segformer-b0-PLbubble

NredCat822/segformer-b0-PLbubble

segformer-b0-PLbubble is a machine learning model from NredCat822. Use it for the machine learning task on the model card, and read the license before you ship it in a product. It is set up for transformers. The card lists the license as other.

should probably proofread and complete it, then remove this comment. --

Downloads · 30 days

10% of all-time downloads

All-time downloads

Public

Parameters

3.7M

4 GB on disk

Likes

Public

Hugging Face

Repo makeup

Click a slice to open those files.

.safetensors14.9 MB · 100%

At a glance

Library: transformers
License: other
Model type: segformer
Access: Public
Created: Jun 26, 2024
Updated: Jun 27, 2024
SHA: ea9b9feb

Base models

nvidia/mit-b0

Model card

From the Hugging Face model README

segformer-b0-PLbubble

This model is a fine-tuned version of nvidia/mit-b0 on the None dataset. It achieves the following results on the evaluation set:

Loss: 0.1220
Mean Iou: 1.0
Mean Accuracy: 1.0
Overall Accuracy: 1.0
Per Category Iou: [1.0, nan]
Per Category Accuracy: [1.0, nan]

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: 30

Training results

Training Loss	Epoch	Step	Validation Loss	Mean Iou	Mean Accuracy	Overall Accuracy	Per Category Iou	Per Category Accuracy
0.4349	0.1333	20	0.6675	0.4882	0.9764	0.9764	[0.9763812450566833, 0.0]	[0.9763812450566833, nan]
0.3447	0.2667	40	0.5703	0.4808	0.9615	0.9615	[0.9615355039985939, 0.0]	[0.9615355039985939, nan]
0.2628	0.4	60	0.4469	0.4972	0.9945	0.9945	[0.9944809929475349, 0.0]	[0.9944809929475349, nan]
0.2494	0.5333	80	0.3912	1.0	1.0	1.0	[1.0, nan]	[1.0, nan]
0.1228	0.6667	100	0.2821	0.4969	0.9938	0.9938	[0.9937532268872484, 0.0]	[0.9937532268872484, nan]
0.1172	0.8	120	0.1438	0.4976	0.9952	0.9952	[0.9951531466956675, 0.0]	[0.9951531466956675, nan]
0.1035	0.9333	140	0.1420	1.0	1.0	1.0	[1.0, nan]	[1.0, nan]
0.0766	1.0667	160	0.2453	1.0	1.0	1.0	[1.0, nan]	[1.0, nan]
0.0671	1.2	180	0.2341	1.0	1.0	1.0	[1.0, nan]	[1.0, nan]
0.0321	1.3333	200	0.1829	1.0	1.0	1.0	[1.0, nan]	[1.0, nan]
0.0274	1.4667	220	0.2913	1.0	1.0	1.0	[1.0, nan]	[1.0, nan]
0.0351	1.6	240	0.1384	1.0	1.0	1.0	[1.0, nan]	[1.0, nan]
