learning_rate: 1e-05
train_batch_size: 32
eval_batch_size: 32
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: 6000

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
4.2901	0.0052	31	4.2853	0.0134
4.2516	1.0052	62	4.2535	0.0134
4.2571	2.0052	93	4.2332	0.0134
4.2328	3.0052	124	4.2126	0.0134
4.2345	4.0052	155	4.2022	0.0201
4.2233	5.0052	186	4.1988	0.0268
4.2084	6.0052	217	4.1967	0.0201
4.1906	7.0052	248	4.2004	0.0134
4.176	8.0052	279	4.1855	0.0134
4.2101	9.0052	310	4.1755	0.0268
4.1634	10.0052	341	4.1699	0.0134
4.15	11.0052	372	4.1485	0.0
4.1337	12.0052	403	4.1399	0.0268
4.0795	13.0052	434	4.0924	0.0537
3.9775	14.0052	465	4.0237	0.0336
3.9058	15.0052	496	3.9771	0.0671
3.8452	16.0052	527	3.9138	0.0671
3.672	17.0052	558	3.8184	0.0940
3.5136	18.0052	589	3.6811	0.1477
3.3814	19.0052	620	3.6399	0.1208
3.2558	20.0052	651	3.4243	0.2081
3.01	21.0052	682	3.3260	0.2148
2.9555	22.0052	713	3.2369	0.2215
2.6845	23.0052	744	2.9768	0.3624
2.4133	24.0052	775	3.0204	0.3154
2.4458	25.0052	806	2.8562	0.3289
2.2763	26.0052	837	2.7155	0.3893
2.0426	27.0052	868	2.6809	0.3826
1.956	28.0052	899	2.5535	0.4966
1.8545	29.0052	930	2.4791	0.4362
1.8207	30.0052	961	2.4313	0.4899
1.7027	31.0052	992	2.3144	0.5705
1.4881	32.0052	1023	2.2554	0.5302
1.4513	33.0052	1054	2.2382	0.4899
1.4551	34.0052	1085	2.1496	0.5503
1.2282	35.0052	1116	2.0908	0.5235
1.0717	36.0052	1147	2.0112	0.5705
1.0951	37.0052	1178	1.9430	0.6107
1.0153	38.0052	1209	1.9749	0.5973
0.9146	39.0052	1240	1.8897	0.5638
0.9144	40.0052	1271	1.8523	0.6040
0.8478	41.0052	1302	1.8483	0.6242
0.8885	42.0052	1333	1.7968	0.6174
0.7587	43.0052	1364	1.7370	0.6242
0.6105	44.0052	1395	1.7457	0.6376
0.6016	45.0052	1426	1.7176	0.6107
0.5378	46.0052	1457	1.7152	0.5772
0.5422	47.0052	1488	1.6144	0.6174
0.5434	48.0052	1519	1.5685	0.6779
0.449	49.0052	1550	1.6494	0.5973
0.3718	50.0052	1581	1.5886	0.6376
0.401	51.0052	1612	1.5553	0.6376
0.3296	52.0052	1643	1.5275	0.6443
0.3444	53.0052	1674	1.5059	0.6443
0.3474	54.0052	1705	1.5190	0.6779
0.2824	55.0052	1736	1.5185	0.6040
0.2759	56.0052	1767	1.4980	0.6577
0.2569	57.0052	1798	1.4961	0.6174
0.1998	58.0052	1829	1.4438	0.6376
0.1938	59.0052	1860	1.4378	0.6443
0.1644	60.0052	1891	1.4572	0.6644
0.153	61.0052	1922	1.4159	0.6644
0.1544	62.0052	1953	1.3992	0.6779
0.1501	63.0052	1984	1.4149	0.6913
0.113	64.0052	2015	1.3413	0.6779
0.1498	65.0052	2046	1.3149	0.6846
0.1235	66.0052	2077	1.3310	0.6443
