chickens-repro-3

This model is a fine-tuned version of facebook/detr-resnet-50 on an unknown dataset. It achieves the following results on the evaluation set:

• Loss: 0.2061

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: 8
• eval_batch_size: 8
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: cosine
• num_epochs: 60

Training results

Training Loss	Epoch	Step	Validation Loss
1.3117	1.0	57	1.0359
1.0848	2.0	114	0.7879
0.899	3.0	171	0.7501
0.8456	4.0	228	0.8135
0.8739	5.0	285	0.6095
0.6667	6.0	342	0.5471
0.6222	7.0	399	0.4436
0.6046	8.0	456	0.4413
0.5602	9.0	513	0.4294
0.5361	10.0	570	0.4080
0.5127	11.0	627	0.3935
0.5195	12.0	684	0.3533
0.495	13.0	741	0.3580
0.5578	14.0	798	0.4465
0.5777	15.0	855	0.3862
0.4795	16.0	912	0.3570
0.487	17.0	969	0.3705
0.4346	18.0	1026	0.3028
0.4504	19.0	1083	0.3879
0.4318	20.0	1140	0.3304
0.4291	21.0	1197	0.3828
0.4542	22.0	1254	0.3742
0.4395	23.0	1311	0.3422
0.4345	24.0	1368	0.3187
0.414	25.0	1425	0.3225
0.4211	26.0	1482	0.3362
0.4049	27.0	1539	0.3174
0.3907	28.0	1596	0.3501
0.3791	29.0	1653	0.3088
0.387	30.0	1710	0.3053
0.4215	31.0	1767	0.3090
0.396	32.0	1824	0.2858
0.3673	33.0	1881	0.2762
0.3592	34.0	1938	0.3091
0.3575	35.0	1995	0.2545
0.3415	36.0	2052	0.2588
0.3519	37.0	2109	0.2578
0.3504	38.0	2166	0.2590
0.3469	39.0	2223	0.2309
0.3401	40.0	2280	0.2484
0.3237	41.0	2337	0.2497
0.3309	42.0	2394	0.2110
0.3165	43.0	2451	0.2118
0.3133	44.0	2508	0.2088
0.3116	45.0	2565	0.2324
0.3095	46.0	2622	0.2174
0.3108	47.0	2679	0.2299
0.3078	48.0	2736	0.2221
0.3036	49.0	2793	0.2216
0.3	50.0	2850	0.2076
0.2969	51.0	2907	0.2067
0.2951	52.0	2964	0.2092
0.2992	53.0	3021	0.2115
0.2993	54.0	3078	0.2188
0.2981	55.0	3135	0.2162
0.3013	56.0	3192	0.2093
0.2937	57.0	3249	0.2037
0.2967	58.0	3306	0.2068
0.2951	59.0	3363	0.2064
0.2968	60.0	3420	0.2061

Framework versions

• Transformers 4.44.2
• Pytorch 2.4.1+cu121
• Datasets 2.19.2
• Tokenizers 0.19.1