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	5	9.7313	0.0018	9.7313	3.1195
No log	2.0	10	7.0923	0.0	7.0923	2.6631
No log	3.0	15	4.9524	0.0079	4.9524	2.2254
No log	4.0	20	2.7718	0.0	2.7718	1.6649
No log	5.0	25	1.6157	0.0213	1.6157	1.2711
No log	6.0	30	0.9867	0.0213	0.9867	0.9933
No log	7.0	35	0.8428	0.1422	0.8428	0.9180
No log	8.0	40	0.8178	0.3365	0.8178	0.9043
No log	9.0	45	0.5288	0.4828	0.5288	0.7272
No log	10.0	50	0.5852	0.4456	0.5852	0.7650
No log	11.0	55	1.1145	0.3527	1.1145	1.0557
No log	12.0	60	0.5823	0.5364	0.5823	0.7631
No log	13.0	65	0.5501	0.5590	0.5501	0.7417
No log	14.0	70	0.8906	0.4321	0.8906	0.9437
No log	15.0	75	0.5745	0.5562	0.5745	0.7580
No log	16.0	80	0.5811	0.5652	0.5811	0.7623
No log	17.0	85	0.6983	0.4992	0.6983	0.8356
No log	18.0	90	0.5424	0.5727	0.5424	0.7365
No log	19.0	95	0.5967	0.5439	0.5967	0.7724
No log	20.0	100	0.6400	0.5238	0.6400	0.8000
No log	21.0	105	0.6356	0.5183	0.6356	0.7972
No log	22.0	110	0.5887	0.5391	0.5887	0.7672
No log	23.0	115	0.6803	0.5022	0.6803	0.8248
No log	24.0	120	0.6155	0.5284	0.6155	0.7845
No log	25.0	125	0.6055	0.5155	0.6055	0.7781
No log	26.0	130	0.7915	0.4034	0.7915	0.8897
No log	27.0	135	0.5866	0.5360	0.5866	0.7659
No log	28.0	140	0.6735	0.5138	0.6735	0.8206
No log	29.0	145	0.7194	0.4672	0.7194	0.8482
No log	30.0	150	0.5788	0.5716	0.5788	0.7608
No log	31.0	155	0.5930	0.5630	0.5930	0.7700
No log	32.0	160	0.5846	0.5549	0.5846	0.7646
No log	33.0	165	0.6073	0.5435	0.6073	0.7793
No log	34.0	170	0.5507	0.5881	0.5507	0.7421
No log	35.0	175	0.5998	0.5372	0.5998	0.7745
No log	36.0	180	0.6228	0.5345	0.6228	0.7892
No log	37.0	185	0.7055	0.4668	0.7055	0.8399
No log	38.0	190	0.5426	0.5503	0.5426	0.7366
No log	39.0	195	0.6685	0.4995	0.6685	0.8176
No log	40.0	200	0.5632	0.5639	0.5632	0.7505
No log	41.0	205	0.5914	0.5579	0.5914	0.7690
No log	42.0	210	0.5611	0.5343	0.5611	0.7491
No log	43.0	215	0.6325	0.5322	0.6325	0.7953
No log	44.0	220	0.5685	0.5605	0.5685	0.7540
No log	45.0	225	0.6755	0.5044	0.6755	0.8219
No log	46.0	230	0.6317	0.5421	0.6317	0.7948
No log	47.0	235	0.5740	0.5345	0.5740	0.7576
No log	48.0	240	0.5575	0.5559	0.5575	0.7467
No log	49.0	245	0.6267	0.5478	0.6267	0.7917
No log	50.0	250	0.6389	0.5231	0.6389	0.7993
No log	51.0	255	0.6186	0.5486	0.6186	0.7865
No log	52.0	260	0.6119	0.5532	0.6119	0.7822
No log	53.0	265	0.6012	0.5473	0.6012	0.7754
No log	54.0	270	0.5799	0.5414	0.5799	0.7615
No log	55.0	275	0.6068	0.5292	0.6068	0.7790
No log	56.0	280	0.6163	0.5526	0.6163	0.7850
No log	57.0	285	0.5679	0.5450	0.5679	0.7536
No log	58.0	290	0.6604	0.4940	0.6604	0.8126
No log	59.0	295	0.5852	0.5575	0.5852	0.7650
No log	60.0	300	0.6722	0.5045	0.6722	0.8199
No log	61.0	305	0.6213	0.5325	0.6213	0.7882
No log	62.0	310	0.5724	0.5348	0.5724	0.7566
No log	63.0	315	0.5896	0.5573	0.5896	0.7678
No log	64.0	320	0.6102	0.5454	0.6102	0.7811

Framework versions

Transformers 4.51.1
Pytorch 2.5.1+cu124
Datasets 3.5.0
Tokenizers 0.21.0

genki10/BERT_V8_sp10_lw40_ex50_lo50_k10_k10_fold4

BERT_V8_sp10_lw40_ex50_lo50_k10_k10_fold4

Model description

Intended uses & limitations

Training and evaluation data

Training procedure

Training hyperparameters

Training results

Framework versions

genki10/
BERT_V8_sp10_lw40_ex50_lo50_k10_k10_fold4