0.0947	67.0052	2108	1.3592	0.6577
0.0864	68.0052	2139	1.3824	0.6510
0.0866	69.0052	2170	1.3675	0.6644
0.0839	70.0052	2201	1.3086	0.6510
0.0732	71.0052	2232	1.3155	0.6711
0.0765	72.0052	2263	1.3024	0.6577
0.0698	73.0052	2294	1.2732	0.7047
0.0599	74.0052	2325	1.3444	0.6779
0.0724	75.0052	2356	1.3529	0.6309
0.0598	76.0052	2387	1.3223	0.6443
0.0515	77.0052	2418	1.3446	0.6510
0.0439	78.0052	2449	1.2611	0.7114
0.041	79.0052	2480	1.3011	0.6644
0.0417	80.0052	2511	1.2694	0.6846
0.0385	81.0052	2542	1.2977	0.6711
0.0339	82.0052	2573	1.2928	0.6779
0.0338	83.0052	2604	1.2569	0.6846
0.0266	84.0052	2635	1.2849	0.6846
0.0259	85.0052	2666	1.3345	0.6779
0.0258	86.0052	2697	1.2836	0.6779
0.0269	87.0052	2728	1.2712	0.6846
0.0248	88.0052	2759	1.2739	0.6913
0.023	89.0052	2790	1.2564	0.6644
0.0217	90.0052	2821	1.2790	0.6846
0.0209	91.0052	2852	1.2695	0.6779
0.0231	92.0052	2883	1.2718	0.6913
0.0192	93.0052	2914	1.2617	0.6913
0.0221	94.0052	2945	1.2444	0.6577
0.0177	95.0052	2976	1.2480	0.7114
0.018	96.0052	3007	1.2612	0.7114
0.0177	97.0052	3038	1.3213	0.6711
0.0191	98.0052	3069	1.2393	0.6846
0.0157	99.0052	3100	1.2632	0.6779
0.0174	100.0052	3131	1.3244	0.6913
0.018	101.0052	3162	1.2433	0.7047
0.015	102.0052	3193	1.1871	0.7047
0.0156	103.0052	3224	1.2912	0.6913
0.0153	104.0052	3255	1.2344	0.6980
0.0129	105.0052	3286	1.1846	0.7114
0.0164	106.0052	3317	1.2692	0.7047
0.0128	107.0052	3348	1.2297	0.6846
0.0121	108.0052	3379	1.2345	0.6980
0.0297	109.0052	3410	1.2527	0.7047
0.0123	110.0052	3441	1.3150	0.6779
0.0111	111.0052	3472	1.2627	0.6846
0.0123	112.0052	3503	1.2884	0.6846
0.0123	113.0052	3534	1.2814	0.6779
0.0106	114.0052	3565	1.3040	0.6846
0.0112	115.0052	3596	1.2438	0.6980
0.0109	116.0052	3627	1.3151	0.6779
0.01	117.0052	3658	1.3124	0.6779
0.0125	118.0052	3689	1.3081	0.6779
0.0097	119.0052	3720	1.2511	0.6846
0.0121	120.0052	3751	1.3298	0.6913
0.0105	121.0052	3782	1.3070	0.6644
0.0093	122.0052	3813	1.3212	0.6913
0.0102	123.0052	3844	1.2974	0.6846
0.0095	124.0052	3875	1.2708	0.6846
0.0088	125.0052	3906	1.2223	0.6846
0.0094	126.0052	3937	1.2796	0.6846
0.0086	127.0052	3968	1.3051	0.6711
0.0089	128.0052	3999	1.2705	0.6779
0.0079	129.0052	4030	1.2524	0.6711
0.008	130.0052	4061	1.2657	0.6577
0.0102	131.0052	4092	1.3071	0.6779
0.0087	132.0052	4123	1.2879	0.6779
0.008	133.0052	4154	1.3138	0.6711
0.0082	134.0052	4185	1.3133	0.6779
0.0084	135.0052	4216	1.3118	0.6711
0.0073	136.0052	4247	1.2649	0.6711
