ht-stmini-cls-v6_ftis_noPretrain-tdso-m1drp0.0trp0.0

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

• Loss: 2.3742
• Accuracy: 0.9116
• Macro F1: 0.7864

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: 0.0001
• train_batch_size: 8
• eval_batch_size: 4
• 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_steps: 6733
• training_steps: 134674

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy	Macro F1
62.6403	0.0013	174	56.7836	0.0443	0.0216
26.1102	1.0013	348	124.0118	0.1789	0.0547
8.6719	2.0013	522	200.2045	0.5049	0.1255
7.576	3.0013	696	164.4635	0.5422	0.1325
6.7493	4.0013	870	197.1530	0.5725	0.1388
6.1301	5.0013	1044	176.2657	0.5900	0.1448
5.2532	6.0012	1218	126.3396	0.5783	0.1466
4.933	7.0012	1392	94.1460	0.6039	0.1532
3.8345	8.0012	1566	69.1127	0.6177	0.1562
3.7226	9.0012	1740	50.3189	0.6004	0.1582
3.4296	10.0012	1914	42.1937	0.6176	0.1578
3.1138	11.0012	2088	33.7713	0.6232	0.1741
3.0592	12.0012	2262	26.9765	0.6314	0.1870
2.9529	13.0012	2436	24.9169	0.6246	0.1950
2.7779	14.0012	2610	20.0050	0.6413	0.2076
2.8292	15.0012	2784	18.4746	0.6631	0.2430
2.6306	16.0012	2958	15.9812	0.6677	0.2397
2.5388	17.0012	3132	14.4981	0.6799	0.2767
2.5245	18.0012	3306	16.0667	0.6806	0.2770
2.5363	19.0012	3480	12.8726	0.6848	0.2862
2.3926	20.0011	3654	10.8167	0.7149	0.3186
2.3569	21.0011	3828	10.1099	0.7084	0.3143
2.2546	22.0011	4002	8.9831	0.7395	0.3617
2.0872	23.0011	4176	10.2174	0.7291	0.3766
2.0374	24.0011	4350	8.8943	0.7384	0.3897
2.0311	25.0011	4524	9.6646	0.7537	0.4145
1.9311	26.0011	4698	8.6274	0.7513	0.4106
2.0015	27.0011	4872	11.3291	0.7406	0.4037
1.8797	28.0011	5046	10.2950	0.7561	0.4363
1.8778	29.0011	5220	9.9098	0.7580	0.4276
1.8153	30.0011	5394	9.1804	0.7645	0.4486
1.7197	31.0011	5568	7.9961	0.7619	0.4291
1.6695	32.0011	5742	9.5490	0.7699	0.4686
1.7076	33.0010	5916	8.2911	0.7780	0.4751
1.6238	34.0010	6090	9.8021	0.7815	0.4911
1.5907	35.0010	6264	10.0771	0.7896	0.4934
1.5242	36.0010	6438	9.8011	0.7775	0.4770
1.5165	37.0010	6612	10.7399	0.7659	0.4680
1.474	38.0010	6786	10.7274	0.7941	0.4960
1.4203	39.0010	6960	11.5419	0.7950	0.4930
1.3587	40.0010	7134	10.1150	0.8008	0.5196
1.3311	41.0010	7308	8.6723	0.8078	0.5301
1.2788	42.0010	7482	9.3513	0.8073	0.5236
1.2469	43.0010	7656	8.6972	0.8075	0.5378
1.271	44.0010	7830	9.4428	0.8158	0.5456
1.2388	45.0010	8004	10.2855	0.8114	0.5369
1.2037	46.0010	8178	11.2129	0.8097	0.5401
1.1815	47.0009	8352	11.6078	0.8109	0.5411
1.1735	48.0009	8526	10.8350	0.8110	0.5405
1.1409	49.0009	8700	11.3457	0.8168	0.5452
1.12	50.0009	8874	11.3485	0.8142	0.5559
1.0936	51.0009	9048	12.0677	0.8191	0.5594
