ht-stmini-cls-v6_ftis_noPretrain-tdso-m1drp0.5trp0.5

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

• Loss: 2.4235
• Accuracy: 0.9443
• Macro F1: 0.8652

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: 134675

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy	Macro F1
43.2853	0.0015	202	72.2821	0.0578	0.0260
11.3531	1.0015	404	183.9046	0.3842	0.1067
7.7616	2.0015	606	296.1333	0.5161	0.1272
6.8436	3.0015	808	338.5297	0.5695	0.1373
6.1521	4.0015	1010	241.5134	0.5859	0.1465
5.1682	5.0015	1212	163.7811	0.6014	0.1526
4.4783	6.0015	1414	103.7835	0.6049	0.1561
3.8324	7.0015	1616	74.2983	0.6069	0.1599
3.4638	8.0015	1818	51.5712	0.6063	0.1702
3.3046	9.0015	2020	37.5402	0.6216	0.1695
3.0795	10.0015	2222	27.0707	0.6405	0.1865
2.9634	11.0015	2424	22.7454	0.6465	0.1978
2.8201	12.0015	2626	17.4222	0.6586	0.2076
2.7821	13.0015	2828	14.4185	0.6399	0.2073
2.7301	14.0015	3030	11.6616	0.6770	0.2476
2.5645	15.0015	3232	9.8802	0.6865	0.2912
2.537	16.0015	3434	11.5990	0.7016	0.3127
2.3898	17.0015	3636	9.5902	0.7334	0.3404
2.2816	18.0015	3838	9.6463	0.7088	0.3426
2.2398	19.0015	4040	8.2580	0.7471	0.4034
2.145	20.0015	4242	8.4411	0.7494	0.3975
2.0978	21.0015	4444	8.0135	0.7285	0.4085
1.9472	22.0015	4646	7.7603	0.7718	0.4463
1.9554	23.0015	4848	7.2962	0.7864	0.4697
1.8458	24.0015	5050	7.1245	0.7894	0.4739
1.8258	25.0015	5252	7.2591	0.8065	0.5112
1.7876	26.0015	5454	6.8281	0.7971	0.5011
1.7299	27.0015	5656	7.0918	0.8017	0.5122
1.6427	28.0015	5858	8.0051	0.8023	0.5172
1.5989	29.0015	6060	8.2211	0.8095	0.5343
1.5664	30.0015	6262	9.7400	0.8138	0.5421
1.5366	31.0015	6464	8.9349	0.8272	0.5781
1.5739	32.0015	6666	9.5120	0.8139	0.5638
1.4858	33.0015	6868	11.8903	0.8310	0.5804
1.4514	34.0015	7070	11.1792	0.8451	0.6121
1.3623	35.0015	7272	10.1040	0.8353	0.6101
1.2955	36.0015	7474	10.4790	0.8161	0.5803
1.275	37.0015	7676	12.7349	0.8453	0.6270
1.2641	38.0015	7878	12.2775	0.8367	0.6193
1.2392	39.0015	8080	12.2088	0.8483	0.6347
1.1719	40.0015	8282	10.6927	0.8626	0.6627
1.1527	41.0015	8484	13.6029	0.8576	0.6611
1.1091	42.0015	8686	11.9136	0.8639	0.6646
1.1421	43.0015	8888	12.1072	0.8674	0.6799
1.0815	44.0015	9090	11.9381	0.8624	0.6786
1.0497	45.0015	9292	11.5159	0.8681	0.6719
1.0198	46.0015	9494	12.7141	0.8692	0.6863
1.0317	47.0015	9696	10.0744	0.8713	0.6898
1.0344	48.0015	9898	9.1169	0.8710	0.6954
0.9841	49.0015	10100	11.0608	0.8822	0.7021
0.9621	50.0015	10302	10.9688	0.8806	0.7052
0.9527	51.0015	10504	11.1877	0.8883	0.7215
0.939	52.0015	10706	11.8438	0.8830	0.7138
0.9152	53.0015	10908	9.7798	0.8912	0.7263
0.9008	54.0015	11110	8.2620	0.8935	0.7307
0.9039	55.0015	11312	8.3810	0.8983	0.7413
