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	4	12.2896	-0.0007	12.2897	3.5057
No log	2.0	8	7.9310	0.0	7.9311	2.8162
No log	3.0	12	5.4051	0.0117	5.4054	2.3250
No log	4.0	16	3.3893	0.0039	3.3897	1.8411
No log	5.0	20	1.6786	0.0422	1.6791	1.2958
No log	6.0	24	0.9710	0.0107	0.9715	0.9856
No log	7.0	28	1.5325	0.0213	1.5329	1.2381
No log	8.0	32	1.5697	0.1399	1.5698	1.2529
No log	9.0	36	1.0515	0.2103	1.0511	1.0252
No log	10.0	40	1.0773	0.2036	1.0764	1.0375
No log	11.0	44	1.1181	0.2183	1.1169	1.0568
No log	12.0	48	0.9389	0.2657	0.9377	0.9683
No log	13.0	52	1.2578	0.2301	1.2563	1.1208
No log	14.0	56	2.3649	0.1014	2.3634	1.5373
No log	15.0	60	1.2554	0.2252	1.2541	1.1199
No log	16.0	64	1.6755	0.1579	1.6740	1.2938
No log	17.0	68	1.4934	0.2005	1.4918	1.2214
No log	18.0	72	2.1484	0.1340	2.1467	1.4652
No log	19.0	76	1.4979	0.2238	1.4968	1.2234
No log	20.0	80	1.8279	0.1599	1.8268	1.3516
No log	21.0	84	1.2135	0.2495	1.2123	1.1011
No log	22.0	88	1.7871	0.1819	1.7859	1.3364
No log	23.0	92	1.8896	0.1557	1.8884	1.3742
No log	24.0	96	1.2847	0.2164	1.2833	1.1328
No log	25.0	100	2.0110	0.1308	2.0096	1.4176
No log	26.0	104	1.6666	0.1699	1.6655	1.2906
No log	27.0	108	1.7205	0.1568	1.7192	1.3112

genki10/Trial3BERT_AugV8_k5_task1_organization_sp050_lw010_fold2

Trial3BERT_AugV8_k5_task1_organization_sp050_lw010_fold2