segformer-finetuned-tt-2k-b1

This model is a fine-tuned version of nvidia/mit-b1 on the Saumya-Mundra/text255 dataset. It achieves the following results on the evaluation set:

• Loss: 0.0912
• Mean Iou: 0.4902
• Mean Accuracy: 0.9805
• Overall Accuracy: 0.9805
• Accuracy Text: nan
• Accuracy No Text: 0.9805
• Iou Text: 0.0
• Iou No Text: 0.9805

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: 6e-07
• train_batch_size: 8
• eval_batch_size: 8
• seed: 1337
• 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: polynomial
• training_steps: 5000

Training results

Training Loss	Epoch	Step	Accuracy No Text	Accuracy Text	Iou No Text	Iou Text	Validation Loss	Mean Accuracy	Mean Iou	Overall Accuracy
0.3305	1.0	125	0.9586	nan	0.9586	0.0	0.1846	0.9586	0.4793	0.9586
0.2037	2.0	250	0.9706	nan	0.9706	0.0	0.1322	0.9706	0.4853	0.9706
0.1534	3.0	375	0.9784	nan	0.9784	0.0	0.1074	0.9784	0.4892	0.9784
0.1313	4.0	500	0.9839	nan	0.9839	0.0	0.0976	0.9839	0.4920	0.9839
0.1156	5.0	625	0.9799	nan	0.9799	0.0	0.1001	0.9799	0.4900	0.9799
0.1123	6.0	750	0.9866	nan	0.9866	0.0	0.0920	0.9866	0.4933	0.9866
0.108	7.0	875	0.9815	nan	0.9815	0.0	0.0946	0.9815	0.4908	0.9815
0.1017	8.0	1000	0.9805	nan	0.9805	0.0	0.0943	0.9805	0.4903	0.9805
0.0994	9.0	1125	0.9808	nan	0.9808	0.0	0.0927	0.9808	0.4904	0.9808
0.0926	10.0	1250	0.9783	nan	0.9783	0.0	0.0957	0.9783	0.4891	0.9783
0.0907	11.0	1375	0.9830	nan	0.9830	0.0	0.0913	0.9830	0.4915	0.9830
0.0893	12.0	1500	0.9838	nan	0.9838	0.0	0.0893	0.9838	0.4919	0.9838
0.0853	13.0	1625	0.9804	nan	0.9804	0.0	0.0913	0.9804	0.4902	0.9804
0.0834	14.0	1750	0.9820	nan	0.9820	0.0	0.0899	0.9820	0.4910	0.9820
0.0861	15.0	1875	0.9815	nan	0.9815	0.0	0.0902	0.9815	0.4907	0.9815
0.0803	16.0	2000	0.9793	nan	0.9793	0.0	0.0929	0.9793	0.4897	0.9793
0.0884	17.0	2125	0.1001	0.4875	0.9751	0.9751	nan	0.9751	0.0	0.9751
0.0871	18.0	2250	0.0907	0.4892	0.9783	0.9783	nan	0.9783	0.0	0.9783
0.0854	19.0	2375	0.0893	0.4924	0.9849	0.9849	nan	0.9849	0.0	0.9849
0.0852	20.0	2500	0.0870	0.4915	0.9831	0.9831	nan	0.9831	0.0	0.9831
0.0858	21.0	2625	0.0925	0.4896	0.9792	0.9792	nan	0.9792	0.0	0.9792
0.0804	22.0	2750	0.0964	0.4887	0.9774	0.9774	nan	0.9774	0.0	0.9774
0.076	23.0	2875	0.0934	0.4893	0.9786	0.9786	nan	0.9786	0.0	0.9786
0.0753	24.0	3000	0.0906	0.4890	0.9781	0.9781	nan	0.9781	0.0	0.9781
0.0742	25.0	3125	0.0962	0.4900	0.9801	0.9801	nan	0.9801	0.0	0.9801
0.0724	26.0	3250	0.0892	0.4920	0.9840	0.9840	nan	0.9840	0.0	0.9840
0.0794	27.0	3375	0.0885	0.4902	0.9803	0.9803	nan	0.9803	0.0	0.9803
0.0685	28.0	3500	0.0932	0.4911	0.9821	0.9821	nan	0.9821	0.0	0.9821
0.0695	29.0	3625	0.0890	0.4906	0.9812	0.9812	nan	0.9812	0.0	0.9812
0.065	30.0	3750	0.0877	0.4904	0.9808	0.9808	nan	0.9808	0.0	0.9808
0.0699	31.0	3875	0.0947	0.4877	0.9754	0.9754	nan	0.9754	0.0	0.9754
0.0742	32.0	4000	0.0875	0.4902	0.9805	0.9805	nan	0.9805	0.0	0.9805
0.0646	33.0	4125	0.0895	0.4903	0.9805	0.9805	nan	0.9805	0.0	0.9805
0.0677	34.0	4250	0.0915	0.4909	0.9818	0.9818	nan	0.9818	0.0	0.9818
0.0666	35.0	4375	0.0932	0.4890	0.9781	0.9781	nan	0.9781	0.0	0.9781
0.062	36.0	4500	0.0893	0.4901	0.9803	0.9803	nan	0.9803	0.0	0.9803
0.0623	37.0	4625	0.0934	0.4895	0.9789	0.9789	nan	0.9789	0.0	0.9789
0.0658	38.0	4750	0.0907	0.4913	0.9826	0.9826	nan	0.9826	0.0	0.9826
0.0596	39.0	4875	0.0904	0.4915	0.9831	0.9831	nan	0.9831	0.0	0.9831
0.0628	40.0	5000	0.0912	0.4902	0.9805	0.9805	nan	0.9805	0.0	0.9805

Framework versions

• Transformers 4.49.0.dev0
• Pytorch 2.5.1+cu124
• Datasets 3.2.0
• Tokenizers 0.21.0