0.8985	56.0015	11514	9.2391	0.8945	0.7266
0.8929	57.0015	11716	8.9072	0.8961	0.7360
0.8769	58.0015	11918	8.8795	0.8928	0.7338
0.8501	59.0015	12120	10.4380	0.8998	0.7491
0.8528	60.0015	12322	8.4509	0.8976	0.7448
0.8453	61.0015	12524	6.9527	0.9007	0.7494
0.8261	62.0015	12726	6.6855	0.9030	0.7567
0.8289	63.0015	12928	7.4025	0.9013	0.7546
0.8255	64.0015	13130	7.3783	0.9014	0.7559
0.819	65.0015	13332	6.4510	0.8949	0.7471
0.8055	66.0015	13534	6.3875	0.9079	0.7657
0.8075	67.0015	13736	5.5012	0.9053	0.7586
0.789	68.0015	13938	6.3053	0.9067	0.7672
0.7876	69.0015	14140	6.1137	0.9028	0.7641
0.7937	70.0015	14342	5.4490	0.9074	0.7741
0.794	71.0015	14544	4.8522	0.9088	0.7717
0.7793	72.0015	14746	5.3337	0.9117	0.7771
0.7702	73.0015	14948	5.0454	0.9103	0.7785
0.7742	74.0015	15150	5.4170	0.9041	0.7582
0.7639	75.0015	15352	5.0985	0.9132	0.7854
0.7653	76.0015	15554	4.3750	0.9052	0.7507
0.7648	77.0015	15756	4.5401	0.9101	0.7592
0.7552	78.0015	15958	4.5033	0.9099	0.7733
0.7613	79.0015	16160	4.3565	0.9110	0.7762
0.755	80.0015	16362	4.2386	0.9081	0.7810
0.7482	81.0015	16564	3.8732	0.9147	0.7855
0.7465	82.0015	16766	4.2196	0.9178	0.7928
0.7449	83.0015	16968	3.7305	0.9156	0.7902
0.7527	84.0015	17170	3.7698	0.9132	0.7907
0.7324	85.0015	17372	3.9383	0.9145	0.7859
0.7392	86.0015	17574	3.7822	0.9168	0.7895
0.7481	87.0015	17776	3.4162	0.9198	0.8044
0.7295	88.0015	17978	3.7789	0.9185	0.7953
0.7301	89.0015	18180	3.1398	0.9200	0.7988
0.7179	90.0015	18382	3.6025	0.9184	0.7977
0.7269	91.0015	18584	3.3802	0.9208	0.8058
0.7305	92.0015	18786	3.3714	0.9179	0.7973
0.7191	93.0015	18988	3.7397	0.9205	0.8032
0.729	94.0015	19190	3.4946	0.9140	0.7942
0.7214	95.0015	19392	2.9989	0.9224	0.8079
0.7167	96.0015	19594	3.1224	0.9207	0.8057
0.7151	97.0015	19796	3.0803	0.9236	0.8059
0.7093	98.0015	19998	3.1858	0.9216	0.8094
0.7126	99.0015	20200	3.3136	0.9244	0.8123
0.7063	100.0015	20402	3.0639	0.9242	0.8138
0.7162	101.0015	20604	3.1035	0.9230	0.8071
0.709	102.0015	20806	2.9842	0.9236	0.8158
0.7072	103.0015	21008	3.2557	0.9220	0.8083
0.7044	104.0015	21210	2.8068	0.9260	0.8144
0.7011	105.0015	21412	3.0918	0.9192	0.7983
0.7009	106.0015	21614	3.3151	0.9188	0.8036
0.6977	107.0015	21816	3.0055	0.9226	0.8153
0.7013	108.0015	22018	3.4072	0.9161	0.8031
0.6872	109.0015	22220	2.8057	0.9213	0.8086
0.6951	110.0015	22422	2.7210	0.9203	0.8062
0.6932	111.0015	22624	3.1909	0.9228	0.8178
0.6873	112.0015	22826	2.7345	0.9239	0.8105
0.698	113.0015	23028	2.8222	0.9222	0.8119
0.6977	114.0015	23230	2.7029	0.9225	0.8126
0.6897	115.0015	23432	2.9469	0.9297	0.8180
0.6928	116.0015	23634	2.6512	0.9232	0.8150
0.6896	117.0015	23836	2.8380	0.9215	0.8125
