ASAP_FineTuningBERT_AugV7_k1_task1_organization_fold1

This model is a fine-tuned version of bert-base-uncased on the None dataset. It achieves the following results on the evaluation set:

• Loss: 1.1756
• Qwk: 0.4486
• Mse: 1.1744
• Rmse: 1.0837

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: 2e-05
• train_batch_size: 64
• eval_batch_size: 64
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 100

Training results

Training Loss	Epoch	Step	Validation Loss	Qwk	Mse	Rmse
No log	1.0	2	10.5305	-0.0043	10.5279	3.2447
No log	2.0	4	8.1178	0.0	8.1159	2.8488
No log	3.0	6	6.4473	0.0	6.4456	2.5388
No log	4.0	8	5.0740	0.0173	5.0727	2.2523
7.2008	5.0	10	3.8957	0.0	3.8948	1.9735
7.2008	6.0	12	3.1086	0.0	3.1078	1.7629
7.2008	7.0	14	2.3895	0.0172	2.3890	1.5456
7.2008	8.0	16	1.8960	0.0730	1.8957	1.3769
7.2008	9.0	18	1.6909	0.0106	1.6907	1.3003
3.3676	10.0	20	1.2727	0.0211	1.2727	1.1281
3.3676	11.0	22	1.0912	0.0211	1.0913	1.0447
3.3676	12.0	24	1.0372	0.0106	1.0374	1.0185
3.3676	13.0	26	0.9480	0.0521	0.9481	0.9737
3.3676	14.0	28	0.9334	0.0910	0.9335	0.9662
2.1136	15.0	30	0.9363	0.0596	0.9363	0.9676
2.1136	16.0	32	0.9859	0.0576	0.9859	0.9929
2.1136	17.0	34	0.7833	0.3894	0.7833	0.8851
2.1136	18.0	36	0.7566	0.4467	0.7566	0.8698
2.1136	19.0	38	0.6950	0.5249	0.6950	0.8337
1.5029	20.0	40	0.8148	0.2530	0.8149	0.9027
1.5029	21.0	42	0.6610	0.4561	0.6610	0.8130
1.5029	22.0	44	0.5488	0.5992	0.5488	0.7408
1.5029	23.0	46	0.5651	0.5646	0.5651	0.7517
1.5029	24.0	48	0.9684	0.2458	0.9687	0.9842
1.1136	25.0	50	0.6435	0.4799	0.6435	0.8022
1.1136	26.0	52	0.6419	0.4632	0.6419	0.8012
1.1136	27.0	54	1.4103	0.0301	1.4109	1.1878
1.1136	28.0	56	1.2360	0.1107	1.2365	1.1120
1.1136	29.0	58	0.6404	0.4591	0.6403	0.8002
0.7212	30.0	60	0.7134	0.4490	0.7134	0.8446
0.7212	31.0	62	1.1411	0.1819	1.1415	1.0684
0.7212	32.0	64	0.8645	0.3619	0.8645	0.9298
0.7212	33.0	66	0.6347	0.5627	0.6344	0.7965
0.7212	34.0	68	0.8048	0.4938	0.8047	0.8970
0.4931	35.0	70	0.9457	0.3850	0.9457	0.9725
0.4931	36.0	72	0.7391	0.5172	0.7388	0.8595
0.4931	37.0	74	0.8287	0.4842	0.8284	0.9102
0.4931	38.0	76	1.0170	0.3689	1.0169	1.0084
0.4931	39.0	78	0.7241	0.5489	0.7237	0.8507
0.3198	40.0	80	0.7136	0.5607	0.7131	0.8445
0.3198	41.0	82	0.9641	0.4363	0.9637	0.9817
0.3198	42.0	84	0.8891	0.4856	0.8885	0.9426
0.3198	43.0	86	0.8881	0.4921	0.8874	0.9420
0.3198	44.0	88	1.1441	0.3594	1.1437	1.0694
0.255	45.0	90	1.1571	0.3438	1.1567	1.0755
0.255	46.0	92	0.8745	0.4826	0.8737	0.9347
