learning_rate: 5e-05
train_batch_size: 4
eval_batch_size: 8
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
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	1.9249	0.0109	0.0354	0.0052	-1.0	0.0329	0.0109	0.0335	0.1437	0.2863	-1.0	0.2843	0.2869	0.0046	0.34	0.0094	0.219	0.0186	0.3
No log	2.0	120	1.7552	0.0307	0.0686	0.027	-1.0	0.1317	0.0312	0.1155	0.2331	0.3925	-1.0	0.3071	0.4029	0.018	0.5075	0.0175	0.15	0.0566	0.52
No log	3.0	180	1.5625	0.0389	0.0978	0.0255	-1.0	0.0548	0.0447	0.1446	0.2812	0.4478	-1.0	0.2757	0.467	0.051	0.57	0.0204	0.2619	0.0452	0.5114
No log	4.0	240	1.6910	0.0592	0.1271	0.0474	-1.0	0.1825	0.0515	0.1635	0.2915	0.4286	-1.0	0.3357	0.4442	0.0439	0.44	0.0721	0.2714	0.0615	0.5743
No log	5.0	300	1.4597	0.0665	0.1389	0.0556	-1.0	0.2186	0.0554	0.1602	0.362	0.4977	-1.0	0.4129	0.5089	0.0538	0.5425	0.0681	0.319	0.0776	0.6314
No log	6.0	360	1.2406	0.0908	0.1801	0.0701	-1.0	0.2087	0.0898	0.2304	0.4411	0.6045	-1.0	0.4443	0.6203	0.0807	0.675	0.0816	0.4929	0.1101	0.6457
No log	7.0	420	1.2385	0.108	0.1981	0.098	-1.0	0.296	0.1089	0.292	0.4907	0.604	-1.0	0.5186	0.6145	0.0613	0.6325	0.097	0.4167	0.1658	0.7629
No log	8.0	480	1.1481	0.1272	0.2265	0.1263	-1.0	0.3262	0.1267	0.3307	0.5254	0.6662	-1.0	0.6186	0.6759	0.0771	0.5875	0.1323	0.7024	0.1721	0.7086
1.4397	9.0	540	1.0555	0.1758	0.304	0.1975	-1.0	0.4053	0.1713	0.3339	0.5702	0.7069	-1.0	0.6614	0.7126	0.1352	0.6725	0.1431	0.7024	0.2491	0.7457
1.4397	10.0	600	0.9996	0.2135	0.3317	0.2421	-1.0	0.3245	0.2411	0.3571	0.6142	0.7234	-1.0	0.6229	0.7368	0.1289	0.685	0.1954	0.731	0.3163	0.7543
1.4397	11.0	660	1.0359	0.313	0.4916	0.3638	-1.0	0.4765	0.3136	0.3783	0.6039	0.6935	-1.0	0.5971	0.7051	0.2058	0.64	0.2602	0.7119	0.4731	0.7286
1.4397	12.0	720	1.0051	0.3329	0.5244	0.3845	-1.0	0.539	0.3262	0.3867	0.6153	0.7231	-1.0	0.6914	0.7268	0.2134	0.6925	0.2743	0.7452	0.5111	0.7314
1.4397	13.0	780	0.9043	0.4053	0.6027	0.4549	-1.0	0.491	0.4133	0.3862	0.6646	0.7517	-1.0	0.71	0.7585	0.286	0.73	0.3504	0.7738	0.5796	0.7514
1.4397	14.0	840	0.9346	0.3972	0.589	0.45	-1.0	0.4686	0.4016	0.3975	0.6671	0.7438	-1.0	0.7171	0.7505	0.3249	0.69	0.3405	0.7786	0.5261	0.7629
1.4397	15.0	900	0.8932	0.46	0.6707	0.5185	-1.0	0.4714	0.4758	0.4033	0.6815	0.7486	-1.0	0.7171	0.7564	0.3733	0.7	0.395	0.7571	0.6115	0.7886
1.4397	16.0	960	0.9136	0.449	0.6785	0.5173	-1.0	0.5232	0.4552	0.3999	0.659	0.7456	-1.0	0.6843	0.7544	0.3302	0.7125	0.3977	0.75	0.619	0.7743