0.696	118.0015	24038	2.7226	0.9266	0.8183
0.6881	119.0015	24240	2.7402	0.9247	0.8199
0.687	120.0015	24442	2.7833	0.9261	0.8236
0.6818	121.0015	24644	2.9167	0.9292	0.8215
0.6797	122.0015	24846	2.6610	0.9251	0.8175
0.6806	123.0015	25048	2.8481	0.9282	0.8256
0.682	124.0015	25250	2.8414	0.9323	0.8271
0.6787	125.0015	25452	2.8047	0.9269	0.8218
0.6845	126.0015	25654	2.7319	0.9266	0.8177
0.6782	127.0015	25856	2.5254	0.9264	0.7981
0.6836	128.0015	26058	2.5662	0.9307	0.8281
0.6702	129.0015	26260	2.8811	0.9237	0.8197
0.6767	130.0015	26462	2.6903	0.9285	0.8254
0.6738	131.0015	26664	2.7479	0.9307	0.8276
0.6774	132.0015	26866	2.5960	0.9304	0.8312
0.6704	133.0015	27068	2.8442	0.9294	0.8264
0.6684	134.0015	27270	2.7251	0.9328	0.8316
0.6693	135.0015	27472	2.8060	0.9299	0.8120
0.6705	136.0015	27674	2.7968	0.9265	0.8245
0.667	137.0015	27876	2.7596	0.9311	0.8343
0.6714	138.0015	28078	2.5643	0.9328	0.8151
0.6737	139.0015	28280	2.4489	0.9309	0.8138
0.6727	140.0015	28482	2.8243	0.9264	0.8197
0.6715	141.0015	28684	2.7018	0.9346	0.8182
0.6693	142.0015	28886	2.7721	0.9293	0.8286
0.6673	143.0015	29088	2.4769	0.9326	0.8361
0.6646	144.0015	29290	2.4916	0.9268	0.8011
0.6612	145.0015	29492	2.5472	0.9301	0.8110
0.6651	146.0015	29694	2.7626	0.9282	0.8304
0.6613	147.0015	29896	2.3738	0.9272	0.8237
0.6626	148.0015	30098	2.7838	0.9293	0.8118
0.6675	149.0015	30300	2.9327	0.9336	0.8364
0.6673	150.0015	30502	3.0875	0.9311	0.8280
0.6612	151.0015	30704	2.6303	0.9304	0.8142
0.6587	152.0015	30906	2.7778	0.9313	0.8160
0.6613	153.0015	31108	2.4631	0.9307	0.8287
0.6632	154.0015	31310	2.8252	0.9338	0.8181
0.6539	155.0015	31512	2.7722	0.9343	0.8387
0.6539	156.0015	31714	2.7446	0.9320	0.8296
0.6542	157.0015	31916	2.4772	0.9329	0.8371
0.6586	158.0015	32118	2.6693	0.9354	0.8362
0.6529	159.0015	32320	2.4620	0.9300	0.8313
0.6486	160.0015	32522	2.4187	0.9333	0.8334
0.6562	161.0015	32724	2.4622	0.9330	0.8351
0.6605	162.0015	32926	2.3617	0.9360	0.8409
0.6522	163.0015	33128	2.5354	0.9332	0.8333
0.6543	164.0015	33330	2.3246	0.9355	0.8394
0.6552	165.0015	33532	2.3555	0.9326	0.8341
0.6508	166.0015	33734	2.4460	0.9368	0.8205
0.6516	167.0015	33936	2.5803	0.9334	0.8365
0.6518	168.0015	34138	2.5872	0.9345	0.8385
0.6556	169.0015	34340	2.3757	0.9379	0.8212
0.6514	170.0015	34542	2.4257	0.9365	0.8207
0.6464	171.0015	34744	2.3747	0.9356	0.8414
0.649	172.0015	34946	2.5538	0.9374	0.8396
0.6465	173.0015	35148	2.6072	0.9342	0.8389
0.6437	174.0015	35350	2.5343	0.9339	0.8416
0.6476	175.0015	35552	2.3341	0.9345	0.8414
0.6489	176.0015	35754	2.4761	0.9323	0.8365
0.6442	177.0015	35956	2.7341	0.9347	0.8406
0.6401	178.0015	36158	2.4527	0.9351	0.8427
