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	7	6.1246	0.0075	6.1246	2.4748
No log	2.0	14	3.0389	0.0	3.0389	1.7432
No log	3.0	21	1.3229	0.0316	1.3229	1.1502
No log	4.0	28	1.0427	0.0316	1.0427	1.0211
No log	5.0	35	1.4409	0.0151	1.4409	1.2004
No log	6.0	42	0.7892	0.3689	0.7892	0.8884
No log	7.0	49	0.8122	0.2569	0.8122	0.9012
No log	8.0	56	0.7282	0.3410	0.7282	0.8533
No log	9.0	63	0.6628	0.3547	0.6628	0.8141
No log	10.0	70	0.6982	0.3713	0.6982	0.8356
No log	11.0	77	0.7386	0.4020	0.7386	0.8594
No log	12.0	84	0.9223	0.3823	0.9223	0.9603
No log	13.0	91	0.6944	0.3883	0.6944	0.8333
No log	14.0	98	0.8427	0.3382	0.8427	0.9180
No log	15.0	105	0.6942	0.4224	0.6942	0.8332
No log	16.0	112	0.8425	0.3251	0.8425	0.9179
No log	17.0	119	0.7859	0.3410	0.7859	0.8865
No log	18.0	126	0.7371	0.4094	0.7371	0.8586
No log	19.0	133	0.8593	0.2959	0.8593	0.9270
No log	20.0	140	0.7547	0.3638	0.7547	0.8688
No log	21.0	147	0.8457	0.3169	0.8457	0.9196
No log	22.0	154	0.7803	0.3414	0.7803	0.8833
No log	23.0	161	0.9002	0.2717	0.9002	0.9488
No log	24.0	168	0.7746	0.3135	0.7746	0.8801
No log	25.0	175	0.8775	0.2909	0.8775	0.9367
No log	26.0	182	0.7917	0.3140	0.7917	0.8898
No log	27.0	189	0.8313	0.2862	0.8313	0.9118
No log	28.0	196	0.8602	0.3015	0.8602	0.9275
No log	29.0	203	0.8003	0.3182	0.8003	0.8946
No log	30.0	210	0.8697	0.2699	0.8697	0.9326

genki10/Trial3BERT_AugV8_k10_task1_organization_sp010_lw040_fold0

Trial3BERT_AugV8_k10_task1_organization_sp010_lw040_fold0