304	0.4254	0.8792
0.0514	18.5	2368	0.4199	0.8893
0.0386	19.0	2432	0.4236	0.8926
0.0385	19.5	2496	0.4127	0.8859
0.0404	20.0	2560	0.4166	0.8859
0.0346	20.5	2624	0.4047	0.8926
0.0333	21.0	2688	0.4339	0.8893
0.0284	21.5	2752	0.4248	0.8859
0.0286	22.0	2816	0.4503	0.9094
0.024	22.5	2880	0.4578	0.8893
0.0205	23.0	2944	0.4262	0.9060
0.0192	23.5	3008	0.4398	0.8826
0.0158	24.0	3072	0.4416	0.8926
0.0129	24.5	3136	0.4419	0.8993
0.014	25.0	3200	0.4412	0.9027
0.0132	25.5	3264	0.4470	0.8926
0.0121	26.0	3328	0.4364	0.9128
0.0146	26.5	3392	0.4252	0.8893
0.0123	27.0	3456	0.4499	0.8893
0.0133	27.5	3520	0.4494	0.8893
0.0085	28.0	3584	0.4469	0.8960
0.0092	28.5	3648	0.4245	0.9060
0.0101	29.0	3712	0.4433	0.9094
0.0107	29.5	3776	0.4493	0.9094
0.0077	30.0	3840	0.4336	0.8993

Framework versions

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