0.6424	179.0015	36360	2.4496	0.9354	0.8437
0.6433	180.0015	36562	2.3992	0.9368	0.8450
0.6364	181.0015	36764	2.3422	0.9360	0.8371
0.6453	182.0015	36966	2.2387	0.9339	0.8215
0.64	183.0015	37168	2.3683	0.9377	0.8256
0.6431	184.0015	37370	2.4120	0.9367	0.8438
0.6394	185.0015	37572	2.4415	0.9346	0.8438
0.6389	186.0015	37774	2.5479	0.9361	0.8463
0.6363	187.0015	37976	2.4861	0.9375	0.8466
0.6387	188.0015	38178	2.5486	0.9356	0.8404
0.6399	189.0015	38380	2.5733	0.9371	0.8440
0.6358	190.0015	38582	2.5241	0.9379	0.8215
0.6322	191.0015	38784	2.5134	0.9394	0.8476
0.6303	192.0015	38986	2.5565	0.9365	0.8463
0.6367	193.0015	39188	2.3788	0.9377	0.8274
0.6389	194.0015	39390	2.7886	0.9382	0.8279
0.6335	195.0015	39592	2.6757	0.9387	0.8313
0.632	196.0015	39794	2.6494	0.9361	0.8260
0.6381	197.0015	39996	2.3435	0.9344	0.8391
0.6264	198.0015	40198	2.4460	0.9393	0.8486
0.6323	199.0015	40400	2.5763	0.9377	0.8452
0.6216	200.0015	40602	2.5581	0.9321	0.8373
0.6436	201.0015	40804	2.6015	0.9366	0.8432
0.633	202.0015	41006	2.4508	0.9384	0.8238
0.6259	203.0015	41208	2.3502	0.9375	0.8454
0.6297	204.0015	41410	2.4568	0.9396	0.8299
0.6203	205.0015	41612	2.1617	0.9413	0.8363
0.6311	206.0015	41814	2.5255	0.9387	0.8323
0.6245	207.0015	42016	2.4640	0.9400	0.8340
0.6233	208.0015	42218	2.3665	0.9377	0.8316
0.6307	209.0015	42420	2.2082	0.9394	0.8275
0.6263	210.0015	42622	2.2723	0.9389	0.8516
0.6245	211.0015	42824	2.3421	0.9358	0.8473
0.624	212.0015	43026	2.3680	0.9345	0.8394
0.6233	213.0015	43228	2.4448	0.9426	0.8360
0.621	214.0015	43430	2.2144	0.9374	0.8494
0.6253	215.0015	43632	2.5043	0.9358	0.8294
0.6255	216.0015	43834	2.4814	0.9353	0.8461
0.6228	217.0015	44036	2.2161	0.9352	0.8473
0.6227	218.0015	44238	2.4652	0.9394	0.8490
0.627	219.0015	44440	2.4980	0.9395	0.8507
0.6191	220.0015	44642	2.5161	0.9393	0.8282
0.6187	221.0015	44844	2.3815	0.9373	0.8460
0.6238	222.0015	45046	2.5998	0.9389	0.8450
0.6213	223.0015	45248	2.2785	0.9397	0.8518
0.6169	224.0015	45450	2.4286	0.9375	0.8444
0.6207	225.0015	45652	2.2681	0.9379	0.8255
0.6183	226.0015	45854	2.3262	0.9375	0.8278
0.6173	227.0015	46056	2.5640	0.9370	0.8270
0.6152	228.0015	46258	2.4490	0.9389	0.8473
0.6192	229.0015	46460	2.2929	0.9405	0.8269
0.6198	230.0015	46662	2.5070	0.9356	0.8490
0.6169	231.0015	46864	2.4588	0.9369	0.8486
0.6181	232.0015	47066	2.5950	0.9378	0.8499
0.6123	233.0015	47268	2.5675	0.9420	0.8550
0.6198	234.0015	47470	2.6166	0.9386	0.8518
0.6155	235.0015	47672	2.3451	0.9413	0.8535
0.6161	236.0015	47874	2.3903	0.9432	0.8575
0.6107	237.0015	48076	2.5790	0.9424	0.8588
0.6169	238.0015	48278	2.6280	0.9402	0.8528
0.6184	239.0015	48480	2.4680	0.9441	0.8391