0.022	1.7333	260	0.1360	1.0	1.0	1.0	[1.0, nan]	[1.0, nan]
0.0241	1.8667	280	0.0779	1.0	1.0	1.0	[1.0, nan]	[1.0, nan]
0.0182	2.0	300	0.2171	0.4979	0.9958	0.9958	[0.9957545835530363, 0.0]	[0.9957545835530363, nan]
0.0204	2.1333	320	0.0848	1.0	1.0	1.0	[1.0, nan]	[1.0, nan]
0.0137	2.2667	340	0.0955	1.0	1.0	1.0	[1.0, nan]	[1.0, nan]
0.0143	2.4	360	0.1749	1.0	1.0	1.0	[1.0, nan]	[1.0, nan]
0.0094	2.5333	380	0.2083	1.0	1.0	1.0	[1.0, nan]	[1.0, nan]
0.0106	2.6667	400	0.0401	1.0	1.0	1.0	[1.0, nan]	[1.0, nan]
0.008	2.8	420	0.2128	1.0	1.0	1.0	[1.0, nan]	[1.0, nan]
0.0074	2.9333	440	0.1823	1.0	1.0	1.0	[1.0, nan]	[1.0, nan]
0.0076	3.0667	460	0.0463	1.0	1.0	1.0	[1.0, nan]	[1.0, nan]
0.0102	3.2	480	0.0970	1.0	1.0	1.0	[1.0, nan]	[1.0, nan]
0.0095	3.3333	500	0.0600	1.0	1.0	1.0	[1.0, nan]	[1.0, nan]
0.0075	3.4667	520	0.1235	1.0	1.0	1.0	[1.0, nan]	[1.0, nan]
0.0063	3.6	540	0.0755	1.0	1.0	1.0	[1.0, nan]	[1.0, nan]
0.0058	3.7333	560	0.1467	1.0	1.0	1.0	[1.0, nan]	[1.0, nan]
0.0071	3.8667	580	0.1714	1.0	1.0	1.0	[1.0, nan]	[1.0, nan]
0.0057	4.0	600	0.1630	1.0	1.0	1.0	[1.0, nan]	[1.0, nan]
0.0044	4.1333	620	0.1440	1.0	1.0	1.0	[1.0, nan]	[1.0, nan]
0.0054	4.2667	640	0.1697	1.0	1.0	1.0	[1.0, nan]	[1.0, nan]
0.0067	4.4	660	0.0370	1.0	1.0	1.0	[1.0, nan]	[1.0, nan]
0.0056	4.5333	680	0.0017	1.0	1.0	1.0	[1.0, nan]	[1.0, nan]
0.0047	4.6667	700	0.0768	1.0	1.0	1.0	[1.0, nan]	[1.0, nan]
0.0037	4.8	720	0.1698	1.0	1.0	1.0	[1.0, nan]	[1.0, nan]
0.0035	4.9333	740	0.1520	1.0	1.0	1.0	[1.0, nan]	[1.0, nan]
0.0029	5.0667	760	0.1739	1.0	1.0	1.0	[1.0, nan]	[1.0, nan]
0.0032	5.2	780	0.0686	1.0	1.0	1.0	[1.0, nan]	[1.0, nan]
0.0036	5.3333	800	0.0714	1.0	1.0	1.0	[1.0, nan]	[1.0, nan]
0.0046	5.4667	820	0.1578	1.0	1.0	1.0	[1.0, nan]	[1.0, nan]
0.0031	5.6	840	0.0672	1.0	1.0	1.0	[1.0, nan]	[1.0, nan]
0.0046	5.7333	860	0.1603	1.0	1.0	1.0	[1.0, nan]	[1.0, nan]
0.0025	5.8667	880	0.0582	1.0	1.0	1.0	[1.0, nan]	[1.0, nan]
0.0023	6.0	900	0.0454	1.0	1.0	1.0	[1.0, nan]	[1.0, nan]
0.0028	6.1333	920	0.0213	1.0	1.0	1.0	[1.0, nan]	[1.0, nan]
0.0022	6.2667	940	0.1520	1.0	1.0	1.0	[1.0, nan]	[1.0, nan]
0.0022	6.4	960	0.1324	1.0	1.0	1.0	[1.0, nan]	[1.0, nan]
