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 results

Training Loss	Epoch	Step	Validation Loss	Qwk	Mse	Rmse
No log	1.0	7	8.6316	0.0	8.6318	2.9380
No log	2.0	14	5.4630	0.0064	5.4633	2.3374
No log	3.0	21	2.4876	0.0005	2.4880	1.5773
No log	4.0	28	1.1733	0.0107	1.1737	1.0834
No log	5.0	35	0.9423	0.0213	0.9427	0.9709
No log	6.0	42	1.5849	0.2072	1.5852	1.2590
No log	7.0	49	2.4752	0.1201	2.4751	1.5732
No log	8.0	56	1.3770	0.2143	1.3768	1.1734
No log	9.0	63	1.1882	0.3104	1.1880	1.0900
No log	10.0	70	0.7477	0.4006	0.7475	0.8646
No log	11.0	77	1.5511	0.2088	1.5510	1.2454
No log	12.0	84	1.7249	0.2045	1.7249	1.3134
No log	13.0	91	1.3111	0.2408	1.3111	1.1450
No log	14.0	98	1.0516	0.2610	1.0516	1.0255
No log	15.0	105	1.4984	0.2021	1.4983	1.2240
No log	16.0	112	1.3496	0.2295	1.3493	1.1616
No log	17.0	119	1.2933	0.2323	1.2931	1.1371
No log	18.0	126	1.2980	0.1889	1.2980	1.1393
No log	19.0	133	1.7087	0.1334	1.7085	1.3071
No log	20.0	140	1.8473	0.1286	1.8473	1.3592
No log	21.0	147	2.3794	0.0874	2.3796	1.5426
No log	22.0	154	1.8563	0.1197	1.8562	1.3624
No log	23.0	161	2.1004	0.1026	2.1003	1.4492
No log	24.0	168	2.4220	0.0826	2.4220	1.5563
No log	25.0	175	1.7442	0.1147	1.7441	1.3206
No log	26.0	182	1.6175	0.1358	1.6174	1.2718
No log	27.0	189	1.7776	0.1127	1.7776	1.3333
No log	28.0	196	1.9236	0.1158	1.9236	1.3869
No log	29.0	203	2.3211	0.1013	2.3210	1.5235
No log	30.0	210	2.2213	0.0978	2.2211	1.4903
No log	31.0	217	1.9166	0.1195	1.9165	1.3844
No log	32.0	224	1.2384	0.2021	1.2382	1.1128
No log	33.0	231	1.8307	0.1273	1.8306	1.3530
No log	34.0	238	2.1980	0.1035	2.1980	1.4826
No log	35.0	245	1.5319	0.1577	1.5317	1.2376
No log	36.0	252	1.7768	0.1378	1.7766	1.3329
No log	37.0	259	1.8709	0.1297	1.8707	1.3677
No log	38.0	266	1.5552	0.1523	1.5552	1.2471
No log	39.0	273	1.7163	0.1412	1.7164	1.3101
No log	40.0	280	1.8281	0.1299	1.8282	1.3521

Framework versions

Transformers 4.51.1
Pytorch 2.5.1+cu124
Datasets 3.5.0
Tokenizers 0.21.0

genki10/BERT_V8_sp20_lw10_ex50_lo00_k10_k10_fold2

BERT_V8_sp20_lw10_ex50_lo00_k10_k10_fold2

Model description

Intended uses & limitations

Training and evaluation data

Training procedure

Training hyperparameters

Training results

Framework versions

genki10/
BERT_V8_sp20_lw10_ex50_lo00_k10_k10_fold2