0.609	240.0015	48682	2.4801	0.9389	0.8527
0.6119	241.0015	48884	2.7898	0.9380	0.8487
0.6089	242.0015	49086	2.2715	0.9389	0.8483
0.61	243.0015	49288	2.6468	0.9409	0.8542
0.6138	244.0015	49490	2.4042	0.9378	0.8508
0.6195	245.0015	49692	2.3606	0.9403	0.8306
0.6109	246.0015	49894	2.5278	0.9390	0.8541
0.6104	247.0015	50096	2.4921	0.9421	0.8547
0.6097	248.0015	50298	2.3190	0.9422	0.8553
0.6111	249.0015	50500	2.4929	0.9400	0.8540
0.6124	250.0015	50702	2.7351	0.9447	0.8624
0.6034	251.0015	50904	2.3177	0.9425	0.8583
0.6112	252.0015	51106	2.3869	0.9401	0.8541
0.6132	253.0015	51308	2.3981	0.9401	0.8524
0.6077	254.0015	51510	2.1906	0.9395	0.8559
0.61	255.0015	51712	2.2398	0.9433	0.8577
0.6061	256.0015	51914	2.1558	0.9433	0.8601
0.6112	257.0015	52116	2.6822	0.9408	0.8364
0.6042	258.0015	52318	2.3884	0.9434	0.8608
0.6049	259.0015	52520	2.3569	0.9431	0.8643
0.6091	260.0015	52722	2.5853	0.9421	0.8600
0.6048	261.0015	52924	2.2484	0.9406	0.8573
0.6024	262.0015	53126	2.5345	0.9422	0.8423
0.6003	263.0015	53328	2.5924	0.9397	0.8565
0.6033	264.0015	53530	2.9824	0.9404	0.8537
0.6004	265.0015	53732	2.6332	0.9413	0.8568
0.6038	266.0015	53934	2.6856	0.9404	0.8580
0.6013	267.0015	54136	2.4376	0.9353	0.8505
0.6124	268.0015	54338	2.5377	0.9355	0.8557
0.6023	269.0015	54540	2.4440	0.9410	0.8565
0.6174	270.0015	54742	2.4355	0.9420	0.8559
0.6138	271.0015	54944	2.6792	0.9327	0.8458
0.6069	272.0015	55146	2.4422	0.9393	0.8528
0.6044	273.0015	55348	2.6024	0.9404	0.8576
0.5996	274.0015	55550	2.5928	0.9405	0.8597
0.6027	275.0015	55752	2.6916	0.9425	0.8589
0.6027	276.0015	55954	2.5204	0.9403	0.8561
0.602	277.0015	56156	2.7102	0.9410	0.8568
0.6025	278.0015	56358	2.4499	0.9443	0.8652
0.5984	279.0015	56560	2.4095	0.9434	0.8624
0.5963	280.0015	56762	2.2662	0.9424	0.8606
0.5997	281.0015	56964	2.5003	0.9427	0.8620
0.5995	282.0015	57166	2.4803	0.9447	0.8477
0.6	283.0015	57368	2.4274	0.9423	0.8603
0.6	284.0015	57570	2.5557	0.9417	0.8444
0.6023	285.0015	57772	2.5390	0.9406	0.8409
0.5944	286.0015	57974	2.4972	0.9385	0.8543
0.5977	287.0015	58176	2.5065	0.9406	0.8422
0.6026	288.0015	58378	2.4524	0.9413	0.8583
0.5963	289.0015	58580	2.4146	0.9408	0.8594
0.6034	290.0015	58782	2.5736	0.9430	0.8619
0.6013	291.0015	58984	2.7404	0.9434	0.8623
0.594	292.0015	59186	2.3056	0.9398	0.8564
0.5936	293.0015	59388	2.8047	0.9415	0.8440
0.5952	294.0015	59590	2.3130	0.9406	0.8399
0.5898	295.0015	59792	2.7333	0.9391	0.8585
0.5927	296.0015	59994	2.6466	0.9405	0.8617
0.6016	297.0015	60196	2.6073	0.9390	0.8363
0.5954	298.0015	60398	2.5689	0.9413	0.8591

Framework versions

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