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	8.0110	0.0016	8.0110	2.8304
No log	2.0	10	3.7223	0.0133	3.7223	1.9293
No log	3.0	15	1.7032	0.0445	1.7032	1.3051
No log	4.0	20	0.9440	0.0212	0.9440	0.9716
No log	5.0	25	0.8259	0.0785	0.8259	0.9088
No log	6.0	30	0.6934	0.4221	0.6934	0.8327
No log	7.0	35	0.5956	0.4413	0.5956	0.7718
No log	8.0	40	0.5756	0.5191	0.5756	0.7587
No log	9.0	45	0.9277	0.4125	0.9277	0.9632
No log	10.0	50	0.9035	0.4267	0.9035	0.9505
No log	11.0	55	0.7443	0.4779	0.7443	0.8628
No log	12.0	60	0.6462	0.4710	0.6462	0.8039
No log	13.0	65	0.5709	0.5837	0.5709	0.7556
No log	14.0	70	0.5909	0.5480	0.5909	0.7687
No log	15.0	75	1.1276	0.3733	1.1276	1.0619
No log	16.0	80	0.9380	0.4298	0.9380	0.9685
No log	17.0	85	1.1009	0.3866	1.1009	1.0492
No log	18.0	90	0.6830	0.5477	0.6830	0.8264
No log	19.0	95	1.2763	0.2567	1.2763	1.1297
No log	20.0	100	0.5386	0.5618	0.5386	0.7339
No log	21.0	105	0.6254	0.5383	0.6254	0.7908
No log	22.0	110	0.5906	0.5644	0.5906	0.7685
No log	23.0	115	0.5822	0.5481	0.5822	0.7630
No log	24.0	120	0.6293	0.5186	0.6293	0.7933
No log	25.0	125	0.6807	0.4921	0.6807	0.8250
No log	26.0	130	0.6228	0.5603	0.6228	0.7892
No log	27.0	135	0.6456	0.5265	0.6456	0.8035
No log	28.0	140	0.6960	0.5144	0.6960	0.8343
No log	29.0	145	0.6997	0.5108	0.6997	0.8365
No log	30.0	150	0.5544	0.5874	0.5544	0.7445
No log	31.0	155	0.5893	0.5807	0.5893	0.7677
No log	32.0	160	0.6098	0.5276	0.6098	0.7809
No log	33.0	165	0.5502	0.5591	0.5502	0.7417
No log	34.0	170	0.6434	0.5004	0.6434	0.8021
No log	35.0	175	0.5442	0.5972	0.5442	0.7377
No log	36.0	180	0.7800	0.4591	0.7800	0.8832
No log	37.0	185	0.6246	0.5462	0.6246	0.7903
No log	38.0	190	0.5689	0.5711	0.5689	0.7543
No log	39.0	195	0.7020	0.5007	0.7020	0.8378
No log	40.0	200	0.5394	0.5632	0.5394	0.7344
No log	41.0	205	0.7408	0.4730	0.7408	0.8607
No log	42.0	210	0.6519	0.4969	0.6519	0.8074
No log	43.0	215	0.5501	0.5829	0.5501	0.7417
No log	44.0	220	0.5728	0.5739	0.5728	0.7568
No log	45.0	225	0.6013	0.5591	0.6013	0.7754
No log	46.0	230	0.5901	0.5639	0.5901	0.7682
No log	47.0	235	0.5973	0.5626	0.5973	0.7728
No log	48.0	240	0.5594	0.5727	0.5594	0.7479
No log	49.0	245	0.5854	0.5461	0.5854	0.7651
No log	50.0	250	0.7211	0.4734	0.7211	0.8492
No log	51.0	255	0.5983	0.5472	0.5983	0.7735
No log	52.0	260	0.5900	0.5526	0.5900	0.7681
No log	53.0	265	0.7121	0.5231	0.7121	0.8439
No log	54.0	270	0.5529	0.5726	0.5529	0.7436
No log	55.0	275	0.5608	0.5590	0.5608	0.7489
No log	56.0	280	0.5933	0.5447	0.5933	0.7702
No log	57.0	285	0.7129	0.5212	0.7129	0.8443
No log	58.0	290	0.5372	0.5517	0.5372	0.7329
No log	59.0	295	0.6164	0.5377	0.6164	0.7851
No log	60.0	300	0.6424	0.5227	0.6424	0.8015
No log	61.0	305	0.5711	0.5618	0.5711	0.7557
No log	62.0	310	0.6147	0.5302	0.6147	0.7840
No log	63.0	315	0.6013	0.5451	0.6013	0.7755
No log	64.0	320	0.5445	0.5895	0.5445	0.7379
No log	65.0	325	0.7256	0.4924	0.7256	0.8518

Framework versions

Transformers 4.51.1
Pytorch 2.5.1+cu124
Datasets 3.5.0
Tokenizers 0.21.0

genki10/BERT_V8_sp10_lw20_ex100_lo100_k10_k10_fold4

BERT_V8_sp10_lw20_ex100_lo100_k10_k10_fold4

Model description

Intended uses & limitations

Training and evaluation data

Training procedure

Training hyperparameters

Training results

Framework versions

genki10/
BERT_V8_sp10_lw20_ex100_lo100_k10_k10_fold4