0.255	47.0	94	0.8284	0.5088	0.8277	0.9098
0.255	48.0	96	1.0254	0.4535	1.0247	1.0123
0.255	49.0	98	1.1496	0.3907	1.1490	1.0719
0.2188	50.0	100	0.9093	0.4850	0.9084	0.9531
0.2188	51.0	102	0.9368	0.4954	0.9359	0.9674
0.2188	52.0	104	1.0193	0.4760	1.0186	1.0093
0.2188	53.0	106	0.8865	0.4877	0.8858	0.9412
0.2188	54.0	108	0.9286	0.5088	0.9279	0.9633
0.1342	55.0	110	1.1767	0.4539	1.1758	1.0844
0.1342	56.0	112	1.2905	0.4333	1.2895	1.1355
0.1342	57.0	114	1.3161	0.4236	1.3150	1.1468
0.1342	58.0	116	1.1108	0.4814	1.1099	1.0535
0.1342	59.0	118	1.1345	0.4657	1.1336	1.0647
0.1698	60.0	120	1.0892	0.4964	1.0881	1.0431
0.1698	61.0	122	1.1502	0.4779	1.1491	1.0720
0.1698	62.0	124	1.3678	0.3787	1.3670	1.1692
0.1698	63.0	126	1.3231	0.3670	1.3224	1.1500
0.1698	64.0	128	1.0797	0.4872	1.0788	1.0386
0.1438	65.0	130	1.0542	0.4943	1.0531	1.0262
0.1438	66.0	132	1.2483	0.4339	1.2475	1.1169
0.1438	67.0	134	1.2503	0.4053	1.2496	1.1178
0.1438	68.0	136	1.2306	0.4421	1.2296	1.1089
0.1438	69.0	138	1.1132	0.4898	1.1120	1.0545
0.143	70.0	140	1.1231	0.4747	1.1220	1.0592
0.143	71.0	142	1.2575	0.4119	1.2566	1.1210
0.143	72.0	144	1.2055	0.4174	1.2046	1.0975
0.143	73.0	146	1.0455	0.4933	1.0445	1.0220
0.143	74.0	148	1.0315	0.5282	1.0303	1.0151
0.1487	75.0	150	1.1548	0.4758	1.1536	1.0741
0.1487	76.0	152	1.2815	0.4167	1.2804	1.1315
0.1487	77.0	154	1.2815	0.4055	1.2804	1.1316
0.1487	78.0	156	1.1616	0.4492	1.1605	1.0773
0.1487	79.0	158	1.0290	0.5006	1.0279	1.0139
0.096	80.0	160	1.0472	0.4732	1.0461	1.0228
0.096	81.0	162	1.2787	0.4105	1.2777	1.1303
0.096	82.0	164	1.4538	0.3653	1.4528	1.2053
0.096	83.0	166	1.4759	0.3680	1.4748	1.2144
0.096	84.0	168	1.3824	0.4092	1.3812	1.1752
0.1076	85.0	170	1.2009	0.4758	1.1995	1.0952
0.1076	86.0	172	1.0840	0.5315	1.0827	1.0405
0.1076	87.0	174	1.0628	0.5255	1.0615	1.0303
0.1076	88.0	176	1.1317	0.4900	1.1304	1.0632
0.1076	89.0	178	1.2921	0.4261	1.2908	1.1362
0.1292	90.0	180	1.3609	0.4109	1.3598	1.1661
0.1292	91.0	182	1.3985	0.3906	1.3973	1.1821
0.1292	92.0	184	1.4058	0.3828	1.4046	1.1852
0.1292	93.0	186	1.3374	0.4097	1.3362	1.1559
0.1292	94.0	188	1.2645	0.4340	1.2632	1.1239
0.0871	95.0	190	1.2275	0.4388	1.2262	1.1073
0.0871	96.0	192	1.1940	0.4522	1.1927	1.0921
0.0871	97.0	194	1.1788	0.4579	1.1775	1.0851
0.0871	98.0	196	1.1768	0.4568	1.1756	1.0843
0.0871	99.0	198	1.1760	0.4486	1.1748	1.0839
0.1092	100.0	200	1.1756	0.4486	1.1744	1.0837

Framework versions

• Transformers 4.44.2
• Pytorch 2.4.1+cu121
• Datasets 3.2.0
• Tokenizers 0.19.1