0.0018	6.5333	980	0.1648	1.0	1.0	1.0	[1.0, nan]	[1.0, nan]
0.0032	6.6667	1000	0.1482	1.0	1.0	1.0	[1.0, nan]	[1.0, nan]
0.0027	6.8	1020	0.0168	1.0	1.0	1.0	[1.0, nan]	[1.0, nan]
0.0025	6.9333	1040	0.1659	1.0	1.0	1.0	[1.0, nan]	[1.0, nan]
0.0018	7.0667	1060	0.1450	1.0	1.0	1.0	[1.0, nan]	[1.0, nan]
0.0033	7.2	1080	0.0364	1.0	1.0	1.0	[1.0, nan]	[1.0, nan]
0.0015	7.3333	1100	0.0243	1.0	1.0	1.0	[1.0, nan]	[1.0, nan]
0.0016	7.4667	1120	0.1476	1.0	1.0	1.0	[1.0, nan]	[1.0, nan]
0.0016	7.6	1140	0.0828	1.0	1.0	1.0	[1.0, nan]	[1.0, nan]
0.0015	7.7333	1160	0.1479	1.0	1.0	1.0	[1.0, nan]	[1.0, nan]
0.0015	7.8667	1180	0.0738	1.0	1.0	1.0	[1.0, nan]	[1.0, nan]
0.0019	8.0	1200	0.0908	1.0	1.0	1.0	[1.0, nan]	[1.0, nan]
0.0028	8.1333	1220	0.1636	1.0	1.0	1.0	[1.0, nan]	[1.0, nan]
0.001	8.2667	1240	0.1233	1.0	1.0	1.0	[1.0, nan]	[1.0, nan]
0.0014	8.4	1260	0.0878	1.0	1.0	1.0	[1.0, nan]	[1.0, nan]
0.0021	8.5333	1280	0.0775	1.0	1.0	1.0	[1.0, nan]	[1.0, nan]
0.0018	8.6667	1300	0.0159	1.0	1.0	1.0	[1.0, nan]	[1.0, nan]
0.0012	8.8	1320	0.1521	1.0	1.0	1.0	[1.0, nan]	[1.0, nan]
0.0016	8.9333	1340	0.1453	1.0	1.0	1.0	[1.0, nan]	[1.0, nan]
0.0009	9.0667	1360	0.0766	1.0	1.0	1.0	[1.0, nan]	[1.0, nan]
0.001	9.2	1380	0.0553	1.0	1.0	1.0	[1.0, nan]	[1.0, nan]
0.001	9.3333	1400	0.1483	1.0	1.0	1.0	[1.0, nan]	[1.0, nan]
0.0011	9.4667	1420	0.1172	1.0	1.0	1.0	[1.0, nan]	[1.0, nan]
0.0021	9.6	1440	0.0503	1.0	1.0	1.0	[1.0, nan]	[1.0, nan]
0.0009	9.7333	1460	0.2155	1.0	1.0	1.0	[1.0, nan]	[1.0, nan]
0.0009	9.8667	1480	0.2272	1.0	1.0	1.0	[1.0, nan]	[1.0, nan]
0.0008	10.0	1500	0.2017	1.0	1.0	1.0	[1.0, nan]	[1.0, nan]
0.0019	10.1333	1520	0.1512	1.0	1.0	1.0	[1.0, nan]	[1.0, nan]
0.0009	10.2667	1540	0.1371	1.0	1.0	1.0	[1.0, nan]	[1.0, nan]
0.0008	10.4	1560	0.0169	1.0	1.0	1.0	[1.0, nan]	[1.0, nan]
0.0015	10.5333	1580	0.1463	1.0	1.0	1.0	[1.0, nan]	[1.0, nan]
0.0015	10.6667	1600	0.0502	1.0	1.0	1.0	[1.0, nan]	[1.0, nan]
0.0015	10.8	1620	0.0403	1.0	1.0	1.0	[1.0, nan]	[1.0, nan]
0.0012	10.9333	1640	0.0887	1.0	1.0	1.0	[1.0, nan]	[1.0, nan]
0.0013	11.0667	1660	0.0072	1.0	1.0	1.0	[1.0, nan]	[1.0, nan]
0.0007	11.2	1680	0.0104	1.0	1.0	1.0	[1.0, nan]	[1.0, nan]
