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	9.0995	0.0	9.0996	3.0166
No log	2.0	10	4.3939	0.0113	4.3944	2.0963
No log	3.0	15	1.7899	0.0837	1.7904	1.3381
No log	4.0	20	0.9306	0.0216	0.9311	0.9649
No log	5.0	25	1.7355	0.1621	1.7360	1.3176
No log	6.0	30	0.7245	0.3819	0.7248	0.8513
No log	7.0	35	1.4390	0.1623	1.4394	1.1998
No log	8.0	40	0.6972	0.3946	0.6974	0.8351
No log	9.0	45	0.5946	0.4454	0.5946	0.7711
No log	10.0	50	0.7240	0.4137	0.7241	0.8510
No log	11.0	55	0.6303	0.4750	0.6303	0.7939
No log	12.0	60	0.5752	0.5318	0.5751	0.7583
No log	13.0	65	1.1129	0.3678	1.1128	1.0549
No log	14.0	70	0.7007	0.4958	0.7005	0.8369
No log	15.0	75	0.6710	0.5088	0.6707	0.8190
No log	16.0	80	1.0031	0.3436	1.0030	1.0015
No log	17.0	85	0.8759	0.3582	0.8757	0.9358
No log	18.0	90	0.9769	0.3848	0.9769	0.9884
No log	19.0	95	0.7490	0.3664	0.7489	0.8654
No log	20.0	100	1.2251	0.2987	1.2250	1.1068
No log	21.0	105	0.7532	0.4234	0.7532	0.8679
No log	22.0	110	0.7112	0.3987	0.7111	0.8433
No log	23.0	115	0.8188	0.3887	0.8186	0.9048
No log	24.0	120	1.3646	0.2796	1.3646	1.1682
No log	25.0	125	1.2261	0.2912	1.2260	1.1072
No log	26.0	130	0.6700	0.4472	0.6699	0.8184
No log	27.0	135	0.9383	0.3559	0.9382	0.9686
No log	28.0	140	1.1699	0.3221	1.1698	1.0816
No log	29.0	145	0.7976	0.3927	0.7974	0.8930
No log	30.0	150	0.9647	0.3398	0.9646	0.9821
No log	31.0	155	0.9009	0.3584	0.9007	0.9491
No log	32.0	160	0.8061	0.3823	0.8060	0.8978
No log	33.0	165	1.0697	0.2887	1.0697	1.0343
No log	34.0	170	0.9338	0.3981	0.9337	0.9663
No log	35.0	175	0.9500	0.3800	0.9499	0.9746
No log	36.0	180	1.0301	0.3116	1.0301	1.0149
No log	37.0	185	0.8711	0.3178	0.8711	0.9333
No log	38.0	190	0.7334	0.4025	0.7333	0.8563
No log	39.0	195	1.3412	0.2385	1.3412	1.1581
No log	40.0	200	1.0301	0.3011	1.0300	1.0149
No log	41.0	205	0.8433	0.3538	0.8432	0.9183
No log	42.0	210	1.0755	0.2785	1.0754	1.0370

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_fold2

BERT_V8_sp10_lw40_ex100_lo00_k7_k7_fold2

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_fold2