SignBart-LSA-64

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

• Loss: 0.2409
• Accuracy: 0.9615
• Precision: 0.9682
• Recall: 0.9615

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: 0.0002
• train_batch_size: 256
• eval_batch_size: 256
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: cosine
• lr_scheduler_warmup_ratio: 0.2
• num_epochs: 1000

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy	Precision	Recall
4.2172	1.0	9	4.2018	0.0	0.0	0.0
4.2136	2.0	18	4.2010	0.0	0.0	0.0
4.214	3.0	27	4.1997	0.0	0.0	0.0
4.2096	4.0	36	4.1979	0.0	0.0	0.0
4.2102	5.0	45	4.1954	0.0	0.0	0.0
4.2123	6.0	54	4.1925	0.0	0.0	0.0
4.2094	7.0	63	4.1889	0.0010	0.0010	0.0010
4.2062	8.0	72	4.1849	0.0031	0.0012	0.0031
4.2003	9.0	81	4.1804	0.0052	0.0018	0.0052
4.1971	10.0	90	4.1754	0.0063	0.0017	0.0063
4.1982	11.0	99	4.1699	0.0083	0.0019	0.0083
4.1818	12.0	108	4.1638	0.0167	0.0032	0.0167
4.1876	13.0	117	4.1574	0.0219	0.0040	0.0219
4.1747	14.0	126	4.1503	0.025	0.0041	0.025
4.1659	15.0	135	4.1429	0.0281	0.0039	0.0281
4.1609	16.0	144	4.1351	0.0344	0.0040	0.0344
4.1506	17.0	153	4.1266	0.0406	0.0193	0.0406
4.154	18.0	162	4.1176	0.0583	0.0389	0.0583
4.1401	19.0	171	4.1076	0.0594	0.0364	0.0594
4.1274	20.0	180	4.0969	0.0594	0.0260	0.0594
4.1199	21.0	189	4.0854	0.0615	0.0181	0.0615
4.1081	22.0	198	4.0732	0.0698	0.0216	0.0698
4.0985	23.0	207	4.0593	0.0719	0.0215	0.0719
4.0862	24.0	216	4.0443	0.0854	0.0307	0.0854
4.0822	25.0	225	4.0284	0.1094	0.0452	0.1094
4.0548	26.0	234	4.0109	0.1281	0.0703	0.1281
4.0267	27.0	243	3.9911	0.1344	0.0691	0.1344
4.0132	28.0	252	3.9692	0.1406	0.0716	0.1406
4.0086	29.0	261	3.9459	0.1531	0.0812	0.1531
3.9763	30.0	270	3.9213	0.1521	0.0704	0.1521
3.9624	31.0	279	3.8940	0.1615	0.0797	0.1615
3.9275	32.0	288	3.8653	0.1583	0.0870	0.1583
3.9263	33.0	297	3.8366	0.1573	0.0966	0.1573
3.8771	34.0	306	3.8047	0.1656	0.1045	0.1656
3.872	35.0	315	3.7709	0.175	0.1187	0.175
3.8443	36.0	324	3.7360	0.1802	0.1326	0.1802
3.8155	37.0	333	3.7009	0.1927	0.1457	0.1927
3.7737	38.0	342	3.6639	0.2042	0.1560	0.2042
3.7519	39.0	351	3.6270	0.2135	0.1454	0.2135
3.7261	40.0	360	3.5904	0.2198	0.1583	0.2198
3.6808	41.0	369	3.5540	0.2260	0.1886	0.2260
3.6687	42.0	378	3.5190	0.2458	0.2351	0.2458
3.6037	43.0	387	3.4840	0.2615	0.2549	0.2615
3.5966	44.0	396	3.4515	0.2656	0.2585	0.2656
3.6106	45.0	405	3.4204	0.2844	0.2754	0.2844
3.5682	46.0	414	3.3888	0.2938	0.2750	0.2938
3.5059	47.0	423	3.3578	0.3052	0.3334	0.3052
3.5069	48.0	432	3.3258	0.3187	0.3557	0.3187
3.49	49.0	441	3.2957	0.3427	0.3487	0.3427
3.4691	50.0	450	3.2648	0.3563	0.3854	0.3563
3.4124	51.0	459	3.2320	0.3677	0.3837	0.3677
3.3699	52.0	468	3.1962	0.3844	0.3843	0.3844
3.3603	53.0	477	3.1609	0.4073	0.4014	0.4073
3.3471	54.0	486	3.1269	0.4177	0.4033	0.4177
3.2801	55.0	495	3.0938	0.425	0.4281	0.425
3.2711	56.0	504	3.0582	0.4437	0.4322	0.4437
3.2693	57.0	513	3.0254	0.4510	0.4874	0.4510
3.2246	58.0	522	2.9963	0.4625	0.4903	0.4625
3.1744	59.0	531	2.9585	0.4906	0.5313	0.4906
3.1366	60.0	540	2.9218	0.5042	0.5419	0.5042
