learning_rate: 2e-05
train_batch_size: 64
eval_batch_size: 64
seed: 42
optimizer: Use 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: 150

Training Loss	Epoch	Step	Validation Loss	Qwk	Mse	Rmse
No log	1.0	3	10.5104	0.0325	10.5078	3.2416
No log	2.0	6	6.9995	0.0	6.9971	2.6452
No log	3.0	9	4.9492	0.0238	4.9471	2.2242
No log	4.0	12	3.2526	0.0	3.2508	1.8030
No log	5.0	15	2.2392	0.1489	2.2375	1.4958
No log	6.0	18	1.5395	0.0106	1.5379	1.2401
No log	7.0	21	1.6064	0.0172	1.6048	1.2668
No log	8.0	24	1.8075	0.0533	1.8058	1.3438
No log	9.0	27	1.0215	0.0	1.0200	1.0100
No log	10.0	30	1.5842	0.0676	1.5828	1.2581
No log	11.0	33	1.3725	0.1123	1.3709	1.1709
No log	12.0	36	1.4777	0.1446	1.4760	1.2149
No log	13.0	39	1.2903	0.1299	1.2885	1.1351
No log	14.0	42	1.5229	0.1636	1.5209	1.2332
No log	15.0	45	0.9456	0.2966	0.9438	0.9715
No log	16.0	48	1.0656	0.2408	1.0637	1.0313
No log	17.0	51	0.7734	0.3335	0.7719	0.8786
No log	18.0	54	0.7657	0.3494	0.7643	0.8743
No log	19.0	57	1.1494	0.2397	1.1475	1.0712
No log	20.0	60	0.8837	0.2779	0.8824	0.9394
No log	21.0	63	0.9496	0.2741	0.9477	0.9735
No log	22.0	66	1.0534	0.2835	1.0513	1.0253
No log	23.0	69	0.8554	0.3727	0.8536	0.9239
No log	24.0	72	1.3938	0.2777	1.3914	1.1796
No log	25.0	75	0.8753	0.3416	0.8734	0.9345
No log	26.0	78	2.2477	0.0869	2.2447	1.4982
No log	27.0	81	1.0341	0.2923	1.0316	1.0157
No log	28.0	84	1.8651	0.0772	1.8621	1.3646
No log	29.0	87	1.0424	0.2385	1.0401	1.0199
No log	30.0	90	1.8928	0.0859	1.8901	1.3748
No log	31.0	93	1.2267	0.2083	1.2242	1.1064
No log	32.0	96	1.6785	0.1129	1.6759	1.2946
No log	33.0	99	1.0634	0.2517	1.0610	1.0300
No log	34.0	102	1.8970	0.0849	1.8942	1.3763
No log	35.0	105	1.1083	0.2290	1.1057	1.0515
No log	36.0	108	1.7450	0.1248	1.7420	1.3199
No log	37.0	111	1.2839	0.2028	1.2812	1.1319
No log	38.0	114	1.3469	0.1468	1.3442	1.1594

genki10/BERT_AugV8_k3_task1_organization_sp040_lw040_fold1

BERT_AugV8_k3_task1_organization_sp040_lw040_fold1