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	9.7300	0.0072	9.7271	3.1188
No log	2.0	4	8.8310	0.0	8.8284	2.9713
No log	3.0	6	7.8456	0.0	7.8432	2.8006
No log	4.0	8	6.7136	0.0	6.7113	2.5906
No log	5.0	10	5.4301	0.0480	5.4280	2.3298
No log	6.0	12	4.4218	0.0	4.4198	2.1023
No log	7.0	14	3.6176	0.0	3.6157	1.9015
No log	8.0	16	2.7642	0.0	2.7624	1.6620
No log	9.0	18	2.1804	0.1218	2.1787	1.4760
No log	10.0	20	1.7592	0.0414	1.7576	1.3258
No log	11.0	22	1.3317	0.0	1.3302	1.1533
No log	12.0	24	1.0933	0.0	1.0919	1.0449
No log	13.0	26	0.9120	0.2455	0.9108	0.9544
No log	14.0	28	0.8437	0.2525	0.8426	0.9179
No log	15.0	30	0.8111	0.2507	0.8099	0.9000
No log	16.0	32	0.7930	0.3264	0.7918	0.8898
No log	17.0	34	0.7410	0.3352	0.7399	0.8602
No log	18.0	36	0.8099	0.2707	0.8086	0.8992
No log	19.0	38	0.7160	0.3556	0.7149	0.8455
No log	20.0	40	0.8379	0.3165	0.8367	0.9147
No log	21.0	42	1.3357	0.1479	1.3339	1.1549
No log	22.0	44	0.9434	0.2845	0.9421	0.9706
No log	23.0	46	0.9660	0.3202	0.9643	0.9820
No log	24.0	48	1.4549	0.1843	1.4526	1.2052
No log	25.0	50	0.8393	0.3659	0.8379	0.9154
No log	26.0	52	0.9122	0.3470	0.9115	0.9547
No log	27.0	54	1.0963	0.2455	1.0946	1.0462
No log	28.0	56	1.4169	0.1652	1.4145	1.1893
No log	29.0	58	1.1904	0.2830	1.1892	1.0905
No log	30.0	60	1.2105	0.2543	1.2088	1.0995
No log	31.0	62	1.8025	0.1441	1.7999	1.3416
No log	32.0	64	1.2448	0.2512	1.2430	1.1149
No log	33.0	66	1.2242	0.2327	1.2227	1.1057
No log	34.0	68	1.4587	0.1877	1.4565	1.2069
No log	35.0	70	1.2825	0.2182	1.2806	1.1317
No log	36.0	72	1.3058	0.2211	1.3038	1.1418
No log	37.0	74	1.3224	0.2176	1.3203	1.1490
No log	38.0	76	1.6539	0.1271	1.6511	1.2850
No log	39.0	78	1.3116	0.2466	1.3097	1.1444
No log	40.0	80	1.3302	0.2460	1.3282	1.1525
No log	41.0	82	1.6099	0.1709	1.6071	1.2677
No log	42.0	84	1.2817	0.2496	1.2797	1.1312
No log	43.0	86	1.2826	0.2145	1.2804	1.1315
No log	44.0	88	1.5107	0.1568	1.5081	1.2281
No log	45.0	90	1.1629	0.2267	1.1609	1.0775
No log	46.0	92	1.0957	0.2443	1.0941	1.0460
No log	47.0	94	1.3019	0.2143	1.2998	1.1401
No log	48.0	96	1.3199	0.1992	1.3177	1.1479
No log	49.0	98	1.1658	0.2415	1.1641	1.0789
No log	50.0	100	1.2057	0.2245	1.2039	1.0972
No log	51.0	102	1.2988	0.2135	1.2969	1.1388
No log	52.0	104	1.1663	0.2464	1.1646	1.0792
No log	53.0	106	1.1251	0.2451	1.1236	1.0600
No log	54.0	108	1.2468	0.2182	1.2448	1.1157
No log	55.0	110	1.1224	0.2428	1.1207	1.0587

Framework versions

Transformers 4.47.0
Pytorch 2.5.1+cu121
Datasets 3.3.1
Tokenizers 0.21.0

genki10/BERT_V8_sp10_lw20_ex200_lo100_k3_k3_fold1

BERT_V8_sp10_lw20_ex200_lo100_k3_k3_fold1

Model description

Intended uses & limitations

Training and evaluation data

Training procedure

Training hyperparameters

Training results

Framework versions

genki10/
BERT_V8_sp10_lw20_ex200_lo100_k3_k3_fold1