1.0655	52.0009	9222	14.4880	0.8216	0.5624
1.0552	53.0009	9396	12.4191	0.8276	0.5723
1.0397	54.0009	9570	12.3578	0.8201	0.5774
1.0131	55.0009	9744	13.9476	0.8338	0.5820
1.0339	56.0009	9918	12.0094	0.8325	0.5843
0.9916	57.0009	10092	11.2168	0.8357	0.5870
0.9806	58.0009	10266	11.1167	0.8371	0.5950
0.9513	59.0009	10440	10.4721	0.8361	0.5947
0.955	60.0008	10614	10.9748	0.8395	0.5982
0.9554	61.0008	10788	11.1069	0.8411	0.6015
0.9299	62.0008	10962	10.6514	0.8414	0.6031
0.9205	63.0008	11136	11.0018	0.8463	0.6117
0.9162	64.0008	11310	11.2923	0.8384	0.6112
0.8943	65.0008	11484	10.8327	0.8486	0.6166
0.887	66.0008	11658	10.2883	0.8399	0.6227
0.8687	67.0008	11832	9.2572	0.8491	0.6199
0.8828	68.0008	12006	8.4879	0.8531	0.6339
0.8622	69.0008	12180	10.2659	0.8509	0.6202
0.859	70.0008	12354	9.6680	0.8547	0.6331
0.8624	71.0008	12528	8.7441	0.8608	0.6419
0.8602	72.0008	12702	9.1228	0.8571	0.6347
0.841	73.0007	12876	8.0354	0.8580	0.6388
0.8225	74.0007	13050	7.5402	0.8548	0.6413
0.825	75.0007	13224	7.4796	0.8541	0.6369
0.8072	76.0007	13398	6.5122	0.8608	0.6470
0.8297	77.0007	13572	6.8775	0.8594	0.6573
0.8147	78.0007	13746	6.1688	0.8617	0.6505
0.8032	79.0007	13920	7.1547	0.8665	0.6560
0.7962	80.0007	14094	6.1545	0.8719	0.6641
0.8004	81.0007	14268	5.8117	0.8703	0.6678
0.7837	82.0007	14442	5.8828	0.8680	0.6648
0.7666	83.0007	14616	5.9117	0.8669	0.6629
0.7688	84.0007	14790	4.9190	0.8644	0.6594
0.7774	85.0007	14964	4.8923	0.8672	0.6627
0.7688	86.0007	15138	5.0258	0.8734	0.6708
0.7602	87.0006	15312	4.8561	0.8730	0.6704
0.7566	88.0006	15486	4.5316	0.8760	0.6769
0.7565	89.0006	15660	4.4197	0.8753	0.6790
0.7616	90.0006	15834	4.8349	0.8738	0.6764
0.7524	91.0006	16008	4.2265	0.8719	0.6776
0.7644	92.0006	16182	4.0898	0.8799	0.6836
0.7408	93.0006	16356	3.9834	0.8776	0.6815
0.7432	94.0006	16530	3.9848	0.8760	0.6834
0.735	95.0006	16704	3.6688	0.8838	0.6891
0.733	96.0006	16878	3.6450	0.8799	0.6861
0.7316	97.0006	17052	3.7666	0.8841	0.6907
0.7218	98.0006	17226	3.6376	0.8811	0.6927
0.7272	99.0006	17400	3.2633	0.8859	0.6946
0.728	100.0005	17574	3.2722	0.8873	0.6937
0.7243	101.0005	17748	3.3194	0.8775	0.6859
0.7223	102.0005	17922	3.6240	0.8815	0.6975
0.7206	103.0005	18096	3.4883	0.8827	0.6929
0.7149	104.0005	18270	3.3674	0.8832	0.6994
0.7139	105.0005	18444	3.3190	0.8806	0.6933
0.7122	106.0005	18618	3.3375	0.8820	0.6906
0.703	107.0005	18792	3.0462	0.8875	0.7058
0.7079	108.0005	18966	3.2106	0.8920	0.7081
0.7082	109.0005	19140	2.8437	0.8920	0.7066
0.7082	110.0005	19314	3.2704	0.8854	0.7067
0.7048	111.0005	19488	3.1294	0.8887	0.7055
0.7003	112.0005	19662	3.2370	0.8828	0.6996
