learning_rate: 5e-05
train_batch_size: 4
eval_batch_size: 8
seed: 42
optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
lr_scheduler_type: cosine
num_epochs: 30

Training results

Training Loss	Epoch	Step	Validation Loss	Map	Map 50	Map 75	Map Small	Map Medium	Map Large	Mar 1	Mar 10	Mar 100	Mar Small	Mar Medium	Mar Large	Map Banana	Mar 100 Banana	Map Orange	Mar 100 Orange	Map Apple	Mar 100 Apple
No log	1.0	60	2.0522	0.0212	0.0659	0.0094	-1.0	0.0089	0.0224	0.0708	0.1782	0.3389	-1.0	0.1545	0.3583	0.0286	0.47	0.0188	0.1095	0.0163	0.4371
No log	2.0	120	1.3198	0.0567	0.1232	0.051	-1.0	0.0697	0.0631	0.2052	0.3331	0.4683	-1.0	0.2786	0.4856	0.0729	0.635	0.0362	0.0929	0.0609	0.6771
No log	3.0	180	1.2090	0.0921	0.1887	0.0873	-1.0	0.1566	0.0939	0.2567	0.489	0.6513	-1.0	0.5	0.6744	0.0601	0.665	0.1329	0.6119	0.0833	0.6771
No log	4.0	240	1.1433	0.1304	0.2633	0.1009	-1.0	0.2368	0.1273	0.2722	0.5105	0.6946	-1.0	0.5571	0.7147	0.1161	0.7175	0.1069	0.6833	0.1683	0.6829
No log	5.0	300	1.0861	0.2409	0.4113	0.2534	-1.0	0.292	0.2451	0.2862	0.5113	0.6582	-1.0	0.4938	0.6821	0.2332	0.6875	0.1112	0.5071	0.3784	0.78
No log	6.0	360	0.9964	0.3507	0.5542	0.3631	-1.0	0.3617	0.3669	0.3496	0.6003	0.7269	-1.0	0.6009	0.7467	0.3467	0.735	0.1982	0.7	0.5071	0.7457
No log	7.0	420	0.9856	0.3777	0.5941	0.4072	-1.0	0.3972	0.3969	0.3606	0.6248	0.7391	-1.0	0.6723	0.752	0.3275	0.715	0.2587	0.7452	0.5468	0.7571
No log	8.0	480	0.9274	0.4051	0.6384	0.4608	-1.0	0.4151	0.4289	0.3563	0.6106	0.6984	-1.0	0.6018	0.7146	0.3412	0.6875	0.3621	0.7333	0.512	0.6743
1.2211	9.0	540	0.8870	0.4612	0.695	0.4905	-1.0	0.463	0.4856	0.3918	0.6802	0.7621	-1.0	0.6982	0.7759	0.3606	0.72	0.4637	0.7976	0.5594	0.7686
1.2211	10.0	600	0.8816	0.469	0.7295	0.517	-1.0	0.4611	0.4929	0.3873	0.6704	0.7389	-1.0	0.6509	0.7562	0.3453	0.7025	0.4932	0.7857	0.5685	0.7286
1.2211	11.0	660	0.9075	0.4599	0.7067	0.5385	-1.0	0.4542	0.4916	0.3901	0.6846	0.745	-1.0	0.6759	0.7585	0.3281	0.7125	0.5024	0.7738	0.5491	0.7486
1.2211	12.0	720	0.8782	0.4853	0.7556	0.5286	-1.0	0.4689	0.5082	0.3702	0.6625	0.7526	-1.0	0.7009	0.7599	0.3648	0.7625	0.5537	0.781	0.5374	0.7143
1.2211	13.0	780	0.8738	0.491	0.7734	0.5499	-1.0	0.5316	0.503	0.3916	0.6773	0.7592	-1.0	0.6741	0.7742	0.3581	0.7425	0.5286	0.7952	0.5864	0.74
1.2211	14.0	840	0.8793	0.493	0.7751	0.5936	-1.0	0.5263	0.5055	0.3819	0.6716	0.756	-1.0	0.7089	0.765	0.3553	0.735	0.548	0.7786	0.5755	0.7543
1.2211	15.0	900	0.8371	0.5027	0.7757	0.5671	-1.0	0.4608	0.5358	0.399	0.6867	0.7638	-1.0	0.6339	0.786	0.3999	0.7475	0.5337	0.781	0.5744	0.7629
