learning_rate: 2e-05
train_batch_size: 64
eval_batch_size: 64
seed: 42
optimizer: Use OptimizerNames.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	10.6077	0.0	10.6056	3.2566
No log	2.0	8	8.3655	0.0	8.3637	2.8920
No log	3.0	12	7.9363	0.0	7.9346	2.8168
No log	4.0	16	7.4788	0.0	7.4771	2.7344
No log	5.0	20	6.5038	-0.0017	6.5023	2.5500
No log	6.0	24	4.0815	0.0	4.0805	2.0200
No log	7.0	28	2.7843	0.0003	2.7834	1.6684
No log	8.0	32	1.7015	0.0093	1.7007	1.3041
No log	9.0	36	1.1864	0.0	1.1861	1.0891
No log	10.0	40	1.0123	0.0	1.0121	1.0060
No log	11.0	44	1.2791	0.0129	1.2788	1.1309
No log	12.0	48	1.0698	0.1225	1.0696	1.0342
No log	13.0	52	1.2781	0.1472	1.2780	1.1305
No log	14.0	56	1.2359	0.1895	1.2357	1.1116
No log	15.0	60	0.6045	0.4462	0.6046	0.7776
No log	16.0	64	0.9881	0.2481	0.9879	0.9939
No log	17.0	68	0.7992	0.3210	0.7994	0.8941
No log	18.0	72	0.7167	0.4027	0.7171	0.8468
No log	19.0	76	1.6460	0.2078	1.6458	1.2829
No log	20.0	80	0.6952	0.5174	0.6955	0.8340
No log	21.0	84	1.8536	0.1954	1.8531	1.3613
No log	22.0	88	0.9072	0.3954	0.9072	0.9525
No log	23.0	92	1.4696	0.2580	1.4694	1.2122
No log	24.0	96	1.3728	0.2841	1.3727	1.1716
No log	25.0	100	1.1966	0.3212	1.1966	1.0939
No log	26.0	104	1.2964	0.2944	1.2964	1.1386
No log	27.0	108	1.5836	0.2521	1.5835	1.2584
No log	28.0	112	1.0246	0.3770	1.0248	1.0123
No log	29.0	116	1.8242	0.1960	1.8240	1.3506
No log	30.0	120	1.4130	0.2677	1.4131	1.1887
No log	31.0	124	0.8526	0.3840	0.8529	0.9235
No log	32.0	128	1.5843	0.2363	1.5842	1.2587
No log	33.0	132	0.8602	0.4028	0.8603	0.9275
No log	34.0	136	1.3910	0.2563	1.3909	1.1793
No log	35.0	140	1.2751	0.2854	1.2750	1.1292
No log	36.0	144	1.0376	0.3437	1.0376	1.0186
No log	37.0	148	1.1208	0.3265	1.1208	1.0587
No log	38.0	152	1.1748	0.3165	1.1749	1.0839
No log	39.0	156	1.1776	0.3215	1.1776	1.0852
No log	40.0	160	1.2587	0.2935	1.2587	1.1219
No log	41.0	164	0.9508	0.3482	0.9509	0.9751
No log	42.0	168	1.2712	0.2868	1.2711	1.1274
No log	43.0	172	0.8891	0.3756	0.8893	0.9430
No log	44.0	176	1.5354	0.2425	1.5353	1.2391
No log	45.0	180	1.0074	0.3544	1.0076	1.0038
No log	46.0	184	1.0331	0.3554	1.0332	1.0165
No log	47.0	188	1.3824	0.2874	1.3824	1.1757
No log	48.0	192	0.8946	0.4039	0.8947	0.9459
No log	49.0	196	1.1818	0.3135	1.1819	1.0871
No log	50.0	200	1.0506	0.3377	1.0507	1.0250

Framework versions

Transformers 4.51.1
Pytorch 2.5.1+cu124
Datasets 3.5.0
Tokenizers 0.21.0

genki10/BERT_V8_sp10_lw40_ex100_lo100_k5_k5_fold3

BERT_V8_sp10_lw40_ex100_lo100_k5_k5_fold3

Model description

Intended uses & limitations

Training and evaluation data

Training procedure

Training hyperparameters

Training results

Framework versions

genki10/
BERT_V8_sp10_lw40_ex100_lo100_k5_k5_fold3