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	9.0042	0.0	9.0016	3.0003
No log	2.0	8	5.1799	0.0377	5.1778	2.2755
No log	3.0	12	2.8779	0.0	2.8763	1.6960
No log	4.0	16	1.5244	0.0379	1.5228	1.2340
No log	5.0	20	0.9789	0.0	0.9776	0.9887
No log	6.0	24	0.9062	0.0429	0.9051	0.9514
No log	7.0	28	0.9764	0.0696	0.9754	0.9876
No log	8.0	32	0.8301	0.1779	0.8293	0.9106
No log	9.0	36	1.0025	0.1376	1.0010	1.0005
No log	10.0	40	0.7482	0.3083	0.7476	0.8646
No log	11.0	44	0.7519	0.3739	0.7506	0.8664
No log	12.0	48	0.7289	0.3556	0.7279	0.8532
No log	13.0	52	0.8471	0.2932	0.8456	0.9196
No log	14.0	56	0.7691	0.3699	0.7679	0.8763
No log	15.0	60	0.7476	0.3785	0.7466	0.8640
No log	16.0	64	0.7852	0.4707	0.7845	0.8857
No log	17.0	68	0.9856	0.3809	0.9838	0.9919
No log	18.0	72	0.9874	0.4208	0.9871	0.9935
No log	19.0	76	1.0095	0.3300	1.0076	1.0038
No log	20.0	80	0.8171	0.4207	0.8164	0.9035
No log	21.0	84	0.8760	0.2857	0.8745	0.9352
No log	22.0	88	0.7888	0.3834	0.7878	0.8876
No log	23.0	92	0.9385	0.3186	0.9367	0.9678
No log	24.0	96	0.7317	0.3972	0.7306	0.8548
No log	25.0	100	0.7737	0.3886	0.7723	0.8788
No log	26.0	104	0.7599	0.4105	0.7589	0.8712
No log	27.0	108	0.8428	0.3243	0.8413	0.9172
No log	28.0	112	0.8178	0.3602	0.8163	0.9035
No log	29.0	116	0.7469	0.4134	0.7459	0.8637
No log	30.0	120	0.7544	0.4005	0.7531	0.8678
No log	31.0	124	0.8822	0.4027	0.8805	0.9383
No log	32.0	128	0.7523	0.3997	0.7511	0.8666
No log	33.0	132	0.7994	0.3579	0.7979	0.8932
No log	34.0	136	0.8077	0.3525	0.8061	0.8979
No log	35.0	140	0.7792	0.4233	0.7781	0.8821
No log	36.0	144	0.9388	0.2819	0.9370	0.9680
No log	37.0	148	0.8457	0.4099	0.8448	0.9192
No log	38.0	152	0.8349	0.3217	0.8333	0.9129
No log	39.0	156	0.7902	0.3725	0.7887	0.8881
No log	40.0	160	0.7865	0.3823	0.7850	0.8860
No log	41.0	164	0.7430	0.4092	0.7416	0.8612
No log	42.0	168	0.8421	0.3400	0.8405	0.9168
No log	43.0	172	0.7728	0.3936	0.7716	0.8784
No log	44.0	176	0.8136	0.3710	0.8121	0.9012
No log	45.0	180	0.7670	0.4060	0.7658	0.8751
No log	46.0	184	0.9081	0.3418	0.9064	0.9521

Framework versions

Transformers 4.51.1
Pytorch 2.5.1+cu124
Datasets 3.5.0
Tokenizers 0.21.0

genki10/BERT_V8_sp10_lw20_ex200_lo50_k10_k10_fold1

BERT_V8_sp10_lw20_ex200_lo50_k10_k10_fold1

Model description

Intended uses & limitations

Training and evaluation data

Training procedure

Training hyperparameters

Training results

Framework versions

genki10/
BERT_V8_sp10_lw20_ex200_lo50_k10_k10_fold1