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: 100

Training Loss	Epoch	Step	Validation Loss	Qwk	Mse	Rmse
No log	1.0	8	5.9199	0.0250	5.9199	2.4331
No log	2.0	16	2.7331	0.0	2.7331	1.6532
No log	3.0	24	1.6454	0.0106	1.6454	1.2827
No log	4.0	32	1.2582	0.0316	1.2582	1.1217
No log	5.0	40	0.9739	0.0106	0.9739	0.9869
No log	6.0	48	0.8171	0.3363	0.8171	0.9039
No log	7.0	56	0.7090	0.2077	0.7090	0.8420
No log	8.0	64	0.7333	0.1730	0.7333	0.8563
No log	9.0	72	0.7268	0.3025	0.7268	0.8525
No log	10.0	80	0.7367	0.3996	0.7367	0.8583
No log	11.0	88	0.7169	0.4242	0.7169	0.8467
No log	12.0	96	0.6962	0.3946	0.6962	0.8344
No log	13.0	104	0.7549	0.3510	0.7549	0.8688
No log	14.0	112	0.6670	0.3847	0.6670	0.8167
No log	15.0	120	0.6844	0.4130	0.6844	0.8273
No log	16.0	128	0.6666	0.4042	0.6666	0.8165
No log	17.0	136	0.7832	0.3974	0.7832	0.8850
No log	18.0	144	0.7490	0.4289	0.7490	0.8654
No log	19.0	152	0.6883	0.3867	0.6883	0.8296
No log	20.0	160	0.6861	0.4303	0.6861	0.8283
No log	21.0	168	0.6647	0.4099	0.6647	0.8153
No log	22.0	176	0.7023	0.3643	0.7023	0.8380
No log	23.0	184	0.8977	0.3693	0.8977	0.9475
No log	24.0	192	0.6517	0.4085	0.6517	0.8073
No log	25.0	200	0.6192	0.4298	0.6192	0.7869
No log	26.0	208	0.6690	0.4576	0.6690	0.8179
No log	27.0	216	0.6558	0.4340	0.6558	0.8098
No log	28.0	224	0.6413	0.4563	0.6413	0.8008
No log	29.0	232	0.7080	0.3991	0.7080	0.8414
No log	30.0	240	0.7013	0.3407	0.7013	0.8374
No log	31.0	248	0.6557	0.4041	0.6557	0.8098
No log	32.0	256	0.7943	0.4344	0.7943	0.8913
No log	33.0	264	0.6566	0.4352	0.6566	0.8103
No log	34.0	272	0.6328	0.4552	0.6328	0.7955
No log	35.0	280	0.6802	0.4334	0.6802	0.8247
No log	36.0	288	0.6643	0.4395	0.6643	0.8151

genki10/ASAP_FineTuningBERT_AugV8_k10_task1_organization_k10_fold0

ASAP_FineTuningBERT_AugV8_k10_task1_organization_k10_fold0