0.0011	11.3333	1700	0.1380	1.0	1.0	1.0	[1.0, nan]	[1.0, nan]
0.0013	11.4667	1720	0.1270	1.0	1.0	1.0	[1.0, nan]	[1.0, nan]
0.001	11.6	1740	0.1037	1.0	1.0	1.0	[1.0, nan]	[1.0, nan]
0.0008	11.7333	1760	0.0829	1.0	1.0	1.0	[1.0, nan]	[1.0, nan]
0.0008	11.8667	1780	0.0124	1.0	1.0	1.0	[1.0, nan]	[1.0, nan]
0.0011	12.0	1800	0.1691	1.0	1.0	1.0	[1.0, nan]	[1.0, nan]
0.0007	12.1333	1820	0.0873	1.0	1.0	1.0	[1.0, nan]	[1.0, nan]
0.0008	12.2667	1840	0.0830	1.0	1.0	1.0	[1.0, nan]	[1.0, nan]
0.0011	12.4	1860	0.0893	1.0	1.0	1.0	[1.0, nan]	[1.0, nan]
0.0007	12.5333	1880	0.0830	1.0	1.0	1.0	[1.0, nan]	[1.0, nan]
0.0007	12.6667	1900	0.0718	1.0	1.0	1.0	[1.0, nan]	[1.0, nan]
0.0008	12.8	1920	0.1217	1.0	1.0	1.0	[1.0, nan]	[1.0, nan]
0.0005	12.9333	1940	0.0428	1.0	1.0	1.0	[1.0, nan]	[1.0, nan]
0.0011	13.0667	1960	0.0398	1.0	1.0	1.0	[1.0, nan]	[1.0, nan]
0.0014	13.2	1980	0.0986	1.0	1.0	1.0	[1.0, nan]	[1.0, nan]
0.0006	13.3333	2000	0.0159	1.0	1.0	1.0	[1.0, nan]	[1.0, nan]
0.0014	13.4667	2020	0.0748	1.0	1.0	1.0	[1.0, nan]	[1.0, nan]
0.0005	13.6	2040	0.0898	1.0	1.0	1.0	[1.0, nan]	[1.0, nan]
0.0008	13.7333	2060	0.0292	1.0	1.0	1.0	[1.0, nan]	[1.0, nan]
0.0006	13.8667	2080	0.1166	1.0	1.0	1.0	[1.0, nan]	[1.0, nan]
0.0008	14.0	2100	0.0387	1.0	1.0	1.0	[1.0, nan]	[1.0, nan]
0.0009	14.1333	2120	0.1439	1.0	1.0	1.0	[1.0, nan]	[1.0, nan]
0.0005	14.2667	2140	0.0181	1.0	1.0	1.0	[1.0, nan]	[1.0, nan]
0.0005	14.4	2160	0.1052	1.0	1.0	1.0	[1.0, nan]	[1.0, nan]
0.0011	14.5333	2180	0.0284	1.0	1.0	1.0	[1.0, nan]	[1.0, nan]
0.0006	14.6667	2200	0.0839	1.0	1.0	1.0	[1.0, nan]	[1.0, nan]
0.0008	14.8	2220	0.0989	1.0	1.0	1.0	[1.0, nan]	[1.0, nan]
0.0006	14.9333	2240	0.0986	1.0	1.0	1.0	[1.0, nan]	[1.0, nan]
0.0005	15.0667	2260	0.1199	1.0	1.0	1.0	[1.0, nan]	[1.0, nan]
0.0008	15.2	2280	0.1042	1.0	1.0	1.0	[1.0, nan]	[1.0, nan]
0.0019	15.3333	2300	0.0328	1.0	1.0	1.0	[1.0, nan]	[1.0, nan]
0.001	15.4667	2320	0.1013	1.0	1.0	1.0	[1.0, nan]	[1.0, nan]
0.0006	15.6	2340	0.0943	1.0	1.0	1.0	[1.0, nan]	[1.0, nan]
0.0008	15.7333	2360	0.0977	1.0	1.0	1.0	[1.0, nan]	[1.0, nan]
0.0005	15.8667	2380	0.1455	1.0	1.0	1.0	[1.0, nan]	[1.0, nan]
0.0004	16.0	2400	0.0704	1.0	1.0	1.0	[1.0, nan]	[1.0, nan]
