fancy-plant-219

This model is a fine-tuned version of facebook/convnextv2-tiny-1k-224 on an unknown dataset. It achieves the following results on the evaluation set:

• Loss: 0.0531
• Accuracy: 0.9805
• Precision: 0.9805
• Recall: 0.9805
• F1: 0.9805
• Roc Auc: 0.9974

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: 0.0001
• train_batch_size: 256
• eval_batch_size: 256
• 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
• lr_scheduler_warmup_ratio: 0.1
• num_epochs: 50

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy	Precision	Recall	F1	Roc Auc
1.3945	1.0	17	1.4430	0.4779	0.4233	0.4779	0.4381	0.6365
1.3203	2.0	34	1.2260	0.4049	0.5854	0.4049	0.4639	0.7864
1.1476	3.0	51	0.9415	0.5677	0.5641	0.5677	0.5634	0.8224
0.8622	4.0	68	0.6177	0.6133	0.6349	0.6133	0.6032	0.8612
0.7741	5.0	85	0.6050	0.5964	0.5937	0.5964	0.5373	0.8716
0.6872	6.0	102	0.4559	0.6536	0.7085	0.6536	0.6351	0.9020
0.5383	7.0	119	0.3990	0.7227	0.7441	0.7227	0.7034	0.9283
0.4257	8.0	136	0.2967	0.7643	0.8000	0.7643	0.7658	0.9521
0.3358	9.0	153	0.2559	0.8086	0.8325	0.8086	0.8089	0.9608
0.2355	10.0	170	0.1693	0.8958	0.8956	0.8958	0.8950	0.9789
0.1634	11.0	187	0.1659	0.8945	0.8979	0.8945	0.8950	0.9826
0.112	12.0	204	0.2273	0.8320	0.8777	0.8320	0.8334	0.9880
0.1065	13.0	221	0.1733	0.8984	0.9139	0.8984	0.8966	0.9901
0.1051	14.0	238	0.1226	0.9258	0.9298	0.9258	0.9245	0.9934
0.056	15.0	255	0.0664	0.9479	0.9499	0.9479	0.9481	0.9959
0.0501	16.0	272	0.0804	0.9531	0.9532	0.9531	0.9532	0.9960
0.0306	17.0	289	0.0784	0.9557	0.9563	0.9557	0.9556	0.9960
0.0315	18.0	306	0.0870	0.9648	0.9652	0.9648	0.9647	0.9968
0.0263	19.0	323	0.0637	0.9622	0.9624	0.9622	0.9623	0.9972
0.0259	20.0	340	0.0949	0.9479	0.9505	0.9479	0.9479	0.9945
0.0171	21.0	357	0.0903	0.9596	0.9601	0.9596	0.9594	0.9952
0.0236	22.0	374	0.0777	0.9714	0.9717	0.9714	0.9713	0.9962
0.0295	23.0	391	0.0733	0.9648	0.9664	0.9648	0.9650	0.9977
0.0143	24.0	408	0.0790	0.9701	0.9705	0.9701	0.9701	0.9967
0.0116	25.0	425	0.0849	0.9635	0.9637	0.9635	0.9634	0.9974
0.0079	26.0	442	0.0496	0.9792	0.9794	0.9792	0.9792	0.9978
0.0111	27.0	459	0.0382	0.9805	0.9806	0.9805	0.9805	0.9977
0.0097	28.0	476	0.0456	0.9792	0.9792	0.9792	0.9792	0.9971
0.004	29.0	493	0.0628	0.9766	0.9769	0.9766	0.9765	0.9970
0.0089	30.0	510	0.0584	0.9766	0.9768	0.9766	0.9765	0.9966
0.0035	31.0	527	0.0527	0.9792	0.9792	0.9792	0.9792	0.9982
0.007	32.0	544	0.0531	0.9805	0.9805	0.9805	0.9805	0.9974

Framework versions

• Transformers 4.52.3
• Pytorch 2.7.0+cpu
• Datasets 3.6.0
• Tokenizers 0.21.0