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	5	9.7359	0.0018	9.7359	3.1202
No log	2.0	10	7.1375	0.0	7.1375	2.6716
No log	3.0	15	4.9495	0.0079	4.9495	2.2247
No log	4.0	20	2.9237	0.0	2.9237	1.7099
No log	5.0	25	1.7167	0.0266	1.7167	1.3102
No log	6.0	30	1.0906	0.0213	1.0906	1.0443
No log	7.0	35	0.9866	0.0213	0.9866	0.9933
No log	8.0	40	1.1321	0.0213	1.1321	1.0640
No log	9.0	45	1.1559	0.1573	1.1559	1.0751
No log	10.0	50	0.8138	0.2576	0.8138	0.9021
No log	11.0	55	0.6620	0.5005	0.6620	0.8136
No log	12.0	60	0.9221	0.4409	0.9221	0.9603
No log	13.0	65	0.6228	0.5164	0.6228	0.7892
No log	14.0	70	0.6446	0.4360	0.6446	0.8029
No log	15.0	75	0.7135	0.4450	0.7135	0.8447
No log	16.0	80	1.5916	0.3450	1.5916	1.2616
No log	17.0	85	0.5899	0.5726	0.5899	0.7680
No log	18.0	90	0.7635	0.4426	0.7635	0.8738
No log	19.0	95	0.6430	0.4644	0.6430	0.8019
No log	20.0	100	0.6831	0.5126	0.6831	0.8265
No log	21.0	105	0.7265	0.5110	0.7265	0.8523
No log	22.0	110	0.6614	0.5022	0.6614	0.8132
No log	23.0	115	0.6411	0.5106	0.6411	0.8007
No log	24.0	120	0.7291	0.4728	0.7291	0.8539
No log	25.0	125	0.7983	0.4823	0.7983	0.8935
No log	26.0	130	0.6715	0.5092	0.6715	0.8194
No log	27.0	135	0.5838	0.5226	0.5838	0.7641
No log	28.0	140	0.5891	0.5891	0.5891	0.7675
No log	29.0	145	0.8243	0.4738	0.8243	0.9079
No log	30.0	150	0.5724	0.5953	0.5724	0.7566
No log	31.0	155	0.7173	0.4894	0.7173	0.8469
No log	32.0	160	0.7654	0.4839	0.7654	0.8749
No log	33.0	165	0.6092	0.5042	0.6092	0.7805
No log	34.0	170	0.7216	0.4700	0.7216	0.8495
No log	35.0	175	0.7422	0.4875	0.7422	0.8615
No log	36.0	180	0.6277	0.5388	0.6277	0.7923
No log	37.0	185	0.8488	0.4330	0.8488	0.9213
No log	38.0	190	0.6258	0.5024	0.6258	0.7911
No log	39.0	195	0.6130	0.5249	0.6130	0.7829
No log	40.0	200	0.7849	0.4368	0.7849	0.8859
No log	41.0	205	0.5774	0.5531	0.5774	0.7599
No log	42.0	210	0.8272	0.4670	0.8272	0.9095
No log	43.0	215	0.6254	0.5088	0.6254	0.7908
No log	44.0	220	0.5836	0.5354	0.5836	0.7639
No log	45.0	225	0.7241	0.4783	0.7241	0.8509
No log	46.0	230	0.5746	0.5608	0.5746	0.7580
No log	47.0	235	0.6958	0.4827	0.6958	0.8342
No log	48.0	240	0.7015	0.4806	0.7015	0.8375
No log	49.0	245	0.6243	0.5060	0.6243	0.7901
No log	50.0	250	0.6161	0.5096	0.6161	0.7849
No log	51.0	255	0.6643	0.5042	0.6643	0.8151
No log	52.0	260	0.7491	0.4691	0.7491	0.8655
No log	53.0	265	0.5767	0.5300	0.5767	0.7594
No log	54.0	270	0.6467	0.5060	0.6467	0.8041
No log	55.0	275	0.7260	0.4635	0.7260	0.8521
No log	56.0	280	0.5861	0.5221	0.5861	0.7655
No log	57.0	285	0.7642	0.4544	0.7642	0.8742
No log	58.0	290	0.6652	0.4960	0.6652	0.8156
No log	59.0	295	0.6696	0.4952	0.6696	0.8183
No log	60.0	300	0.6942	0.4905	0.6942	0.8332

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_k7_k7_fold4

BERT_V8_sp10_lw40_ex50_lo00_k7_k7_fold4

Model description

Intended uses & limitations

Training and evaluation data

Training procedure

Training hyperparameters

Training results

Framework versions

genki10/
BERT_V8_sp10_lw40_ex50_lo00_k7_k7_fold4