MAE-CT-CPC-Dicotomized-n0-m1-v8-1

This model is a fine-tuned version of beingbatman/MAE-CT-CPC-Dicotomized-v8-n0-m1 on an unknown dataset. It achieves the following results on the evaluation set:

• Loss: 0.8805
• Accuracy: 0.8372

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: 4
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• lr_scheduler_warmup_ratio: 0.1
• training_steps: 3500

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
0.3313	0.02	70	0.8279	0.6875
0.4602	1.02	140	0.7751	0.6562
0.413	2.02	210	0.9297	0.6562
0.2196	3.02	280	1.3078	0.5938
0.4898	4.02	350	1.2869	0.625
0.1867	5.02	420	1.5884	0.625
0.0394	6.02	490	1.7787	0.625
0.1218	7.02	560	1.7999	0.5938
0.192	8.02	630	1.7295	0.625
0.3974	9.02	700	1.4709	0.6562
0.4529	10.02	770	1.6416	0.625
0.0831	11.02	840	2.0432	0.6875
0.0104	12.02	910	2.1283	0.5938
0.0287	13.02	980	1.8532	0.75
0.0426	14.02	1050	2.0925	0.6875
0.0145	15.02	1120	2.3519	0.625
0.0024	16.02	1190	2.0705	0.625
0.0176	17.02	1260	2.3603	0.625
0.0023	18.02	1330	2.3409	0.6562
0.1111	19.02	1400	2.3461	0.625
0.0002	20.02	1470	2.0998	0.6875
0.0432	21.02	1540	2.2703	0.5938
0.006	22.02	1610	2.3306	0.6562
0.0014	23.02	1680	2.4463	0.625
0.0173	24.02	1750	2.5565	0.6562
0.0001	25.02	1820	2.7107	0.625
0.0001	26.02	1890	3.0925	0.5938
0.1792	27.02	1960	2.5367	0.625
0.0004	28.02	2030	2.9952	0.5625
0.0001	29.02	2100	2.7962	0.625
0.0	30.02	2170	3.1082	0.5938
0.0001	31.02	2240	2.6867	0.625
0.0	32.02	2310	2.6702	0.625
0.0	33.02	2380	3.3403	0.5938
0.0	34.02	2450	3.0539	0.625
0.2031	35.02	2520	2.7333	0.6875
0.0	36.02	2590	2.9420	0.5938
0.0	37.02	2660	2.9199	0.6562
0.0018	38.02	2730	2.8934	0.5938
0.0	39.02	2800	2.8320	0.625
0.0	40.02	2870	2.8381	0.625
0.0	41.02	2940	2.8439	0.625
0.0	42.02	3010	2.8525	0.625
0.0	43.02	3080	2.6921	0.5938
0.0	44.02	3150	2.9580	0.625
0.0	45.02	3220	3.0292	0.5938
0.0	46.02	3290	3.1119	0.625
0.0	47.02	3360	3.1150	0.625
0.0	48.02	3430	3.1127	0.625
0.0	49.02	3500	3.1126	0.625

Framework versions

• Transformers 4.45.2
• Pytorch 2.0.1+cu117
• Datasets 3.0.1
• Tokenizers 0.20.0