3.1226	61.0	549	2.8878	0.5302	0.5937	0.5302
3.0467	62.0	558	2.8518	0.5542	0.6232	0.5542
3.0471	63.0	567	2.8120	0.5729	0.6449	0.5729
3.0399	64.0	576	2.7763	0.5781	0.6647	0.5781
2.9649	65.0	585	2.7373	0.6135	0.6656	0.6135
2.9504	66.0	594	2.7027	0.6177	0.6883	0.6177
2.9176	67.0	603	2.6628	0.6354	0.7052	0.6354
2.9244	68.0	612	2.6323	0.6542	0.7287	0.6542
2.8611	69.0	621	2.5924	0.6760	0.7324	0.6760
2.8989	70.0	630	2.5576	0.6875	0.7508	0.6875
2.7687	71.0	639	2.5221	0.7031	0.7665	0.7031
2.7654	72.0	648	2.4863	0.7146	0.7857	0.7146
2.7292	73.0	657	2.4485	0.7240	0.7910	0.7240
2.6447	74.0	666	2.4061	0.7344	0.7961	0.7344
2.7717	75.0	675	2.3737	0.7406	0.7947	0.7406
2.5778	76.0	684	2.3312	0.7490	0.8071	0.7490
2.6746	77.0	693	2.2978	0.7531	0.8055	0.7531
2.6079	78.0	702	2.2624	0.7635	0.7928	0.7635
2.5206	79.0	711	2.2256	0.7635	0.8078	0.7635
2.5532	80.0	720	2.1870	0.7667	0.8043	0.7667
2.4121	81.0	729	2.1464	0.7823	0.7978	0.7823
2.4203	82.0	738	2.1060	0.7823	0.7964	0.7823
2.433	83.0	747	2.0701	0.7885	0.8162	0.7885
2.3695	84.0	756	2.0274	0.7969	0.8212	0.7969
2.3072	85.0	765	1.9860	0.7979	0.8245	0.7979
2.2647	86.0	774	1.9457	0.8010	0.8280	0.8010
2.2401	87.0	783	1.9080	0.8042	0.8113	0.8042
2.1957	88.0	792	1.8656	0.8083	0.8220	0.8083
2.2112	89.0	801	1.8304	0.825	0.8577	0.825
2.1939	90.0	810	1.7934	0.8240	0.8373	0.8240
2.1612	91.0	819	1.7592	0.8313	0.8473	0.8313
2.1678	92.0	828	1.7257	0.8344	0.8523	0.8344
1.9956	93.0	837	1.6915	0.8323	0.8503	0.8323
2.0315	94.0	846	1.6535	0.8396	0.8737	0.8396
2.0363	95.0	855	1.6182	0.8406	0.8679	0.8406
1.9001	96.0	864	1.5784	0.8552	0.8659	0.8552
1.9939	97.0	873	1.5477	0.8635	0.8764	0.8635
1.8149	98.0	882	1.5087	0.8615	0.8813	0.8615
1.7856	99.0	891	1.4704	0.8667	0.8958	0.8667
1.8717	100.0	900	1.4419	0.8740	0.8874	0.8740
1.8364	101.0	909	1.4115	0.8771	0.9048	0.8771
1.8102	102.0	918	1.3775	0.8812	0.9070	0.8812
1.6851	103.0	927	1.3444	0.8812	0.9100	0.8812
1.7903	104.0	936	1.3126	0.8865	0.8962	0.8865
1.599	105.0	945	1.2809	0.8833	0.8936	0.8833
1.6684	106.0	954	1.2526	0.8875	0.9000	0.8875
1.586	107.0	963	1.2219	0.8906	0.9173	0.8906
1.6537	108.0	972	1.1907	0.8938	0.9187	0.8938
1.5607	109.0	981	1.1576	0.8938	0.9194	0.8938
1.5173	110.0	990	1.1245	0.8885	0.9180	0.8885
1.5684	111.0	999	1.1026	0.8969	0.9214	0.8969
1.4264	112.0	1008	1.0762	0.8938	0.9046	0.8938
1.4395	113.0	1017	1.0419	0.8969	0.9255	0.8969
1.3977	114.0	1026	1.0220	0.9042	0.9310	0.9042
1.393	115.0	1035	0.9960	0.8969	0.9259	0.8969
1.3971	116.0	1044	0.9699	0.8938	0.9085	0.8938
1.3164	117.0	1053	0.9460	0.9073	0.9316	0.9073
1.3501	118.0	1062	0.9223	0.9146	0.9347	0.9146
1.3063	119.0	1071	0.9005	0.9135	0.9347	0.9135
1.2035	120.0	1080	0.8777	0.9042	0.9325	0.9042
1.256	121.0	1089	0.8522	0.9187	0.9393	0.9187
1.3574	122.0	1098	0.8342	0.9083	0.9352	0.9083
1.1034	123.0	1107	0.8075	0.9219	0.9431	0.9219
1.1476	124.0	1116	0.7891	0.9219	0.9430	0.9219
1.1662	125.0	1125	0.7708	0.9156	0.9389	0.9156
1.0712	126.0	1134	0.7576	0.9167	0.9383	0.9167
1.237	127.0	1143	0.7308	0.9260	0.9442	0.9260