0.0004	16.1333	2420	0.0749	1.0	1.0	1.0	[1.0, nan]	[1.0, nan]
0.0006	16.2667	2440	0.0422	1.0	1.0	1.0	[1.0, nan]	[1.0, nan]
0.0005	16.4	2460	0.1148	1.0	1.0	1.0	[1.0, nan]	[1.0, nan]
0.0005	16.5333	2480	0.1193	1.0	1.0	1.0	[1.0, nan]	[1.0, nan]
0.0006	16.6667	2500	0.0921	1.0	1.0	1.0	[1.0, nan]	[1.0, nan]
0.0004	16.8	2520	0.1161	1.0	1.0	1.0	[1.0, nan]	[1.0, nan]
0.0004	16.9333	2540	0.0058	1.0	1.0	1.0	[1.0, nan]	[1.0, nan]
0.0003	17.0667	2560	0.0716	1.0	1.0	1.0	[1.0, nan]	[1.0, nan]
0.0004	17.2	2580	0.0665	1.0	1.0	1.0	[1.0, nan]	[1.0, nan]
0.0008	17.3333	2600	0.0849	1.0	1.0	1.0	[1.0, nan]	[1.0, nan]
0.0004	17.4667	2620	0.0328	1.0	1.0	1.0	[1.0, nan]	[1.0, nan]
0.0004	17.6	2640	0.0908	1.0	1.0	1.0	[1.0, nan]	[1.0, nan]
0.0007	17.7333	2660	0.0819	1.0	1.0	1.0	[1.0, nan]	[1.0, nan]
0.0007	17.8667	2680	0.0499	1.0	1.0	1.0	[1.0, nan]	[1.0, nan]
0.0006	18.0	2700	0.0174	1.0	1.0	1.0	[1.0, nan]	[1.0, nan]
0.0005	18.1333	2720	0.1184	1.0	1.0	1.0	[1.0, nan]	[1.0, nan]
0.0003	18.2667	2740	0.0366	1.0	1.0	1.0	[1.0, nan]	[1.0, nan]
0.0004	18.4	2760	0.0037	1.0	1.0	1.0	[1.0, nan]	[1.0, nan]
0.0004	18.5333	2780	0.0031	1.0	1.0	1.0	[1.0, nan]	[1.0, nan]
0.0004	18.6667	2800	0.0479	1.0	1.0	1.0	[1.0, nan]	[1.0, nan]
0.0003	18.8	2820	0.0271	1.0	1.0	1.0	[1.0, nan]	[1.0, nan]
0.0003	18.9333	2840	0.0747	1.0	1.0	1.0	[1.0, nan]	[1.0, nan]
0.0022	19.0667	2860	0.0904	1.0	1.0	1.0	[1.0, nan]	[1.0, nan]
0.0003	19.2	2880	0.1316	1.0	1.0	1.0	[1.0, nan]	[1.0, nan]
0.0004	19.3333	2900	0.1361	1.0	1.0	1.0	[1.0, nan]	[1.0, nan]
0.0006	19.4667	2920	0.0948	1.0	1.0	1.0	[1.0, nan]	[1.0, nan]
0.0003	19.6	2940	0.0495	1.0	1.0	1.0	[1.0, nan]	[1.0, nan]
0.0003	19.7333	2960	0.0979	1.0	1.0	1.0	[1.0, nan]	[1.0, nan]
0.0011	19.8667	2980	0.1175	1.0	1.0	1.0	[1.0, nan]	[1.0, nan]
0.0005	20.0	3000	0.0074	1.0	1.0	1.0	[1.0, nan]	[1.0, nan]
0.0003	20.1333	3020	0.1573	1.0	1.0	1.0	[1.0, nan]	[1.0, nan]
0.0004	20.2667	3040	0.0160	1.0	1.0	1.0	[1.0, nan]	[1.0, nan]
0.0003	20.4	3060	0.0915	1.0	1.0	1.0	[1.0, nan]	[1.0, nan]
0.0003	20.5333	3080	0.0551	1.0	1.0	1.0	[1.0, nan]	[1.0, nan]
0.0003	20.6667	3100	0.0192	1.0	1.0	1.0	[1.0, nan]	[1.0, nan]
0.0003	20.8	3120	0.0277	1.0	1.0	1.0	[1.0, nan]	[1.0, nan]