0.6975	113.0005	19836	3.0805	0.8869	0.7127
0.6923	114.0004	20010	3.0712	0.8819	0.7117
0.6928	115.0004	20184	2.8616	0.8892	0.7114
0.6956	116.0004	20358	2.7246	0.8921	0.7168
0.6954	117.0004	20532	3.0441	0.8893	0.7106
0.6814	118.0004	20706	2.7926	0.8924	0.7166
0.6901	119.0004	20880	2.8609	0.8892	0.7180
0.6897	120.0004	21054	2.8714	0.8894	0.7114
0.6926	121.0004	21228	2.7129	0.8951	0.7189
0.6839	122.0004	21402	2.8462	0.8894	0.7185
0.6964	123.0004	21576	2.7631	0.8929	0.7221
0.6899	124.0004	21750	2.7818	0.8926	0.7204
0.6859	125.0004	21924	2.7123	0.8919	0.7198
0.6829	126.0004	22098	2.8556	0.8948	0.7260
0.6792	127.0003	22272	3.0763	0.8918	0.7229
0.682	128.0003	22446	2.8182	0.8982	0.7283
0.6843	129.0003	22620	2.6731	0.8964	0.7315
0.6831	130.0003	22794	2.7623	0.8940	0.7281
0.6838	131.0003	22968	2.7196	0.8955	0.7259
0.6751	132.0003	23142	2.7951	0.8912	0.7240
0.6716	133.0003	23316	2.6659	0.8954	0.7276
0.6736	134.0003	23490	2.7639	0.8977	0.7332
0.6737	135.0003	23664	2.5438	0.8930	0.7249
0.6675	136.0003	23838	2.6129	0.8968	0.7285
0.6698	137.0003	24012	2.4400	0.8977	0.7297
0.6644	138.0003	24186	2.5817	0.8954	0.7314
0.6696	139.0003	24360	2.7131	0.8963	0.7333
0.6734	140.0003	24534	2.4545	0.8998	0.7373
0.6655	141.0002	24708	2.6708	0.8959	0.7323
0.6691	142.0002	24882	2.4522	0.9011	0.7416
0.6654	143.0002	25056	2.5226	0.9016	0.7350
0.6651	144.0002	25230	2.4909	0.8954	0.7345
0.6677	145.0002	25404	2.6339	0.9002	0.7381
0.6619	146.0002	25578	2.4218	0.9017	0.7369
0.6576	147.0002	25752	2.4724	0.8993	0.7337
0.6585	148.0002	25926	2.4362	0.9041	0.7374
0.6547	149.0002	26100	2.7428	0.8999	0.7397
0.6572	150.0002	26274	2.4462	0.9014	0.7377
0.6569	151.0002	26448	2.6013	0.8949	0.7349
0.6589	152.0002	26622	2.6533	0.8994	0.7404
0.6584	153.0002	26796	2.6931	0.8963	0.7398
0.6543	154.0001	26970	2.5390	0.8998	0.7382
0.6504	155.0001	27144	2.6960	0.8944	0.7306
0.6575	156.0001	27318	2.5314	0.8986	0.7413
0.6551	157.0001	27492	2.6421	0.8998	0.7402
0.6475	158.0001	27666	2.6641	0.8972	0.7390
0.6448	159.0001	27840	2.6487	0.8967	0.7433
0.6442	160.0001	28014	2.5520	0.8927	0.7375
0.6518	161.0001	28188	2.4554	0.9030	0.7475
0.6511	162.0001	28362	2.5174	0.8999	0.7476
0.6562	163.0001	28536	2.4203	0.8991	0.7439
0.6432	164.0001	28710	2.4237	0.9016	0.7461
0.6502	165.0001	28884	2.4404	0.9002	0.7416
0.6483	166.0001	29058	2.4390	0.9020	0.7455
0.6464	167.0001	29232	2.4247	0.9010	0.7495
0.6429	168.0000	29406	2.5408	0.8993	0.7466
0.6434	169.0000	29580	2.3080	0.9056	0.7565
0.6454	170.0000	29754	2.4875	0.8955	0.7456
0.6385	171.0000	29928	2.3568	0.9108	0.7537
0.64	172.0000	30102	2.3760	0.9041	0.7461
0.636	173.0000	30276	2.4239	0.8976	0.7442