1.2211	16.0	960	0.8566	0.5284	0.8069	0.5912	-1.0	0.5525	0.5405	0.4145	0.6845	0.7696	-1.0	0.6955	0.7844	0.3998	0.7325	0.5825	0.7905	0.6027	0.7857
0.7188	17.0	1020	0.7910	0.5304	0.7815	0.574	-1.0	0.4936	0.5569	0.416	0.7022	0.7851	-1.0	0.7214	0.798	0.3872	0.75	0.5964	0.8167	0.6075	0.7886
0.7188	18.0	1080	0.8336	0.505	0.7819	0.5418	-1.0	0.5167	0.5283	0.4074	0.6834	0.7473	-1.0	0.6929	0.7565	0.3938	0.74	0.5618	0.7905	0.5595	0.7114
0.7188	19.0	1140	0.8551	0.4996	0.7851	0.5691	-1.0	0.5065	0.5234	0.38	0.6858	0.7536	-1.0	0.6911	0.7652	0.3639	0.735	0.5646	0.8	0.5702	0.7257
0.7188	20.0	1200	0.8309	0.5223	0.7834	0.5897	-1.0	0.5131	0.5425	0.4048	0.7008	0.7692	-1.0	0.7	0.782	0.3794	0.7475	0.5757	0.8	0.6117	0.76
0.7188	21.0	1260	0.8022	0.5363	0.802	0.6	-1.0	0.5477	0.5564	0.401	0.7121	0.7752	-1.0	0.7205	0.7852	0.3817	0.76	0.625	0.8	0.6022	0.7657
0.7188	22.0	1320	0.8091	0.5445	0.8377	0.6135	-1.0	0.54	0.561	0.3965	0.6942	0.7648	-1.0	0.6946	0.7754	0.412	0.7725	0.6186	0.7762	0.6028	0.7457
0.7188	23.0	1380	0.8117	0.5285	0.8162	0.5925	-1.0	0.5286	0.5497	0.3983	0.6911	0.7631	-1.0	0.6866	0.7751	0.3787	0.7675	0.617	0.7762	0.5898	0.7457
0.7188	24.0	1440	0.8451	0.5301	0.8114	0.5987	-1.0	0.5389	0.5488	0.3987	0.6968	0.7575	-1.0	0.6938	0.7673	0.3902	0.7625	0.6	0.7643	0.6002	0.7457
0.5518	25.0	1500	0.8227	0.5349	0.8131	0.6017	-1.0	0.5089	0.5567	0.4084	0.7012	0.7649	-1.0	0.6938	0.7759	0.3907	0.77	0.622	0.7762	0.592	0.7486
0.5518	26.0	1560	0.8234	0.5404	0.8185	0.6015	-1.0	0.5242	0.5641	0.4206	0.7018	0.7679	-1.0	0.7125	0.777	0.4001	0.765	0.6289	0.7929	0.5923	0.7457
0.5518	27.0	1620	0.8211	0.5433	0.8203	0.6155	-1.0	0.5298	0.5662	0.4123	0.7098	0.7675	-1.0	0.7063	0.7771	0.4042	0.77	0.6313	0.781	0.5944	0.7514
0.5518	28.0	1680	0.8223	0.542	0.8195	0.602	-1.0	0.5315	0.5642	0.4137	0.7073	0.7681	-1.0	0.7196	0.7759	0.3971	0.7675	0.6313	0.7881	0.5975	0.7486
0.5518	29.0	1740	0.8199	0.5409	0.8174	0.602	-1.0	0.5282	0.563	0.4129	0.7074	0.768	-1.0	0.7205	0.7758	0.3961	0.765	0.6296	0.7905	0.5969	0.7486
0.5518	30.0	1800	0.8192	0.5404	0.8175	0.6018	-1.0	0.5282	0.5624	0.4129	0.7058	0.769	-1.0	0.7205	0.777	0.3949	0.765	0.6297	0.7905	0.5967	0.7514

Framework versions

Transformers 4.57.6
Pytorch 2.9.0+cu128
Datasets 4.0.0
Tokenizers 0.22.2

javillo-ur/yolo_finetuned_fruits

yolo_finetuned_fruits

Model description

Intended uses & limitations

Training and evaluation data

Training procedure

Training hyperparameters

Training results

Framework versions

javillo-ur/
yolo_finetuned_fruits