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	6.9847	0.0	6.9847	2.6429
No log	2.0	10	4.7165	0.0115	4.7165	2.1717
No log	3.0	15	2.5808	0.0050	2.5808	1.6065
No log	4.0	20	1.3407	0.0316	1.3407	1.1579
No log	5.0	25	0.8195	0.2555	0.8195	0.9052
No log	6.0	30	0.6614	0.2148	0.6614	0.8133
No log	7.0	35	0.6437	0.4862	0.6437	0.8023
No log	8.0	40	0.7085	0.3985	0.7085	0.8417
No log	9.0	45	0.5326	0.4975	0.5326	0.7298
No log	10.0	50	0.6499	0.4946	0.6499	0.8061
No log	11.0	55	0.5478	0.5587	0.5478	0.7401
No log	12.0	60	0.6199	0.5323	0.6199	0.7873
No log	13.0	65	0.6532	0.5034	0.6532	0.8082
No log	14.0	70	0.7972	0.4032	0.7972	0.8929
No log	15.0	75	0.7727	0.4539	0.7727	0.8790
No log	16.0	80	0.8721	0.3180	0.8721	0.9339
No log	17.0	85	0.5850	0.4918	0.5850	0.7649
No log	18.0	90	0.6445	0.4859	0.6445	0.8028
No log	19.0	95	0.5899	0.5188	0.5899	0.7680
No log	20.0	100	0.6316	0.4909	0.6316	0.7947
No log	21.0	105	0.6853	0.4717	0.6853	0.8278
No log	22.0	110	0.5423	0.5105	0.5423	0.7364
No log	23.0	115	0.5840	0.5453	0.5840	0.7642
No log	24.0	120	0.5626	0.4963	0.5626	0.7501
No log	25.0	125	0.7507	0.3961	0.7507	0.8665
No log	26.0	130	0.5984	0.4845	0.5984	0.7735
No log	27.0	135	0.5748	0.4960	0.5748	0.7582
No log	28.0	140	0.7084	0.4539	0.7084	0.8417
No log	29.0	145	0.6055	0.4734	0.6055	0.7782
No log	30.0	150	0.6253	0.4533	0.6253	0.7908
No log	31.0	155	0.6453	0.4958	0.6453	0.8033
No log	32.0	160	0.6599	0.4794	0.6599	0.8123
No log	33.0	165	0.5598	0.5059	0.5598	0.7482
No log	34.0	170	0.6329	0.4547	0.6329	0.7955
No log	35.0	175	0.5714	0.5012	0.5714	0.7559
No log	36.0	180	0.5693	0.4861	0.5693	0.7545
No log	37.0	185	0.6526	0.4829	0.6526	0.8078
No log	38.0	190	0.5883	0.5111	0.5883	0.7670
No log	39.0	195	0.6308	0.4737	0.6308	0.7942
No log	40.0	200	0.5711	0.5177	0.5711	0.7557
No log	41.0	205	0.5692	0.5166	0.5692	0.7544

Framework versions

Transformers 4.51.1
Pytorch 2.5.1+cu124
Datasets 3.5.0
Tokenizers 0.21.0

genki10/BERT_V8_sp10_lw40_ex100_lo50_k10_k10_fold0

BERT_V8_sp10_lw40_ex100_lo50_k10_k10_fold0

Model description

Intended uses & limitations

Training and evaluation data

Training procedure

Training hyperparameters

Training results

Framework versions

genki10/
BERT_V8_sp10_lw40_ex100_lo50_k10_k10_fold0