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	7.6736	0.0	7.6736	2.7701
No log	2.0	8	5.7678	0.0150	5.7678	2.4016
No log	3.0	12	4.0534	0.0039	4.0534	2.0133
No log	4.0	16	2.4382	0.0868	2.4382	1.5615
No log	5.0	20	1.4678	0.0316	1.4678	1.2115
No log	6.0	24	0.9978	0.0316	0.9978	0.9989
No log	7.0	28	0.7992	0.3341	0.7992	0.8940
No log	8.0	32	0.8924	0.2625	0.8924	0.9447
No log	9.0	36	1.1217	0.2376	1.1217	1.0591
No log	10.0	40	0.5827	0.4757	0.5827	0.7634
No log	11.0	44	0.5971	0.4421	0.5971	0.7727
No log	12.0	48	0.6980	0.4244	0.6980	0.8355
No log	13.0	52	0.6264	0.4606	0.6264	0.7915
No log	14.0	56	0.5644	0.4512	0.5644	0.7513
No log	15.0	60	0.9439	0.3857	0.9439	0.9715
No log	16.0	64	0.6077	0.5173	0.6077	0.7795
No log	17.0	68	0.6971	0.4940	0.6971	0.8349
No log	18.0	72	0.8763	0.4307	0.8763	0.9361
No log	19.0	76	0.6845	0.4802	0.6845	0.8273
No log	20.0	80	0.8647	0.3311	0.8647	0.9299
No log	21.0	84	0.8836	0.2825	0.8836	0.9400
No log	22.0	88	0.6712	0.4146	0.6712	0.8193
No log	23.0	92	0.8922	0.3467	0.8922	0.9445
No log	24.0	96	0.7755	0.4406	0.7755	0.8806
No log	25.0	100	0.6449	0.4760	0.6449	0.8031
No log	26.0	104	1.1170	0.2897	1.1170	1.0569
No log	27.0	108	0.6081	0.5041	0.6081	0.7798
No log	28.0	112	1.0419	0.3341	1.0419	1.0207
No log	29.0	116	1.2053	0.2990	1.2053	1.0979
No log	30.0	120	0.6450	0.4563	0.6450	0.8031
No log	31.0	124	1.3216	0.2366	1.3216	1.1496
No log	32.0	128	0.6616	0.4473	0.6616	0.8134
No log	33.0	132	0.7528	0.4023	0.7528	0.8677
No log	34.0	136	0.6489	0.4577	0.6489	0.8055
No log	35.0	140	0.9468	0.2762	0.9468	0.9731
No log	36.0	144	0.7031	0.4435	0.7031	0.8385
No log	37.0	148	0.6705	0.4833	0.6705	0.8188
No log	38.0	152	0.9473	0.3317	0.9473	0.9733
No log	39.0	156	0.7139	0.4299	0.7139	0.8449
No log	40.0	160	0.8169	0.3154	0.8169	0.9038
No log	41.0	164	0.8190	0.3591	0.8190	0.9050
No log	42.0	168	0.9939	0.3391	0.9939	0.9969
No log	43.0	172	0.6789	0.4432	0.6789	0.8240
No log	44.0	176	0.9796	0.2873	0.9796	0.9897
No log	45.0	180	0.7310	0.4021	0.7310	0.8550
No log	46.0	184	0.7116	0.3995	0.7116	0.8435

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_fold0

BERT_V8_sp10_lw40_ex100_lo100_k5_k5_fold0

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_fold0