0.0082	137.0052	4278	1.3273	0.6779
0.0072	138.0052	4309	1.3363	0.6711
0.0084	139.0052	4340	1.3053	0.6846
0.0069	140.0052	4371	1.2601	0.6779
0.0071	141.0052	4402	1.2748	0.7047
0.007	142.0052	4433	1.2523	0.6846
0.007	143.0052	4464	1.2275	0.7181
0.0065	144.0052	4495	1.2774	0.6779
0.0071	145.0052	4526	1.2965	0.6913
0.0079	146.0052	4557	1.2940	0.6779
0.0073	147.0052	4588	1.3176	0.6913
0.0066	148.0052	4619	1.3858	0.6711
0.0068	149.0052	4650	1.2707	0.6779
0.0071	150.0052	4681	1.3136	0.6711
0.0065	151.0052	4712	1.2763	0.6980
0.0061	152.0052	4743	1.2511	0.6913
0.0062	153.0052	4774	1.3153	0.6846
0.0062	154.0052	4805	1.3124	0.6913
0.0057	155.0052	4836	1.2559	0.6779
0.0061	156.0052	4867	1.2843	0.6711
0.0059	157.0052	4898	1.2882	0.6779
0.0061	158.0052	4929	1.3064	0.6913
0.0059	159.0052	4960	1.2694	0.6779
0.0064	160.0052	4991	1.2823	0.6711
0.0058	161.0052	5022	1.3156	0.6913
0.0057	162.0052	5053	1.2869	0.6913
0.0058	163.0052	5084	1.2940	0.6913
0.0053	164.0052	5115	1.2640	0.6980
0.0057	165.0052	5146	1.2456	0.6913
0.0056	166.0052	5177	1.2819	0.6980
0.0056	167.0052	5208	1.2730	0.6846
0.0055	168.0052	5239	1.2939	0.6846
0.0054	169.0052	5270	1.2879	0.6980
0.0056	170.0052	5301	1.3142	0.7047
0.0054	171.0052	5332	1.3003	0.6980
0.006	172.0052	5363	1.2686	0.6779
0.0054	173.0052	5394	1.2842	0.6846
0.0054	174.0052	5425	1.2889	0.7114
0.0054	175.0052	5456	1.2967	0.6846
0.0054	176.0052	5487	1.3126	0.6913
0.0071	177.0052	5518	1.2822	0.6913
0.0052	178.0052	5549	1.3060	0.6913
0.0052	179.0052	5580	1.2884	0.6980
0.0112	180.0052	5611	1.2783	0.6913
0.0049	181.0052	5642	1.2695	0.6980
0.006	182.0052	5673	1.2844	0.6711
0.0052	183.0052	5704	1.3183	0.6980
0.0051	184.0052	5735	1.3015	0.6779
0.0059	185.0052	5766	1.2990	0.6846
0.0055	186.0052	5797	1.3396	0.6846
0.0051	187.0052	5828	1.3057	0.6980
0.0053	188.0052	5859	1.2746	0.6846
0.0049	189.0052	5890	1.2960	0.6846
0.0053	190.0052	5921	1.3515	0.6846
0.005	191.0052	5952	1.2848	0.6846
0.0049	192.0052	5983	1.2930	0.6846
0.005	193.0028	6000	1.3097	0.6846

Framework versions

Transformers 4.49.0
Pytorch 2.0.1+cu118
Datasets 3.3.2
Tokenizers 0.21.0

ihsanahakiim/videomae-base-finetuned-signlanguage-2

videomae-base-finetuned-signlanguage-2

Model description

Intended uses & limitations

Training and evaluation data

Training procedure

Training hyperparameters

Training results

Framework versions

ihsanahakiim/
videomae-base-finetuned-signlanguage-2