0.0003	20.9333	3140	0.1103	1.0	1.0	1.0	[1.0, nan]	[1.0, nan]
0.0003	21.0667	3160	0.0565	1.0	1.0	1.0	[1.0, nan]	[1.0, nan]
0.0006	21.2	3180	0.0097	1.0	1.0	1.0	[1.0, nan]	[1.0, nan]
0.0003	21.3333	3200	0.0588	1.0	1.0	1.0	[1.0, nan]	[1.0, nan]
0.0003	21.4667	3220	0.0182	1.0	1.0	1.0	[1.0, nan]	[1.0, nan]
0.0003	21.6	3240	0.0832	1.0	1.0	1.0	[1.0, nan]	[1.0, nan]
0.0003	21.7333	3260	0.0988	1.0	1.0	1.0	[1.0, nan]	[1.0, nan]
0.0004	21.8667	3280	0.0841	1.0	1.0	1.0	[1.0, nan]	[1.0, nan]
0.0004	22.0	3300	0.1069	1.0	1.0	1.0	[1.0, nan]	[1.0, nan]
0.0003	22.1333	3320	0.1176	1.0	1.0	1.0	[1.0, nan]	[1.0, nan]
0.0002	22.2667	3340	0.1257	1.0	1.0	1.0	[1.0, nan]	[1.0, nan]
0.0003	22.4	3360	0.1052	1.0	1.0	1.0	[1.0, nan]	[1.0, nan]
0.0003	22.5333	3380	0.0457	1.0	1.0	1.0	[1.0, nan]	[1.0, nan]
0.0003	22.6667	3400	0.1074	1.0	1.0	1.0	[1.0, nan]	[1.0, nan]
0.0007	22.8	3420	0.0232	1.0	1.0	1.0	[1.0, nan]	[1.0, nan]
0.0003	22.9333	3440	0.0478	1.0	1.0	1.0	[1.0, nan]	[1.0, nan]
0.0002	23.0667	3460	0.0762	1.0	1.0	1.0	[1.0, nan]	[1.0, nan]
0.0002	23.2	3480	0.0857	1.0	1.0	1.0	[1.0, nan]	[1.0, nan]
0.0002	23.3333	3500	0.1673	1.0	1.0	1.0	[1.0, nan]	[1.0, nan]
0.0004	23.4667	3520	0.1409	1.0	1.0	1.0	[1.0, nan]	[1.0, nan]
0.0003	23.6	3540	0.1192	1.0	1.0	1.0	[1.0, nan]	[1.0, nan]
0.0003	23.7333	3560	0.1272	1.0	1.0	1.0	[1.0, nan]	[1.0, nan]
0.0003	23.8667	3580	0.1327	1.0	1.0	1.0	[1.0, nan]	[1.0, nan]
0.0003	24.0	3600	0.0691	1.0	1.0	1.0	[1.0, nan]	[1.0, nan]
0.0003	24.1333	3620	0.1050	1.0	1.0	1.0	[1.0, nan]	[1.0, nan]
0.0003	24.2667	3640	0.0339	1.0	1.0	1.0	[1.0, nan]	[1.0, nan]
0.0003	24.4	3660	0.0274	1.0	1.0	1.0	[1.0, nan]	[1.0, nan]
0.0002	24.5333	3680	0.1326	1.0	1.0	1.0	[1.0, nan]	[1.0, nan]
0.0003	24.6667	3700	0.0904	1.0	1.0	1.0	[1.0, nan]	[1.0, nan]
0.0003	24.8	3720	0.1312	1.0	1.0	1.0	[1.0, nan]	[1.0, nan]
0.0002	24.9333	3740	0.0775	1.0	1.0	1.0	[1.0, nan]	[1.0, nan]
0.0004	25.0667	3760	0.1099	1.0	1.0	1.0	[1.0, nan]	[1.0, nan]
0.0002	25.2	3780	0.0509	1.0	1.0	1.0	[1.0, nan]	[1.0, nan]
0.0003	25.3333	3800	0.1120	1.0	1.0	1.0	[1.0, nan]	[1.0, nan]
0.0004	25.4667	3820	0.0131	1.0	1.0	1.0	[1.0, nan]	[1.0, nan]
0.0003	25.6	3840	0.0640	1.0	1.0	1.0	[1.0, nan]	[1.0, nan]
