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	9.7123	0.0	9.7098	3.1161
No log	2.0	8	6.5119	0.0	6.5097	2.5514
No log	3.0	12	4.3347	0.0	4.3327	2.0815
No log	4.0	16	2.7193	0.0	2.7175	1.6485
No log	5.0	20	1.6449	0.0211	1.6433	1.2819
No log	6.0	24	1.0815	0.0	1.0801	1.0393
No log	7.0	28	0.9650	0.0154	0.9635	0.9816
No log	8.0	32	0.9112	0.0816	0.9098	0.9538
No log	9.0	36	1.1881	0.1337	1.1863	1.0892
No log	10.0	40	0.7721	0.2911	0.7706	0.8778
No log	11.0	44	0.8386	0.3790	0.8367	0.9147
No log	12.0	48	0.7274	0.3276	0.7260	0.8520
No log	13.0	52	0.7120	0.4369	0.7103	0.8428
No log	14.0	56	0.6037	0.4354	0.6023	0.7761
No log	15.0	60	0.6211	0.4809	0.6197	0.7872
No log	16.0	64	0.7413	0.4333	0.7397	0.8600
No log	17.0	68	0.8453	0.3404	0.8437	0.9185
No log	18.0	72	0.7801	0.3978	0.7788	0.8825
No log	19.0	76	1.1006	0.3001	1.0987	1.0482
No log	20.0	80	0.6863	0.4958	0.6853	0.8278
No log	21.0	84	1.0359	0.3114	1.0340	1.0168
No log	22.0	88	0.6476	0.4982	0.6465	0.8040
No log	23.0	92	1.0882	0.3073	1.0863	1.0422
No log	24.0	96	0.8331	0.3386	0.8315	0.9119
No log	25.0	100	0.6979	0.4194	0.6967	0.8347
No log	26.0	104	1.1608	0.2517	1.1588	1.0765
No log	27.0	108	0.6940	0.3972	0.6927	0.8323
No log	28.0	112	0.9441	0.2924	0.9423	0.9707
No log	29.0	116	0.7700	0.3247	0.7685	0.8766
No log	30.0	120	0.9107	0.3494	0.9089	0.9533
No log	31.0	124	0.8021	0.3380	0.8005	0.8947
No log	32.0	128	0.7184	0.4431	0.7169	0.8467
No log	33.0	132	0.7299	0.4393	0.7283	0.8534
No log	34.0	136	0.8077	0.3639	0.8061	0.8978
No log	35.0	140	0.8515	0.3634	0.8498	0.9219
No log	36.0	144	0.8896	0.3586	0.8879	0.9423
No log	37.0	148	1.1740	0.2417	1.1721	1.0826

genki10/Trial3BERT_AugV8_k5_task1_organization_sp040_lw010_fold1

Trial3BERT_AugV8_k5_task1_organization_sp040_lw010_fold1