videomae-base-finetuned-ucf101-subset

This model is a fine-tuned version of MCG-NJU/videomae-base on an unknown dataset. It achieves the following results on the evaluation set:

• Loss: 1.9019
• Accuracy: 0.5540

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: 5e-05
• train_batch_size: 64
• eval_batch_size: 64
• seed: 42
• optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
• lr_scheduler_type: linear
• lr_scheduler_warmup_ratio: 0.1
• training_steps: 1920

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
4.2451	0.0083	16	4.2284	0.0107
4.2251	1.0083	32	4.2152	0.0107
4.2276	2.0083	48	4.2096	0.0121
4.2146	3.0083	64	4.2124	0.0149
4.2217	4.0083	80	4.2042	0.0178
4.2091	5.0083	96	4.2051	0.0234
4.2085	6.0083	112	4.1939	0.0185
4.2044	7.0083	128	4.1792	0.0391
4.1624	8.0083	144	4.2015	0.0220
4.1253	9.0083	160	4.1215	0.0298
4.0308	10.0083	176	4.0025	0.0710
3.8065	11.0083	192	3.8723	0.0838
3.7614	12.0083	208	3.7139	0.0994
3.4761	13.0083	224	3.6160	0.1435
3.278	14.0083	240	3.3940	0.1925
3.0999	15.0083	256	3.3183	0.2081
2.9721	16.0083	272	3.1596	0.2486
2.8064	17.0083	288	3.0232	0.2670
2.6554	18.0083	304	2.9448	0.2912
2.5052	19.0083	320	2.8285	0.3310
2.4322	20.0083	336	2.7479	0.3402
2.3193	21.0083	352	2.7941	0.3310
2.2565	22.0083	368	2.6383	0.3672
2.1405	23.0083	384	2.5906	0.3608
2.1049	24.0083	400	2.5515	0.3786
1.8424	25.0083	416	2.4692	0.3920
1.8685	26.0083	432	2.4325	0.4276
1.7478	27.0083	448	2.4165	0.4148
1.7072	28.0083	464	2.3617	0.4268
1.7206	29.0083	480	2.3723	0.4304
1.693	30.0083	496	2.2890	0.4425
1.6347	31.0083	512	2.2442	0.4411
1.5276	32.0083	528	2.2104	0.4673
1.4576	33.0083	544	2.2279	0.4545
1.5455	34.0083	560	2.2050	0.4524
1.4485	35.0083	576	2.1585	0.4737
1.3896	36.0083	592	2.1851	0.4446
1.3766	37.0083	608	2.1185	0.4872
1.4035	38.0083	624	2.1164	0.4794
1.5892	39.0083	640	2.1029	0.4801
1.3647	40.0083	656	2.0912	0.4929
1.388	41.0083	672	2.1331	0.4730
1.3425	42.0083	688	2.1437	0.4794
1.2909	43.0083	704	2.1090	0.4716
1.2757	44.0083	720	2.0686	0.4901
1.181	45.0083	736	2.0485	0.4893
1.1825	46.0083	752	2.0561	0.4844
1.1594	47.0083	768	2.0327	0.4964
1.1699	48.0083	784	2.0950	0.4766
1.1908	49.0083	800	2.0465	0.4851
1.1149	50.0083	816	2.0570	0.4879
1.1388	51.0083	832	2.0232	0.4979
1.0421	52.0083	848	2.0133	0.4986
1.1243	53.0083	864	2.0421	0.4901
1.1064	54.0083	880	1.9614	0.5043
0.9778	55.0083	896	1.9939	0.5071
1.1417	56.0083	912	1.9774	0.5107
1.0578	57.0083	928	1.9625	0.5305
1.0904	58.0083	944	1.9713	0.5057
1.2569	59.0083	960	1.9496	0.5256
1.076	60.0083	976	1.9238	0.5369
1.018	61.0083	992	1.9578	0.5156
0.8569	62.0083	1008	1.9410	0.5185
0.9847	63.0083	1024	1.9655	0.5135
0.8992	64.0083	1040	1.9741	0.5185
0.9781	65.0083	1056	1.9591	0.5249
0.9016	66.0083	1072	1.9802	0.5135
0.9443	67.0083	1088	1.9882	0.5036
0.9359	68.0083	1104	2.0046	0.5092
0.7735	69.0083	1120	2.0172	0.5064
0.9405	70.0083	1136	1.9552	0.5270
0.9709	71.0083	1152	1.9573	0.5227
0.9914	72.0083	1168	1.9768	0.5249
0.8487	73.0083	1184	1.9570	0.5327
0.835	74.0083	1200	1.9759	0.5241
0.8914	75.0083	1216	1.9309	0.5298
0.9242	76.0083	1232	1.9595	0.5241
0.8235	77.0083	1248	1.9556	0.5277
0.8664	78.0083	1264	1.9790	0.5135
0.8699	79.0083	1280	1.9835	0.5227
0.9112	80.0083	1296	1.9426	0.5291
0.7901	81.0083	1312	1.9598	0.5256
0.8186	82.0083	1328	1.9397	0.5320
0.8229	83.0083	1344	1.9384	0.5327
0.9063	84.0083	1360	1.9324	0.5291
0.8843	85.0083	1376	1.9316	0.5369
0.7904	86.0083	1392	1.9269	0.5376
0.7942	87.0083	1408	1.9506	0.5291
0.8798	88.0083	1424	1.9185	0.5405
0.7678	89.0083	1440	1.9362	0.5327
0.7589	90.0083	1456	1.9496	0.5277
0.6679	91.0083	1472	1.9507	0.5298
0.8042	92.0083	1488	1.9510	0.5369
0.7722	93.0083	1504	1.9503	0.5334
0.6831	94.0083	1520	1.9531	0.5348
0.766	95.0083	1536	1.9345	0.5384
0.8099	96.0083	1552	1.9349	0.5376
0.7513	97.0083	1568	1.9238	0.5462
0.6561	98.0083	1584	1.9338	0.5426
0.7423	99.0083	1600	1.9019	0.5540
0.7739	100.0083	1616	1.9165	0.5504
0.6562	101.0083	1632	1.9271	0.5433
0.7182	102.0083	1648	1.9096	0.5440
0.6898	103.0083	1664	1.9213	0.5483
0.6541	104.0083	1680	1.9263	0.5433
0.7131	105.0083	1696	1.9148	0.5469
0.7076	106.0083	1712	1.9193	0.5455
0.7822	107.0083	1728	1.9166	0.5440
0.6955	108.0083	1744	1.9167	0.5490
0.6939	109.0083	1760	1.9129	0.5426
0.7149	110.0083	1776	1.9237	0.5355
0.7341	111.0083	1792	1.9047	0.5433
0.7101	112.0083	1808	1.9010	0.5433
0.764	113.0083	1824	1.9024	0.5455
0.667	114.0083	1840	1.9041	0.5476
0.7465	115.0083	1856	1.9006	0.5483
0.6935	116.0083	1872	1.9016	0.5462
0.7306	117.0083	1888	1.9009	0.5483
0.6578	118.0083	1904	1.9008	0.5483
0.6427	119.0083	1920	1.9014	0.5504

Framework versions

• Transformers 4.48.0
• Pytorch 2.5.1+cu118
• Datasets 3.2.0
• Tokenizers 0.21.0