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	8	5.3735	0.0285	5.3735	2.3181
No log	2.0	16	2.2247	0.0090	2.2247	1.4915
No log	3.0	24	1.4778	0.0420	1.4778	1.2157
No log	4.0	32	1.6164	0.0630	1.6164	1.2714
No log	5.0	40	0.8386	0.3226	0.8386	0.9158
No log	6.0	48	0.9360	0.2205	0.9360	0.9675
No log	7.0	56	0.9161	0.2770	0.9161	0.9571
No log	8.0	64	1.0685	0.2474	1.0685	1.0337
No log	9.0	72	0.8214	0.2743	0.8214	0.9063
No log	10.0	80	0.6390	0.4477	0.6390	0.7994
No log	11.0	88	0.9827	0.2400	0.9827	0.9913
No log	12.0	96	1.2754	0.1599	1.2754	1.1293
No log	13.0	104	1.1600	0.2597	1.1600	1.0770
No log	14.0	112	1.0165	0.2842	1.0165	1.0082
No log	15.0	120	1.6261	0.1863	1.6261	1.2752
No log	16.0	128	1.4793	0.1809	1.4793	1.2163
No log	17.0	136	1.1785	0.2351	1.1785	1.0856
No log	18.0	144	1.1525	0.1485	1.1525	1.0736
No log	19.0	152	1.5034	0.1491	1.5034	1.2261
No log	20.0	160	1.3246	0.1739	1.3246	1.1509
No log	21.0	168	1.0080	0.2329	1.0080	1.0040
No log	22.0	176	1.0475	0.2298	1.0475	1.0235
No log	23.0	184	1.3181	0.2087	1.3181	1.1481
No log	24.0	192	1.2906	0.1516	1.2906	1.1360
No log	25.0	200	1.0212	0.2159	1.0212	1.0105

genki10/BERT_AugV8_k10_task1_organization_sp020_lw070_fold4

BERT_AugV8_k10_task1_organization_sp020_lw070_fold4