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	5	11.8862	-0.0115	11.8842	3.4473
No log	2.0	10	7.5155	0.0	7.5137	2.7411
No log	3.0	15	4.2288	0.0	4.2277	2.0561
No log	4.0	20	2.0917	0.0788	2.0910	1.4460
No log	5.0	25	1.1396	0.0102	1.1391	1.0673
No log	6.0	30	1.1539	0.0266	1.1534	1.0740
No log	7.0	35	1.5775	0.1079	1.5771	1.2558
No log	8.0	40	0.9307	0.2269	0.9308	0.9648
No log	9.0	45	1.8035	0.1272	1.8039	1.3431
No log	10.0	50	1.8448	0.1730	1.8455	1.3585
No log	11.0	55	1.6875	0.1955	1.6882	1.2993
No log	12.0	60	1.1618	0.2528	1.1626	1.0782
No log	13.0	65	1.3545	0.1881	1.3549	1.1640
No log	14.0	70	1.3361	0.2019	1.3363	1.1560
No log	15.0	75	1.3675	0.1840	1.3677	1.1695
No log	16.0	80	1.6534	0.1576	1.6535	1.2859
No log	17.0	85	2.0434	0.1087	2.0434	1.4295
No log	18.0	90	1.7967	0.1615	1.7968	1.3404
No log	19.0	95	1.2303	0.2431	1.2305	1.1093
No log	20.0	100	1.0403	0.2568	1.0406	1.0201
No log	21.0	105	1.4691	0.1959	1.4692	1.2121
No log	22.0	110	1.8689	0.1533	1.8688	1.3670
No log	23.0	115	1.6469	0.1777	1.6469	1.2833
No log	24.0	120	1.4319	0.1843	1.4320	1.1966
No log	25.0	125	1.2960	0.2307	1.2961	1.1385
No log	26.0	130	1.1589	0.2415	1.1589	1.0765
No log	27.0	135	1.2184	0.2403	1.2184	1.1038
No log	28.0	140	1.4231	0.2202	1.4232	1.1930
No log	29.0	145	1.4942	0.1860	1.4944	1.2224
No log	30.0	150	1.4616	0.1905	1.4617	1.2090
No log	31.0	155	1.0092	0.2511	1.0093	1.0047
No log	32.0	160	1.4467	0.1674	1.4467	1.2028
No log	33.0	165	1.7962	0.1649	1.7962	1.3402
No log	34.0	170	1.4803	0.1703	1.4803	1.2167
No log	35.0	175	1.5363	0.1651	1.5362	1.2394

genki10/Trial3BERT_AugV8_k7_task1_organization_sp020_lw030_fold3

Trial3BERT_AugV8_k7_task1_organization_sp020_lw030_fold3