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	9.7156	0.0	9.7158	3.1170
No log	2.0	8	6.4250	0.0	6.4253	2.5348
No log	3.0	12	3.4779	0.0039	3.4783	1.8650
No log	4.0	16	1.9968	0.1335	1.9973	1.4133
No log	5.0	20	0.9811	0.0213	0.9815	0.9907
No log	6.0	24	0.9071	0.1240	0.9075	0.9526
No log	7.0	28	0.8787	0.2010	0.8791	0.9376
No log	8.0	32	1.3709	0.1768	1.3714	1.1710
No log	9.0	36	0.5841	0.4519	0.5844	0.7645
No log	10.0	40	0.9658	0.2657	0.9663	0.9830
No log	11.0	44	0.5860	0.4040	0.5862	0.7656
No log	12.0	48	0.8755	0.3769	0.8759	0.9359
No log	13.0	52	0.5656	0.4913	0.5658	0.7522
No log	14.0	56	0.6760	0.4546	0.6764	0.8224
No log	15.0	60	1.1046	0.2951	1.1050	1.0512
No log	16.0	64	0.6127	0.4591	0.6130	0.7829
No log	17.0	68	1.0349	0.2898	1.0353	1.0175
No log	18.0	72	0.6752	0.4465	0.6753	0.8218
No log	19.0	76	1.5721	0.2121	1.5722	1.2539
No log	20.0	80	0.8084	0.3799	0.8084	0.8991
No log	21.0	84	1.2063	0.2591	1.2065	1.0984
No log	22.0	88	1.1831	0.2231	1.1833	1.0878
No log	23.0	92	0.7718	0.3806	0.7719	0.8786
No log	24.0	96	1.5418	0.1921	1.5421	1.2418
No log	25.0	100	0.9017	0.3359	0.9019	0.9497
No log	26.0	104	0.8508	0.3440	0.8511	0.9225
No log	27.0	108	1.0184	0.2723	1.0187	1.0093
No log	28.0	112	1.1126	0.2660	1.1129	1.0549
No log	29.0	116	0.8663	0.3704	0.8666	0.9309
No log	30.0	120	1.4112	0.1845	1.4115	1.1881
No log	31.0	124	0.7022	0.3871	0.7024	0.8381
No log	32.0	128	1.2740	0.2259	1.2741	1.1288
No log	33.0	132	0.8147	0.3643	0.8148	0.9027
No log	34.0	136	1.5029	0.2164	1.5030	1.2259
No log	35.0	140	0.7372	0.4063	0.7372	0.8586
No log	36.0	144	1.3920	0.1965	1.3920	1.1798
No log	37.0	148	1.1259	0.2466	1.1259	1.0611
No log	38.0	152	0.7675	0.3763	0.7674	0.8760
No log	39.0	156	0.9460	0.3219	0.9459	0.9725
No log	40.0	160	1.1451	0.2210	1.1450	1.0701
No log	41.0	164	1.0136	0.2882	1.0136	1.0068
No log	42.0	168	0.9694	0.3069	0.9693	0.9845
No log	43.0	172	1.3063	0.2254	1.3061	1.1429

Framework versions

Transformers 4.51.1
Pytorch 2.5.1+cu124
Datasets 3.5.0
Tokenizers 0.21.0

genki10/BERT_V8_sp10_lw40_ex50_lo00_k5_k5_fold2

BERT_V8_sp10_lw40_ex50_lo00_k5_k5_fold2

Model description

Intended uses & limitations

Training and evaluation data

Training procedure

Training hyperparameters

Training results

Framework versions

genki10/
BERT_V8_sp10_lw40_ex50_lo00_k5_k5_fold2