1.1346	128.0	1152	0.7135	0.9281	0.9468	0.9281
1.1347	129.0	1161	0.6959	0.9271	0.9454	0.9271
1.2701	130.0	1170	0.6794	0.9302	0.9475	0.9302
1.0452	131.0	1179	0.6618	0.9292	0.9481	0.9292
1.1644	132.0	1188	0.6548	0.9271	0.9459	0.9271
0.9179	133.0	1197	0.6360	0.9344	0.9511	0.9344
0.966	134.0	1206	0.6170	0.9344	0.9499	0.9344
0.9089	135.0	1215	0.6055	0.9323	0.9496	0.9323
0.9997	136.0	1224	0.5930	0.9396	0.9531	0.9396
1.0059	137.0	1233	0.5785	0.9396	0.9531	0.9396
0.9378	138.0	1242	0.5622	0.9365	0.9521	0.9365
0.829	139.0	1251	0.5529	0.9427	0.9572	0.9427
0.9263	140.0	1260	0.5333	0.9437	0.9552	0.9437
0.8812	141.0	1269	0.5216	0.9427	0.9561	0.9427
0.7713	142.0	1278	0.5169	0.9396	0.9530	0.9396
0.9065	143.0	1287	0.4998	0.9437	0.9545	0.9437
0.7999	144.0	1296	0.4795	0.9427	0.9544	0.9427
0.8947	145.0	1305	0.4764	0.9427	0.9552	0.9427
0.8302	146.0	1314	0.4815	0.9344	0.9500	0.9344
0.8456	147.0	1323	0.4596	0.9406	0.9534	0.9406
0.8714	148.0	1332	0.4428	0.9469	0.9589	0.9469
0.7087	149.0	1341	0.4278	0.9458	0.9558	0.9458
0.687	150.0	1350	0.4264	0.95	0.9623	0.95
0.7781	151.0	1359	0.4171	0.9479	0.9583	0.9479
0.8492	152.0	1368	0.4182	0.9469	0.9579	0.9469
0.7646	153.0	1377	0.4007	0.9521	0.9625	0.9521
0.7051	154.0	1386	0.3871	0.9521	0.9629	0.9521
0.7996	155.0	1395	0.3938	0.9458	0.9581	0.9458
0.7274	156.0	1404	0.3866	0.9458	0.9574	0.9458
0.7145	157.0	1413	0.3720	0.95	0.9600	0.95
0.6641	158.0	1422	0.3641	0.9521	0.9616	0.9521
0.5893	159.0	1431	0.3602	0.9542	0.9628	0.9542
0.7172	160.0	1440	0.3505	0.9510	0.9606	0.9510
0.5651	161.0	1449	0.3555	0.9510	0.9621	0.9510
0.5715	162.0	1458	0.3305	0.9521	0.9615	0.9521
0.7592	163.0	1467	0.3361	0.95	0.9599	0.95
0.6483	164.0	1476	0.3233	0.9594	0.9668	0.9594
0.6461	165.0	1485	0.3092	0.9594	0.9662	0.9594
0.5082	166.0	1494	0.3163	0.9552	0.9642	0.9552
0.4968	167.0	1503	0.3108	0.9583	0.9675	0.9583
0.8144	168.0	1512	0.3122	0.9583	0.9669	0.9583
0.527	169.0	1521	0.2953	0.9594	0.9670	0.9594
0.5664	170.0	1530	0.2821	0.9656	0.9721	0.9656
0.5977	171.0	1539	0.2878	0.9604	0.9687	0.9604
0.7829	172.0	1548	0.2971	0.9573	0.9660	0.9573
0.445	173.0	1557	0.2968	0.9563	0.9642	0.9563
0.4656	174.0	1566	0.2810	0.9615	0.9698	0.9615
0.5326	175.0	1575	0.2783	0.9646	0.9725	0.9646
0.4816	176.0	1584	0.2559	0.9656	0.9719	0.9656
0.5455	177.0	1593	0.2617	0.9604	0.9672	0.9604
0.5358	178.0	1602	0.2664	0.9573	0.9648	0.9573
0.4914	179.0	1611	0.2563	0.9635	0.9711	0.9635
0.4054	180.0	1620	0.2510	0.9552	0.9623	0.9552
0.5358	181.0	1629	0.2511	0.9542	0.9628	0.9542
0.4147	182.0	1638	0.2484	0.9573	0.9641	0.9573
0.555	183.0	1647	0.2487	0.9563	0.9639	0.9563
0.4153	184.0	1656	0.2373	0.9646	0.9717	0.9646
0.6092	185.0	1665	0.2366	0.9604	0.9681	0.9604
0.638	186.0	1674	0.2390	0.9677	0.9737	0.9677
0.5667	187.0	1683	0.2395	0.9656	0.9720	0.9656
0.4094	188.0	1692	0.2415	0.9635	0.9704	0.9635
0.5311	189.0	1701	0.2457	0.9594	0.9678	0.9594
0.4081	190.0	1710	0.2409	0.9615	0.9682	0.9615

Framework versions

• Transformers 4.45.1
• Pytorch 2.4.0
• Datasets 3.0.1
• Tokenizers 0.20.0