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	7.0869	0.0	7.0869	2.6621
No log	2.0	10	5.0104	0.0115	5.0104	2.2384
No log	3.0	15	2.8863	0.0	2.8863	1.6989
No log	4.0	20	1.4980	0.0316	1.4980	1.2239
No log	5.0	25	1.0461	0.0316	1.0461	1.0228
No log	6.0	30	1.1213	0.0362	1.1213	1.0589
No log	7.0	35	0.7844	0.3799	0.7844	0.8857
No log	8.0	40	0.6496	0.4246	0.6496	0.8060
No log	9.0	45	0.6213	0.4752	0.6213	0.7882
No log	10.0	50	0.7992	0.3990	0.7992	0.8940
No log	11.0	55	0.6694	0.2950	0.6694	0.8182
No log	12.0	60	0.5599	0.4370	0.5599	0.7483
No log	13.0	65	0.6943	0.3815	0.6943	0.8332
No log	14.0	70	0.6850	0.4698	0.6850	0.8276
No log	15.0	75	0.8728	0.3563	0.8728	0.9342
No log	16.0	80	0.8975	0.3477	0.8975	0.9474
No log	17.0	85	0.6672	0.4929	0.6672	0.8168
No log	18.0	90	0.7410	0.4638	0.7410	0.8608
No log	19.0	95	0.9158	0.3489	0.9158	0.9570
No log	20.0	100	0.6535	0.4379	0.6535	0.8084
No log	21.0	105	0.6833	0.4516	0.6833	0.8266
No log	22.0	110	0.8656	0.3813	0.8656	0.9304
No log	23.0	115	0.7491	0.4425	0.7491	0.8655
No log	24.0	120	0.6406	0.4551	0.6406	0.8004
No log	25.0	125	0.7138	0.4580	0.7138	0.8449
No log	26.0	130	0.7658	0.4131	0.7658	0.8751
No log	27.0	135	0.8057	0.3911	0.8057	0.8976
No log	28.0	140	0.6624	0.4735	0.6624	0.8139
No log	29.0	145	0.6062	0.4654	0.6062	0.7786
No log	30.0	150	0.7320	0.4147	0.7320	0.8556
No log	31.0	155	0.7882	0.4115	0.7882	0.8878
No log	32.0	160	0.6961	0.4331	0.6961	0.8344
No log	33.0	165	0.7389	0.4015	0.7389	0.8596
No log	34.0	170	0.7639	0.4094	0.7639	0.8740
No log	35.0	175	0.8967	0.3241	0.8967	0.9469
No log	36.0	180	0.9300	0.3377	0.9300	0.9644
No log	37.0	185	0.8657	0.3247	0.8657	0.9304
No log	38.0	190	0.6820	0.4447	0.6820	0.8258
No log	39.0	195	0.6862	0.4290	0.6862	0.8284
No log	40.0	200	0.7260	0.4065	0.7260	0.8520
No log	41.0	205	0.7457	0.3941	0.7457	0.8635
No log	42.0	210	0.7459	0.3801	0.7459	0.8637
No log	43.0	215	0.7808	0.3591	0.7808	0.8836
No log	44.0	220	0.7626	0.3398	0.7626	0.8733
No log	45.0	225	0.6324	0.4369	0.6324	0.7952
No log	46.0	230	0.8828	0.3471	0.8828	0.9396
No log	47.0	235	0.7529	0.3714	0.7529	0.8677

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_lo00_k7_k7_fold0

BERT_V8_sp10_lw40_ex100_lo00_k7_k7_fold0

Model description

Intended uses & limitations

Training and evaluation data

Training procedure

Training hyperparameters

Training results

Framework versions

genki10/
BERT_V8_sp10_lw40_ex100_lo00_k7_k7_fold0