0.6387	173.0013	30450	2.5413	0.9010	0.7471
0.6398	174.0013	30624	2.4909	0.9070	0.7480
0.6359	175.0013	30798	2.6506	0.8962	0.7358
0.6382	176.0013	30972	2.5119	0.9039	0.7489
0.633	177.0013	31146	2.5947	0.8984	0.7469
0.6361	178.0013	31320	2.5554	0.9026	0.7521
0.6366	179.0013	31494	2.4180	0.9047	0.7550
0.6323	180.0012	31668	2.4029	0.9026	0.7506
0.6329	181.0012	31842	2.5426	0.9018	0.7489
0.6326	182.0012	32016	2.4835	0.8939	0.7426
0.6327	183.0012	32190	2.4586	0.8995	0.7457
0.629	184.0012	32364	2.5432	0.8981	0.7526
0.6279	185.0012	32538	2.5001	0.8986	0.7533
0.6272	186.0012	32712	2.5697	0.9025	0.7580
0.6247	187.0012	32886	2.5125	0.9027	0.7493
0.6314	188.0012	33060	2.5860	0.8989	0.7448
0.6299	189.0012	33234	2.4703	0.9036	0.7491
0.6369	190.0012	33408	2.5086	0.9068	0.7566
0.63	191.0012	33582	2.6345	0.9057	0.7597
0.6285	192.0012	33756	2.6138	0.9025	0.7560
0.6239	193.0012	33930	2.3178	0.9079	0.7616
0.6263	194.0011	34104	2.4827	0.9020	0.7607
0.6257	195.0011	34278	2.3511	0.9023	0.7553
0.6287	196.0011	34452	2.4559	0.8997	0.7536
0.6238	197.0011	34626	2.4863	0.9029	0.7543
0.6236	198.0011	34800	2.3063	0.9074	0.7635
0.6135	199.0011	34974	2.3097	0.9076	0.7659
0.6234	200.0011	35148	2.3661	0.9094	0.7675
0.6227	201.0011	35322	2.3738	0.9000	0.7537
0.6221	202.0011	35496	2.4352	0.9011	0.7524
0.6193	203.0011	35670	2.4006	0.9017	0.7522
0.6215	204.0011	35844	2.3851	0.9039	0.7601
0.6177	205.0011	36018	2.4385	0.9013	0.7585
0.6176	206.0011	36192	2.2627	0.9032	0.7606
0.6163	207.0010	36366	2.2450	0.9065	0.7667
0.6165	208.0010	36540	2.3804	0.8999	0.7590
0.6147	209.0010	36714	2.2930	0.9069	0.7623
0.6187	210.0010	36888	2.4021	0.8994	0.7531
0.6191	211.0010	37062	2.4193	0.9005	0.7589
0.6175	212.0010	37236	2.2153	0.9069	0.7620
0.6192	213.0010	37410	2.4111	0.9035	0.7638
0.6121	214.0010	37584	2.4468	0.9024	0.7580
0.6098	215.0010	37758	2.3195	0.9043	0.7695
0.6115	216.0010	37932	2.3559	0.9025	0.7626
0.6093	217.0010	38106	2.3240	0.9036	0.7635
0.61	218.0010	38280	2.3471	0.9049	0.7658
0.6104	219.0010	38454	2.3511	0.9057	0.7708
0.6394	220.0010	38628	2.3150	0.9046	0.7695
0.6087	221.0009	38802	2.3065	0.9064	0.7693
0.6057	222.0009	38976	2.5033	0.9020	0.7674
0.6039	223.0009	39150	2.3096	0.9038	0.7651
0.6091	224.0009	39324	2.3658	0.9009	0.7679
0.6059	225.0009	39498	2.2758	0.9063	0.7699
0.607	226.0009	39672	2.2320	0.9086	0.7691
0.6051	227.0009	39846	2.2790	0.9072	0.7679
0.6139	228.0009	40020	2.2307	0.9092	0.7722
0.598	229.0009	40194	2.2525	0.9049	0.7712
0.6053	230.0009	40368	2.3155	0.9046	0.7667
0.6059	231.0009	40542	2.2843	0.9089	0.7694
0.605	232.0009	40716	2.2248	0.9112	0.7799
