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	4	7.5087	0.0	7.5087	2.7402
No log	2.0	8	5.7804	0.0180	5.7804	2.4042
No log	3.0	12	4.0707	0.0039	4.0707	2.0176
No log	4.0	16	2.4399	0.1361	2.4399	1.5620
No log	5.0	20	1.4687	0.0316	1.4687	1.2119
No log	6.0	24	0.9369	0.0212	0.9369	0.9679
No log	7.0	28	0.7224	0.2577	0.7224	0.8499
No log	8.0	32	0.6271	0.4316	0.6271	0.7919
No log	9.0	36	0.5300	0.4344	0.5300	0.7280
No log	10.0	40	0.5407	0.3965	0.5407	0.7353
No log	11.0	44	0.9461	0.3517	0.9461	0.9727
No log	12.0	48	0.5558	0.3863	0.5558	0.7455
No log	13.0	52	0.6814	0.3112	0.6814	0.8255
No log	14.0	56	1.1843	0.3026	1.1843	1.0882
No log	15.0	60	0.5576	0.5111	0.5576	0.7467
No log	16.0	64	0.5646	0.5472	0.5646	0.7514
No log	17.0	68	0.5116	0.4882	0.5116	0.7152
No log	18.0	72	0.5748	0.4957	0.5748	0.7582
No log	19.0	76	0.5669	0.4500	0.5669	0.7529
No log	20.0	80	0.6180	0.4862	0.6180	0.7861
No log	21.0	84	0.6045	0.4902	0.6045	0.7775
No log	22.0	88	0.5698	0.5158	0.5698	0.7549
No log	23.0	92	0.6864	0.4741	0.6864	0.8285
No log	24.0	96	0.5580	0.4917	0.5580	0.7470
No log	25.0	100	0.8096	0.3538	0.8096	0.8998
No log	26.0	104	0.6093	0.4860	0.6093	0.7806
No log	27.0	108	0.8038	0.3887	0.8037	0.8965
No log	28.0	112	0.5754	0.4798	0.5754	0.7585
No log	29.0	116	0.5667	0.4363	0.5667	0.7528
No log	30.0	120	0.7486	0.3713	0.7486	0.8652
No log	31.0	124	0.6050	0.4968	0.6050	0.7778
No log	32.0	128	0.9411	0.3496	0.9411	0.9701
No log	33.0	132	0.6281	0.4685	0.6281	0.7925
No log	34.0	136	0.6570	0.4524	0.6570	0.8105
No log	35.0	140	0.6213	0.4712	0.6213	0.7882
No log	36.0	144	0.6696	0.4623	0.6696	0.8183
No log	37.0	148	0.6675	0.4585	0.6675	0.8170
No log	38.0	152	0.6218	0.4632	0.6218	0.7886
No log	39.0	156	0.5966	0.4831	0.5966	0.7724
No log	40.0	160	0.7012	0.4162	0.7012	0.8374
No log	41.0	164	0.6242	0.4702	0.6242	0.7901
No log	42.0	168	0.5839	0.4725	0.5839	0.7641
No log	43.0	172	0.6263	0.4903	0.6263	0.7914
No log	44.0	176	0.5956	0.4913	0.5956	0.7718
No log	45.0	180	0.6529	0.4768	0.6529	0.8080
No log	46.0	184	0.5769	0.5040	0.5769	0.7596

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_k7_k7_fold0

BERT_V8_sp10_lw40_ex50_lo50_k7_k7_fold0

Model description

Intended uses & limitations

Training and evaluation data

Training procedure

Training hyperparameters

Training results

Framework versions

genki10/
BERT_V8_sp10_lw40_ex50_lo50_k7_k7_fold0