learning_rate: 2e-05
train_batch_size: 64
eval_batch_size: 64
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
num_epochs: 100

Training results

Training Loss	Epoch	Step	Validation Loss	Qwk	Mse	Rmse
No log	1.0	2	7.9842	0.0	7.9845	2.8257
No log	2.0	4	7.6794	0.0	7.6795	2.7712
No log	3.0	6	7.2962	0.0	7.2962	2.7012
No log	4.0	8	6.7312	-0.0005	6.7311	2.5944
No log	5.0	10	5.7663	-0.0139	5.7662	2.4013
No log	6.0	12	4.5258	0.0	4.5260	2.1274
No log	7.0	14	3.7184	0.0	3.7187	1.9284
No log	8.0	16	3.1911	0.0	3.1915	1.7865
No log	9.0	18	2.6010	0.0124	2.6013	1.6129
No log	10.0	20	2.0795	0.0503	2.0799	1.4422
No log	11.0	22	1.8993	0.0399	1.8998	1.3783
No log	12.0	24	1.5001	0.0213	1.5007	1.2250
No log	13.0	26	1.2498	0.0107	1.2503	1.1182
No log	14.0	28	1.1318	0.0	1.1324	1.0641
No log	15.0	30	1.0024	0.0	1.0029	1.0015
No log	16.0	32	0.8899	0.0173	0.8903	0.9435
No log	17.0	34	0.8125	0.3908	0.8129	0.9016
No log	18.0	36	0.8922	-0.0157	0.8929	0.9449
No log	19.0	38	0.9531	-0.0724	0.9537	0.9766
No log	20.0	40	0.8423	0.1474	0.8427	0.9180
No log	21.0	42	0.7628	0.4239	0.7627	0.8734
No log	22.0	44	0.7246	0.4311	0.7245	0.8512
No log	23.0	46	0.7748	0.2549	0.7751	0.8804
No log	24.0	48	0.9418	0.0135	0.9424	0.9708
No log	25.0	50	0.9190	0.0412	0.9196	0.9589
No log	26.0	52	0.6789	0.2912	0.6790	0.8240
No log	27.0	54	0.7025	0.3825	0.7026	0.8382
No log	28.0	56	0.7706	0.3456	0.7707	0.8779
No log	29.0	58	0.6518	0.3982	0.6519	0.8074
No log	30.0	60	0.5898	0.3985	0.5897	0.7679
No log	31.0	62	0.7248	0.2836	0.7248	0.8513
No log	32.0	64	0.7113	0.2904	0.7112	0.8433
No log	33.0	66	0.5919	0.3813	0.5917	0.7692
No log	34.0	68	0.5712	0.4195	0.5709	0.7556
No log	35.0	70	0.6517	0.3772	0.6514	0.8071
No log	36.0	72	0.6345	0.4071	0.6341	0.7963
No log	37.0	74	0.5846	0.4942	0.5841	0.7643
No log	38.0	76	0.6804	0.5050	0.6800	0.8246
No log	39.0	78	0.6590	0.5189	0.6585	0.8115
No log	40.0	80	0.6355	0.5075	0.6348	0.7968
No log	41.0	82	0.6209	0.5524	0.6202	0.7875
No log	42.0	84	0.5996	0.5454	0.5990	0.7739
No log	43.0	86	0.5867	0.5650	0.5861	0.7656
No log	44.0	88	0.6178	0.5265	0.6171	0.7856
No log	45.0	90	0.6305	0.5270	0.6298	0.7936
No log	46.0	92	0.6009	0.5315	0.6002	0.7747
No log	47.0	94	0.5957	0.5761	0.5952	0.7715
No log	48.0	96	0.6154	0.5774	0.6150	0.7842
No log	49.0	98	0.5856	0.5954	0.5852	0.7650
No log	50.0	100	0.5759	0.5515	0.5753	0.7585
No log	51.0	102	0.5808	0.5334	0.5802	0.7617
No log	52.0	104	0.5491	0.5958	0.5487	0.7407
No log	53.0	106	0.5542	0.5688	0.5537	0.7441
No log	54.0	108	0.5517	0.5782	0.5512	0.7424
No log	55.0	110	0.5675	0.5723	0.5670	0.7530
No log	56.0	112	0.5901	0.5762	0.5895	0.7678
No log	57.0	114	0.5882	0.5758	0.5876	0.7666
No log	58.0	116	0.5927	0.5699	0.5922	0.7695
No log	59.0	118	0.6582	0.5527	0.6574	0.8108
No log	60.0	120	0.6501	0.5552	0.6493	0.8058
No log	61.0	122	0.5994	0.5787	0.5989	0.7739
No log	62.0	124	0.5960	0.5866	0.5955	0.7717
No log	63.0	126	0.6024	0.5807	0.6020	0.7759
No log	64.0	128	0.6420	0.5655	0.6413	0.8008
No log	65.0	130	0.6844	0.5571	0.6836	0.8268
No log	66.0	132	0.6493	0.5741	0.6486	0.8053
No log	67.0	134	0.6323	0.5677	0.6318	0.7949
No log	68.0	136	0.6426	0.5875	0.6420	0.8012
No log	69.0	138	0.6504	0.5811	0.6498	0.8061
No log	70.0	140	0.6644	0.5839	0.6637	0.8147
No log	71.0	142	0.6923	0.5582	0.6914	0.8315
No log	72.0	144	0.7039	0.5591	0.7030	0.8385
No log	73.0	146	0.7052	0.5584	0.7044	0.8393
No log	74.0	148	0.6889	0.5790	0.6882	0.8296
No log	75.0	150	0.6837	0.5821	0.6830	0.8264
No log	76.0	152	0.6808	0.5808	0.6800	0.8246
No log	77.0	154	0.6817	0.5956	0.6809	0.8252
No log	78.0	156	0.6889	0.5802	0.6880	0.8295
No log	79.0	158	0.7113	0.5506	0.7104	0.8428
No log	80.0	160	0.7205	0.5425	0.7196	0.8483
No log	81.0	162	0.7207	0.5474	0.7198	0.8484
No log	82.0	164	0.7287	0.5450	0.7278	0.8531

Framework versions

Transformers 4.47.0
Pytorch 2.5.1+cu121
Datasets 3.3.1
Tokenizers 0.21.0

genki10/BERT_V8_sp20_lw10_ex50_lo00_k1_k1_fold2

BERT_V8_sp20_lw10_ex50_lo00_k1_k1_fold2

Model description

Intended uses & limitations

Training and evaluation data

Training procedure

Training hyperparameters

Training results

Framework versions

genki10/
BERT_V8_sp20_lw10_ex50_lo00_k1_k1_fold2