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	4	10.1445	0.0018	10.1445	3.1850
No log	2.0	8	7.8371	0.0	7.8371	2.7995
No log	3.0	12	6.4425	0.0	6.4425	2.5382
No log	4.0	16	4.5485	0.0079	4.5485	2.1327
No log	5.0	20	2.9109	0.0	2.9109	1.7061
No log	6.0	24	1.9080	0.0622	1.9080	1.3813
No log	7.0	28	1.2485	0.0213	1.2485	1.1174
No log	8.0	32	0.8829	0.0213	0.8829	0.9396
No log	9.0	36	1.4123	0.1742	1.4123	1.1884
No log	10.0	40	0.7225	0.4587	0.7225	0.8500
No log	11.0	44	1.7353	0.2071	1.7353	1.3173
No log	12.0	48	0.6879	0.4756	0.6879	0.8294
No log	13.0	52	1.8785	0.1956	1.8785	1.3706
No log	14.0	56	0.9451	0.3930	0.9451	0.9722
No log	15.0	60	0.8624	0.4156	0.8624	0.9287
No log	16.0	64	0.7350	0.4756	0.7350	0.8573
No log	17.0	68	1.2227	0.3643	1.2227	1.1057
No log	18.0	72	0.7321	0.4972	0.7321	0.8556
No log	19.0	76	0.9317	0.4650	0.9317	0.9653
No log	20.0	80	1.0630	0.4416	1.0630	1.0310
No log	21.0	84	1.0901	0.4417	1.0901	1.0441
No log	22.0	88	1.3621	0.3149	1.3621	1.1671
No log	23.0	92	0.8515	0.4761	0.8515	0.9228
No log	24.0	96	1.1970	0.4017	1.1970	1.0941
No log	25.0	100	1.1812	0.4211	1.1812	1.0868
No log	26.0	104	0.9943	0.4467	0.9943	0.9971
No log	27.0	108	1.9168	0.2109	1.9168	1.3845
No log	28.0	112	1.2049	0.3689	1.2049	1.0977
No log	29.0	116	0.8493	0.4532	0.8493	0.9215
No log	30.0	120	1.0476	0.4041	1.0476	1.0235
No log	31.0	124	1.1901	0.3459	1.1901	1.0909
No log	32.0	128	1.0016	0.4041	1.0016	1.0008
No log	33.0	132	0.8774	0.4215	0.8774	0.9367
No log	34.0	136	1.1160	0.3790	1.1160	1.0564
No log	35.0	140	1.0743	0.3801	1.0743	1.0365
No log	36.0	144	0.8119	0.4334	0.8119	0.9011
No log	37.0	148	1.1254	0.3837	1.1254	1.0608
No log	38.0	152	1.0859	0.3963	1.0859	1.0421
No log	39.0	156	1.0973	0.3941	1.0973	1.0475
No log	40.0	160	0.8637	0.4361	0.8637	0.9294
No log	41.0	164	1.2906	0.3064	1.2906	1.1360
No log	42.0	168	1.0042	0.3996	1.0042	1.0021
No log	43.0	172	1.0436	0.3973	1.0436	1.0216
No log	44.0	176	0.9470	0.4196	0.9470	0.9731
No log	45.0	180	0.8414	0.4418	0.8414	0.9173
No log	46.0	184	1.1591	0.3497	1.1591	1.0766
No log	47.0	188	0.8287	0.4317	0.8287	0.9103
No log	48.0	192	1.0427	0.3646	1.0427	1.0211

Framework versions

Transformers 4.47.0
Pytorch 2.5.1+cu121
Datasets 3.3.1
Tokenizers 0.21.0

genki10/BERT_V8_sp20_lw10_ex40_lo00_k5_k5_fold4

BERT_V8_sp20_lw10_ex40_lo00_k5_k5_fold4

Model description

Intended uses & limitations

Training and evaluation data

Training procedure

Training hyperparameters

Training results

Framework versions

genki10/
BERT_V8_sp20_lw10_ex40_lo00_k5_k5_fold4