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	9.5687	0.0	9.5689	3.0934
No log	2.0	6	8.8420	0.0	8.8421	2.9736
No log	3.0	9	7.6946	0.0	7.6949	2.7740
No log	4.0	12	6.4454	0.0	6.4456	2.5388
No log	5.0	15	5.1166	0.0102	5.1169	2.2621
No log	6.0	18	3.9098	0.0	3.9102	1.9774
No log	7.0	21	2.8945	0.0	2.8949	1.7014
No log	8.0	24	2.2005	0.1693	2.2009	1.4836
No log	9.0	27	1.5053	0.0280	1.5057	1.2271
No log	10.0	30	1.0844	0.0280	1.0848	1.0415
No log	11.0	33	1.0395	0.0280	1.0398	1.0197
No log	12.0	36	1.4598	0.1429	1.4602	1.2084
No log	13.0	39	1.1225	0.1031	1.1229	1.0597
No log	14.0	42	0.6596	0.4619	0.6599	0.8123
No log	15.0	45	0.9187	0.1848	0.9189	0.9586
No log	16.0	48	0.8377	0.3440	0.8378	0.9153
No log	17.0	51	0.9582	0.3506	0.9580	0.9788
No log	18.0	54	1.1449	0.3423	1.1444	1.0697
No log	19.0	57	0.6567	0.4582	0.6561	0.8100
No log	20.0	60	0.6011	0.4767	0.6006	0.7750
No log	21.0	63	0.5863	0.4902	0.5858	0.7654
No log	22.0	66	0.7042	0.4365	0.7036	0.8388
No log	23.0	69	0.6141	0.5247	0.6136	0.7833
No log	24.0	72	0.8402	0.4243	0.8393	0.9161
No log	25.0	75	0.6802	0.5222	0.6795	0.8243
No log	26.0	78	1.3449	0.2973	1.3439	1.1593
No log	27.0	81	0.7782	0.4597	0.7775	0.8817
No log	28.0	84	0.9208	0.3620	0.9201	0.9592
No log	29.0	87	0.7903	0.4115	0.7897	0.8887
No log	30.0	90	0.7278	0.4702	0.7272	0.8528
No log	31.0	93	0.8234	0.4133	0.8227	0.9070
No log	32.0	96	1.0664	0.3294	1.0658	1.0324
No log	33.0	99	0.9190	0.3793	0.9185	0.9584
No log	34.0	102	0.9285	0.3885	0.9278	0.9632
No log	35.0	105	0.9468	0.3869	0.9459	0.9726
No log	36.0	108	0.7876	0.4234	0.7869	0.8871
No log	37.0	111	0.6402	0.4792	0.6398	0.7999
No log	38.0	114	0.9756	0.3397	0.9750	0.9874

genki10/BERT_AugV8_k3_task1_organization_sp040_lw010_fold2

BERT_AugV8_k3_task1_organization_sp040_lw010_fold2