learning_rate: 2e-05
train_batch_size: 64
eval_batch_size: 64
seed: 42
optimizer: Use OptimizerNames.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	7	6.3291	-0.0022	6.3291	2.5158
No log	2.0	14	3.3154	0.0	3.3154	1.8208
No log	3.0	21	1.4459	0.0316	1.4459	1.2024
No log	4.0	28	1.7657	0.0601	1.7657	1.3288
No log	5.0	35	1.3857	0.0484	1.3857	1.1771
No log	6.0	42	0.9092	0.1242	0.9092	0.9535
No log	7.0	49	0.7052	0.3888	0.7052	0.8397
No log	8.0	56	0.8489	0.3391	0.8489	0.9214
No log	9.0	63	0.9463	0.2241	0.9463	0.9728
No log	10.0	70	0.8988	0.2741	0.8988	0.9480
No log	11.0	77	1.0681	0.2394	1.0681	1.0335
No log	12.0	84	1.1241	0.2492	1.1241	1.0603
No log	13.0	91	0.9677	0.2599	0.9677	0.9837
No log	14.0	98	0.9343	0.2455	0.9343	0.9666
No log	15.0	105	1.0655	0.2278	1.0655	1.0322
No log	16.0	112	1.5269	0.1512	1.5269	1.2357
No log	17.0	119	1.7580	0.1077	1.7580	1.3259
No log	18.0	126	1.6647	0.1250	1.6647	1.2902
No log	19.0	133	0.9229	0.2802	0.9229	0.9607
No log	20.0	140	1.0661	0.2396	1.0661	1.0325
No log	21.0	147	2.2244	0.0993	2.2244	1.4915
No log	22.0	154	1.5976	0.0878	1.5976	1.2640
No log	23.0	161	1.0648	0.2343	1.0648	1.0319
No log	24.0	168	0.9727	0.2192	0.9727	0.9863
No log	25.0	175	1.0376	0.2296	1.0376	1.0186
No log	26.0	182	1.4088	0.1341	1.4088	1.1869
No log	27.0	189	1.5923	0.1273	1.5923	1.2619
No log	28.0	196	1.4920	0.1576	1.4920	1.2215
No log	29.0	203	1.1298	0.1925	1.1298	1.0629
No log	30.0	210	1.0726	0.2063	1.0726	1.0357
No log	31.0	217	1.1390	0.1666	1.1390	1.0673
No log	32.0	224	1.5666	0.1251	1.5666	1.2516
No log	33.0	231	1.4217	0.1339	1.4217	1.1923
No log	34.0	238	1.4338	0.1482	1.4338	1.1974
No log	35.0	245	1.4021	0.1538	1.4021	1.1841
No log	36.0	252	1.7893	0.0895	1.7893	1.3376
No log	37.0	259	1.3379	0.1581	1.3379	1.1567

genki10/BERT_V8_sp20_lw10_ex100_lo00_k10_k10_fold0

BERT_V8_sp20_lw10_ex100_lo00_k10_k10_fold0