0.0003	25.7333	3860	0.0422	1.0	1.0	1.0	[1.0, nan]	[1.0, nan]
0.0002	25.8667	3880	0.1482	1.0	1.0	1.0	[1.0, nan]	[1.0, nan]
0.0003	26.0	3900	0.1136	1.0	1.0	1.0	[1.0, nan]	[1.0, nan]
0.0002	26.1333	3920	0.1221	1.0	1.0	1.0	[1.0, nan]	[1.0, nan]
0.0002	26.2667	3940	0.0991	1.0	1.0	1.0	[1.0, nan]	[1.0, nan]
0.0004	26.4	3960	0.0169	1.0	1.0	1.0	[1.0, nan]	[1.0, nan]
0.0003	26.5333	3980	0.1594	1.0	1.0	1.0	[1.0, nan]	[1.0, nan]
0.0002	26.6667	4000	0.1176	1.0	1.0	1.0	[1.0, nan]	[1.0, nan]
0.0003	26.8	4020	0.1065	1.0	1.0	1.0	[1.0, nan]	[1.0, nan]
0.0003	26.9333	4040	0.0929	1.0	1.0	1.0	[1.0, nan]	[1.0, nan]
0.0005	27.0667	4060	0.1079	1.0	1.0	1.0	[1.0, nan]	[1.0, nan]
0.0002	27.2	4080	0.1030	1.0	1.0	1.0	[1.0, nan]	[1.0, nan]
0.0002	27.3333	4100	0.0099	1.0	1.0	1.0	[1.0, nan]	[1.0, nan]
0.0002	27.4667	4120	0.0439	1.0	1.0	1.0	[1.0, nan]	[1.0, nan]
0.0005	27.6	4140	0.0538	1.0	1.0	1.0	[1.0, nan]	[1.0, nan]
0.0003	27.7333	4160	0.1287	1.0	1.0	1.0	[1.0, nan]	[1.0, nan]
0.0004	27.8667	4180	0.1273	1.0	1.0	1.0	[1.0, nan]	[1.0, nan]
0.0002	28.0	4200	0.0277	1.0	1.0	1.0	[1.0, nan]	[1.0, nan]
0.0002	28.1333	4220	0.0621	1.0	1.0	1.0	[1.0, nan]	[1.0, nan]
0.0002	28.2667	4240	0.1391	1.0	1.0	1.0	[1.0, nan]	[1.0, nan]
0.0002	28.4	4260	0.0709	1.0	1.0	1.0	[1.0, nan]	[1.0, nan]
0.0003	28.5333	4280	0.1256	1.0	1.0	1.0	[1.0, nan]	[1.0, nan]
0.0002	28.6667	4300	0.0285	1.0	1.0	1.0	[1.0, nan]	[1.0, nan]
0.0003	28.8	4320	0.0218	1.0	1.0	1.0	[1.0, nan]	[1.0, nan]
0.0002	28.9333	4340	0.0459	1.0	1.0	1.0	[1.0, nan]	[1.0, nan]
0.0003	29.0667	4360	0.0612	1.0	1.0	1.0	[1.0, nan]	[1.0, nan]
0.0004	29.2	4380	0.0804	1.0	1.0	1.0	[1.0, nan]	[1.0, nan]
0.0004	29.3333	4400	0.0384	1.0	1.0	1.0	[1.0, nan]	[1.0, nan]
0.0003	29.4667	4420	0.1265	1.0	1.0	1.0	[1.0, nan]	[1.0, nan]
0.0004	29.6	4440	0.0007	1.0	1.0	1.0	[1.0, nan]	[1.0, nan]
0.0002	29.7333	4460	0.0273	1.0	1.0	1.0	[1.0, nan]	[1.0, nan]
0.0002	29.8667	4480	0.0411	1.0	1.0	1.0	[1.0, nan]	[1.0, nan]
0.0003	30.0	4500	0.1220	1.0	1.0	1.0	[1.0, nan]	[1.0, nan]

Framework versions

Transformers 4.41.2
Pytorch 2.3.1+cu121
Datasets 2.20.0
Tokenizers 0.19.1

Library: transformers
Type: segformer
License: other
Created: Jun 26, 2024
Updated: Jun 27, 2024