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	9.5811	0.0	9.5785	3.0949
No log	2.0	8	6.8809	0.0	6.8786	2.6227
No log	3.0	12	4.5073	0.0040	4.5052	2.1225
No log	4.0	16	2.5170	0.0	2.5152	1.5860
No log	5.0	20	1.2733	0.0106	1.2719	1.1278
No log	6.0	24	1.2858	0.0106	1.2844	1.1333
No log	7.0	28	2.2945	0.0773	2.2927	1.5142
No log	8.0	32	1.1517	0.0106	1.1503	1.0725
No log	9.0	36	1.8449	0.0643	1.8432	1.3576
No log	10.0	40	1.4965	0.0450	1.4948	1.2226
No log	11.0	44	1.9732	0.0465	1.9714	1.4041
No log	12.0	48	1.9387	0.0564	1.9370	1.3918
No log	13.0	52	1.2611	0.0796	1.2598	1.1224
No log	14.0	56	2.4793	-0.0212	2.4780	1.5742
No log	15.0	60	1.6531	0.0958	1.6518	1.2852
No log	16.0	64	1.6325	0.1132	1.6307	1.2770
No log	17.0	68	2.3239	0.0787	2.3216	1.5237
No log	18.0	72	1.1376	0.2452	1.1357	1.0657
No log	19.0	76	2.3367	0.0435	2.3343	1.5278
No log	20.0	80	1.8567	0.0438	1.8540	1.3616
No log	21.0	84	1.7186	0.0624	1.7161	1.3100
No log	22.0	88	1.5613	0.1268	1.5593	1.2487
No log	23.0	92	2.4574	0.0194	2.4552	1.5669
No log	24.0	96	1.4650	0.1584	1.4631	1.2096
No log	25.0	100	2.5420	0.0280	2.5397	1.5936
No log	26.0	104	1.3906	0.1716	1.3888	1.1785
No log	27.0	108	2.6062	0.0300	2.6035	1.6135
No log	28.0	112	1.3415	0.1572	1.3394	1.1573
No log	29.0	116	2.7342	0.0098	2.7316	1.6527
No log	30.0	120	1.4365	0.1132	1.4343	1.1976
No log	31.0	124	2.0040	0.0332	2.0015	1.4147
No log	32.0	128	1.5792	0.0694	1.5770	1.2558
No log	33.0	132	1.8801	0.0371	1.8778	1.3703

genki10/BERT_AugV8_k5_task1_organization_sp040_lw040_fold1

BERT_AugV8_k5_task1_organization_sp040_lw040_fold1