README.md

metadata

license: other
tags:
  - generated_from_trainer
model-index:
  - name: segformer-b0-finetuned-segments-toolwear
    results: []

segformer-b0-finetuned-segments-toolwear

This model is a fine-tuned version of nvidia/mit-b0 on an unknown dataset. It achieves the following results on the evaluation set:

• Loss: 0.0236
• Mean Iou: 0.4952
• Mean Accuracy: 0.9904
• Overall Accuracy: 0.9904
• Accuracy Unlabeled: nan
• Accuracy Tool: 0.9904
• Iou Unlabeled: 0.0
• Iou Tool: 0.9904

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-05
• train_batch_size: 2
• eval_batch_size: 2
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 50

Training results

Training Loss	Epoch	Step	Validation Loss	Mean Iou	Mean Accuracy	Overall Accuracy	Accuracy Unlabeled	Accuracy Tool	Iou Unlabeled	Iou Tool
0.1696	1.18	20	0.3490	0.4962	0.9924	0.9924	nan	0.9924	0.0	0.9924
0.1045	2.35	40	0.0977	0.4878	0.9755	0.9755	nan	0.9755	0.0	0.9755
0.0871	3.53	60	0.0650	0.4952	0.9905	0.9905	nan	0.9905	0.0	0.9905
0.0542	4.71	80	0.0652	0.4956	0.9912	0.9912	nan	0.9912	0.0	0.9912
0.0507	5.88	100	0.0573	0.4952	0.9905	0.9905	nan	0.9905	0.0	0.9905
0.071	7.06	120	0.0510	0.4941	0.9883	0.9883	nan	0.9883	0.0	0.9883
0.0456	8.24	140	0.0487	0.4892	0.9785	0.9785	nan	0.9785	0.0	0.9785
0.0489	9.41	160	0.0430	0.4934	0.9867	0.9867	nan	0.9867	0.0	0.9867
0.048	10.59	180	0.0409	0.4940	0.9881	0.9881	nan	0.9881	0.0	0.9881
0.0476	11.76	200	0.0347	0.4966	0.9931	0.9931	nan	0.9931	0.0	0.9931
0.0479	12.94	220	0.0367	0.4972	0.9945	0.9945	nan	0.9945	0.0	0.9945
0.0242	14.12	240	0.0342	0.4962	0.9925	0.9925	nan	0.9925	0.0	0.9925
0.0277	15.29	260	0.0305	0.4967	0.9934	0.9934	nan	0.9934	0.0	0.9934
0.0192	16.47	280	0.0318	0.4956	0.9913	0.9913	nan	0.9913	0.0	0.9913
0.038	17.65	300	0.0284	0.4965	0.9929	0.9929	nan	0.9929	0.0	0.9929
0.0244	18.82	320	0.0280	0.4953	0.9906	0.9906	nan	0.9906	0.0	0.9906
0.0273	20.0	340	0.0269	0.4955	0.9911	0.9911	nan	0.9911	0.0	0.9911
0.0174	21.18	360	0.0280	0.4955	0.9910	0.9910	nan	0.9910	0.0	0.9910
0.0277	22.35	380	0.0270	0.4957	0.9914	0.9914	nan	0.9914	0.0	0.9914
0.0269	23.53	400	0.0271	0.4950	0.9901	0.9901	nan	0.9901	0.0	0.9901
0.0372	24.71	420	0.0252	0.4939	0.9879	0.9879	nan	0.9879	0.0	0.9879
0.023	25.88	440	0.0263	0.4935	0.9870	0.9870	nan	0.9870	0.0	0.9870
0.0183	27.06	460	0.0257	0.4960	0.9920	0.9920	nan	0.9920	0.0	0.9920
0.024	28.24	480	0.0256	0.4950	0.9900	0.9900	nan	0.9900	0.0	0.9900
0.0145	29.41	500	0.0245	0.4956	0.9911	0.9911	nan	0.9911	0.0	0.9911
0.0158	30.59	520	0.0250	0.4947	0.9895	0.9895	nan	0.9895	0.0	0.9895
0.0169	31.76	540	0.0247	0.4956	0.9912	0.9912	nan	0.9912	0.0	0.9912
0.018	32.94	560	0.0237	0.4965	0.9930	0.9930	nan	0.9930	0.0	0.9930
0.0161	34.12	580	0.0237	0.4956	0.9913	0.9913	nan	0.9913	0.0	0.9913
0.0191	35.29	600	0.0241	0.4951	0.9901	0.9901	nan	0.9901	0.0	0.9901
0.0133	36.47	620	0.0240	0.4956	0.9912	0.9912	nan	0.9912	0.0	0.9912
0.0118	37.65	640	0.0244	0.4949	0.9897	0.9897	nan	0.9897	0.0	0.9897
0.0133	38.82	660	0.0229	0.4961	0.9922	0.9922	nan	0.9922	0.0	0.9922
0.0198	40.0	680	0.0236	0.4958	0.9915	0.9915	nan	0.9915	0.0	0.9915
0.0168	41.18	700	0.0234	0.4961	0.9923	0.9923	nan	0.9923	0.0	0.9923
0.0119	42.35	720	0.0233	0.4957	0.9915	0.9915	nan	0.9915	0.0	0.9915
0.0154	43.53	740	0.0243	0.4950	0.9901	0.9901	nan	0.9901	0.0	0.9901
0.0126	44.71	760	0.0242	0.4949	0.9898	0.9898	nan	0.9898	0.0	0.9898
0.0128	45.88	780	0.0243	0.4955	0.9911	0.9911	nan	0.9911	0.0	0.9911
0.0116	47.06	800	0.0239	0.4953	0.9907	0.9907	nan	0.9907	0.0	0.9907
0.0121	48.24	820	0.0239	0.4954	0.9909	0.9909	nan	0.9909	0.0	0.9909
0.0164	49.41	840	0.0236	0.4952	0.9904	0.9904	nan	0.9904	0.0	0.9904

Framework versions

• Transformers 4.28.0
• Pytorch 2.1.0+cu121
• Datasets 2.16.0
• Tokenizers 0.13.3