0.8233	17.0	1020	0.8842	0.472	0.7043	0.5647	-1.0	0.5214	0.4805	0.3964	0.6667	0.7573	-1.0	0.7386	0.7606	0.3924	0.7275	0.4447	0.7786	0.579	0.7657
0.8233	18.0	1080	0.9066	0.4877	0.7263	0.5845	-1.0	0.5344	0.4988	0.3897	0.6804	0.7563	-1.0	0.7357	0.7613	0.3998	0.71	0.4572	0.7619	0.606	0.7971
0.8233	19.0	1140	0.8907	0.5064	0.741	0.5837	-1.0	0.5143	0.5225	0.3963	0.6844	0.756	-1.0	0.71	0.7648	0.4011	0.715	0.4914	0.7786	0.6267	0.7743
0.8233	20.0	1200	0.8983	0.5226	0.779	0.6133	-1.0	0.5526	0.5303	0.4044	0.6931	0.7544	-1.0	0.76	0.7563	0.4215	0.695	0.507	0.7738	0.6393	0.7943
0.8233	21.0	1260	0.8372	0.5484	0.7701	0.641	-1.0	0.5423	0.561	0.4135	0.7104	0.7793	-1.0	0.8	0.7795	0.4446	0.7375	0.5457	0.7976	0.6548	0.8029
0.8233	22.0	1320	0.8065	0.5278	0.7465	0.6028	-1.0	0.5488	0.5416	0.4163	0.7259	0.7807	-1.0	0.7443	0.7871	0.4388	0.765	0.489	0.7857	0.6555	0.7914
0.8233	23.0	1380	0.8122	0.5423	0.7637	0.6037	-1.0	0.53	0.5583	0.4075	0.6963	0.777	-1.0	0.7457	0.7809	0.4426	0.7625	0.5304	0.7857	0.6538	0.7829
0.8233	24.0	1440	0.8222	0.5089	0.7194	0.5928	-1.0	0.5741	0.5159	0.3979	0.6915	0.7724	-1.0	0.7214	0.7786	0.3995	0.76	0.4906	0.7857	0.6366	0.7714
0.6232	25.0	1500	0.8286	0.5212	0.7314	0.5952	-1.0	0.5522	0.5289	0.4019	0.7154	0.7805	-1.0	0.7357	0.7866	0.4001	0.76	0.4929	0.7786	0.6707	0.8029
0.6232	26.0	1560	0.8298	0.5307	0.737	0.5891	-1.0	0.5528	0.5435	0.406	0.7093	0.7718	-1.0	0.7386	0.7775	0.3965	0.745	0.5269	0.7762	0.6686	0.7943
0.6232	27.0	1620	0.8292	0.5412	0.7501	0.6078	-1.0	0.5566	0.5509	0.4173	0.7106	0.7721	-1.0	0.7657	0.7756	0.4197	0.735	0.5364	0.7786	0.6676	0.8029
0.6232	28.0	1680	0.8215	0.5417	0.7518	0.6103	-1.0	0.5583	0.5515	0.4131	0.7052	0.7676	-1.0	0.7486	0.7725	0.4222	0.73	0.5368	0.7786	0.666	0.7943
0.6232	29.0	1740	0.8211	0.5424	0.7539	0.6124	-1.0	0.5556	0.5525	0.4148	0.7053	0.7677	-1.0	0.7486	0.7724	0.4272	0.7325	0.5339	0.7762	0.6661	0.7943
0.6232	30.0	1800	0.8212	0.5422	0.7536	0.6124	-1.0	0.5556	0.5523	0.4148	0.7053	0.7661	-1.0	0.7486	0.7706	0.4267	0.7325	0.5337	0.7714	0.6661	0.7943

Framework versions

Transformers 4.51.3
Pytorch 2.6.0+cu124
Datasets 3.5.0
Tokenizers 0.21.1

pabpelle/yolo_finetuned_fruits

yolo_finetuned_fruits

Model description

Intended uses & limitations

Training and evaluation data

Training procedure

Training hyperparameters

Training results

Framework versions

pabpelle/
yolo_finetuned_fruits