detr-r50-finetuned-mist1-gb-4ah-6l

This model is a fine-tuned version of polejowska/detr-r50-cd45rb-8ah-6l on an unknown dataset. It achieves the following results on the evaluation set:

• Loss: 2.2166

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: 1e-05
• train_batch_size: 4
• eval_batch_size: 8
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 50
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss
3.4044	1.0	115	3.0048
3.1708	2.0	230	2.9028
3.0756	3.0	345	2.8538
2.9769	4.0	460	2.8149
2.8999	5.0	575	2.7332
2.8609	6.0	690	2.7212
2.8338	7.0	805	2.6894
2.8103	8.0	920	2.7045
2.8036	9.0	1035	2.7786
2.7486	10.0	1150	2.6881
2.7076	11.0	1265	2.6059
2.7156	12.0	1380	2.6483
2.6655	13.0	1495	2.5438
2.6368	14.0	1610	2.5342
2.5982	15.0	1725	2.5287
2.6116	16.0	1840	2.4446
2.5592	17.0	1955	2.4365
2.5528	18.0	2070	2.4844
2.5248	19.0	2185	2.4195
2.4853	20.0	2300	2.4538
2.5295	21.0	2415	2.5696
2.5069	22.0	2530	2.4537
2.4504	23.0	2645	2.5152
2.4447	24.0	2760	2.4432
2.4303	25.0	2875	2.4033
2.4137	26.0	2990	2.3796
2.41	27.0	3105	2.3599
2.3816	28.0	3220	2.4018
2.3752	29.0	3335	2.3116
2.3929	30.0	3450	2.3105
2.3791	31.0	3565	2.3677
2.3639	32.0	3680	2.4312
2.3475	33.0	3795	2.3052
2.3429	34.0	3910	2.3222
2.3115	35.0	4025	2.3126
2.3276	36.0	4140	2.3154
2.3126	37.0	4255	2.3534
2.2934	38.0	4370	2.2566
2.2901	39.0	4485	2.2748
2.2622	40.0	4600	2.2620
2.2707	41.0	4715	2.2336
2.2338	42.0	4830	2.2242
2.2457	43.0	4945	2.2192
2.227	44.0	5060	2.2067
2.2215	45.0	5175	2.2183
2.2075	46.0	5290	2.2188
2.2286	47.0	5405	2.2306
2.2292	48.0	5520	2.2160
2.219	49.0	5635	2.2208
2.2125	50.0	5750	2.2166

Framework versions

• Transformers 4.35.0
• Pytorch 2.0.0
• Datasets 2.1.0
• Tokenizers 0.14.1