0.6021	233.0009	40890	2.2576	0.9085	0.7767
0.605	234.0008	41064	2.1415	0.9109	0.7746
0.5998	235.0008	41238	2.2932	0.9076	0.7733
0.6054	236.0008	41412	2.2941	0.9117	0.7802
0.6029	237.0008	41586	2.4787	0.9049	0.7701
0.6046	238.0008	41760	2.3346	0.9068	0.7652
0.6103	239.0008	41934	2.3546	0.9065	0.7708
0.6076	240.0008	42108	2.1917	0.9080	0.7790
0.611	241.0008	42282	2.3109	0.9110	0.7787
0.5955	242.0008	42456	2.2692	0.9092	0.7832
0.5995	243.0008	42630	2.3765	0.9087	0.7755
0.5974	244.0008	42804	2.3788	0.9042	0.7677
0.6018	245.0008	42978	2.1839	0.9132	0.7787
0.599	246.0008	43152	2.2628	0.9080	0.7791
0.5951	247.0007	43326	2.1852	0.9079	0.7748
0.5996	248.0007	43500	2.3220	0.9072	0.7746
0.5987	249.0007	43674	2.2736	0.9081	0.7760
0.5959	250.0007	43848	2.2076	0.9098	0.7807
0.5907	251.0007	44022	2.1656	0.9069	0.7769
0.5932	252.0007	44196	2.1178	0.9103	0.7785
0.6031	253.0007	44370	2.2880	0.9063	0.7757
0.5913	254.0007	44544	2.0688	0.9129	0.7846
0.5869	255.0007	44718	2.5926	0.8980	0.7594
0.5991	256.0007	44892	2.2636	0.9069	0.7743
0.5933	257.0007	45066	2.3013	0.9090	0.7726
0.5897	258.0007	45240	2.1531	0.9116	0.7787
0.5929	259.0007	45414	2.1821	0.9117	0.7805
0.5877	260.0007	45588	2.2698	0.9074	0.7730
0.5917	261.0006	45762	2.2937	0.9061	0.7710
0.5874	262.0006	45936	2.2435	0.9070	0.7770
0.5879	263.0006	46110	2.3501	0.9045	0.7701
0.5929	264.0006	46284	2.2587	0.9061	0.7745
0.578	265.0006	46458	2.3028	0.9034	0.7691
0.5872	266.0006	46632	2.2389	0.9070	0.7748
0.5882	267.0006	46806	2.2594	0.9087	0.7792
0.5891	268.0006	46980	2.3582	0.9033	0.7724
0.5835	269.0006	47154	2.1972	0.9074	0.7784
0.5845	270.0006	47328	2.1843	0.9116	0.7864
0.5845	271.0006	47502	2.2557	0.9083	0.7776
0.5863	272.0006	47676	2.2286	0.9094	0.7806
0.5939	273.0006	47850	2.2552	0.9087	0.7781
0.5841	274.0005	48024	2.2262	0.9078	0.7738
0.5859	275.0005	48198	2.1922	0.9096	0.7780
0.5879	276.0005	48372	2.3511	0.9076	0.7737
0.5866	277.0005	48546	2.1917	0.9097	0.7750
0.5827	278.0005	48720	2.2781	0.9083	0.7721
0.5879	279.0005	48894	2.2850	0.9085	0.7776
0.589	280.0005	49068	2.2713	0.9080	0.7756
0.5825	281.0005	49242	2.3422	0.9072	0.7740
0.5817	282.0005	49416	2.3344	0.9052	0.7698
0.5792	283.0005	49590	2.2083	0.9104	0.7767
0.5746	284.0005	49764	2.2761	0.9083	0.7747
0.5739	285.0005	49938	2.2341	0.9072	0.7737
0.5757	286.0005	50112	2.1585	0.9075	0.7795
0.5824	287.0005	50286	2.3038	0.9065	0.7755
0.5795	288.0004	50460	2.2927	0.9086	0.7760
0.5851	289.0004	50634	2.2379	0.9052	0.7718
0.5777	290.0004	50808	2.1485	0.9098	0.7813

Framework versions

• Transformers 4.46.0
• Pytorch 2.3.1+cu121
• Datasets 2.20.0
• Tokenizers 0.20.1