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 Loss	Epoch	Step	Validation Loss	Qwk	Mse	Rmse
No log	1.0	5	8.2988	0.0	8.2965	2.8804
No log	2.0	10	4.4269	0.0118	4.4249	2.1035
No log	3.0	15	2.5089	0.0	2.5071	1.5834
No log	4.0	20	1.4466	0.0106	1.4451	1.2021
No log	5.0	25	0.9685	0.0	0.9672	0.9835
No log	6.0	30	1.1923	0.0790	1.1908	1.0913
No log	7.0	35	0.6992	0.4461	0.6980	0.8355
No log	8.0	40	1.4548	0.2151	1.4535	1.2056
No log	9.0	45	0.7945	0.3696	0.7932	0.8906
No log	10.0	50	1.1012	0.1759	1.0997	1.0487
No log	11.0	55	0.8510	0.2877	0.8496	0.9217
No log	12.0	60	0.8907	0.2976	0.8893	0.9430
No log	13.0	65	1.3075	0.2366	1.3060	1.1428
No log	14.0	70	1.1337	0.3073	1.1319	1.0639
No log	15.0	75	1.1702	0.3276	1.1682	1.0808
No log	16.0	80	0.9638	0.4080	0.9616	0.9806
No log	17.0	85	0.8020	0.4354	0.7999	0.8944
No log	18.0	90	1.3515	0.2804	1.3494	1.1616
No log	19.0	95	1.5560	0.2580	1.5540	1.2466
No log	20.0	100	1.1469	0.2942	1.1450	1.0700
No log	21.0	105	1.0308	0.3496	1.0287	1.0143
No log	22.0	110	0.9793	0.3654	0.9770	0.9885
No log	23.0	115	0.9752	0.3533	0.9729	0.9863
No log	24.0	120	1.5723	0.1795	1.5699	1.2529
No log	25.0	125	1.1663	0.2765	1.1640	1.0789
No log	26.0	130	1.0205	0.3355	1.0184	1.0092
No log	27.0	135	0.9199	0.3588	0.9179	0.9581
No log	28.0	140	1.2343	0.2830	1.2323	1.1101
No log	29.0	145	1.3878	0.2699	1.3858	1.1772
No log	30.0	150	1.0534	0.2912	1.0514	1.0254
No log	31.0	155	0.9399	0.3138	0.9379	0.9685
No log	32.0	160	1.6169	0.1995	1.6149	1.2708
No log	33.0	165	1.0530	0.3180	1.0510	1.0252
No log	34.0	170	0.9951	0.3350	0.9932	0.9966
No log	35.0	175	1.3152	0.2380	1.3131	1.1459
No log	36.0	180	0.8660	0.3760	0.8640	0.9295
No log	37.0	185	1.2676	0.2904	1.2655	1.1249

genki10/BERT_V8_sp10_lw40_ex50_lo00_k7_k7_fold1

BERT_V8_sp10_lw40_ex50_lo00_k7_k7_fold1