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	7.6684	0.0	7.6684	2.7692
No log	2.0	10	4.7269	0.0079	4.7269	2.1741
No log	3.0	15	2.9501	0.0040	2.9501	1.7176
No log	4.0	20	1.7041	0.0420	1.7041	1.3054
No log	5.0	25	1.0393	0.0107	1.0393	1.0195
No log	6.0	30	1.1101	0.0316	1.1101	1.0536
No log	7.0	35	0.8041	0.3930	0.8041	0.8967
No log	8.0	40	1.0443	0.1475	1.0443	1.0219
No log	9.0	45	0.6134	0.5534	0.6134	0.7832
No log	10.0	50	0.6557	0.5186	0.6557	0.8098
No log	11.0	55	0.5856	0.5214	0.5856	0.7652
No log	12.0	60	0.5746	0.4901	0.5746	0.7580
No log	13.0	65	0.5776	0.5389	0.5776	0.7600
No log	14.0	70	0.5827	0.5972	0.5827	0.7633
No log	15.0	75	0.6713	0.5413	0.6713	0.8193
No log	16.0	80	0.6142	0.5424	0.6142	0.7837
No log	17.0	85	0.5902	0.5445	0.5902	0.7682
No log	18.0	90	0.6192	0.5142	0.6192	0.7869
No log	19.0	95	0.6382	0.4938	0.6382	0.7989
No log	20.0	100	0.7322	0.4367	0.7322	0.8557
No log	21.0	105	0.5552	0.5360	0.5552	0.7451
No log	22.0	110	0.6013	0.5348	0.6013	0.7754
No log	23.0	115	0.5994	0.5342	0.5994	0.7742
No log	24.0	120	0.5765	0.5367	0.5765	0.7593
No log	25.0	125	0.7742	0.4586	0.7742	0.8799
No log	26.0	130	0.5451	0.5520	0.5451	0.7383
No log	27.0	135	0.5504	0.5461	0.5504	0.7419
No log	28.0	140	0.6691	0.4841	0.6691	0.8180
No log	29.0	145	0.6882	0.4652	0.6882	0.8296
No log	30.0	150	0.6114	0.5281	0.6114	0.7819
No log	31.0	155	0.6275	0.5044	0.6275	0.7922
No log	32.0	160	0.6617	0.4898	0.6617	0.8134
No log	33.0	165	0.5840	0.5553	0.5840	0.7642
No log	34.0	170	0.7626	0.4832	0.7626	0.8733
No log	35.0	175	0.5597	0.5371	0.5597	0.7482
No log	36.0	180	0.5519	0.5480	0.5519	0.7429
No log	37.0	185	0.7289	0.4563	0.7289	0.8537
No log	38.0	190	0.5477	0.5422	0.5477	0.7401
No log	39.0	195	0.7415	0.4634	0.7415	0.8611
No log	40.0	200	0.7174	0.4874	0.7174	0.8470
No log	41.0	205	0.6133	0.5146	0.6133	0.7832
No log	42.0	210	0.5793	0.5357	0.5793	0.7611
No log	43.0	215	0.6025	0.5018	0.6025	0.7762
No log	44.0	220	0.7217	0.4927	0.7217	0.8495

Framework versions

Transformers 4.51.1
Pytorch 2.5.1+cu124
Datasets 3.5.0
Tokenizers 0.21.0

genki10/BERT_V8_sp10_lw40_ex10_lo00_k7_k7_fold4

BERT_V8_sp10_lw40_ex10_lo00_k7_k7_fold4

Model description

Intended uses & limitations

Training and evaluation data

Training procedure

Training hyperparameters

Training results

Framework versions

genki10/
BERT_V8_sp10_lw40_ex10_lo00_k7_k7_fold4