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	5.6045	0.0744	5.6050	2.3675
No log	2.0	10	3.0058	0.0	3.0062	1.7338
No log	3.0	15	1.3275	0.0	1.3280	1.1524
No log	4.0	20	0.8508	0.3139	0.8512	0.9226
No log	5.0	25	0.7489	0.0722	0.7491	0.8655
No log	6.0	30	0.5809	0.4290	0.5810	0.7622
No log	7.0	35	0.6266	0.4925	0.6266	0.7916
No log	8.0	40	0.5214	0.5198	0.5214	0.7221
No log	9.0	45	0.5572	0.4405	0.5572	0.7465
No log	10.0	50	0.7531	0.4581	0.7529	0.8677
No log	11.0	55	0.4783	0.5979	0.4782	0.6915
No log	12.0	60	0.5672	0.5238	0.5671	0.7531
No log	13.0	65	0.5267	0.5901	0.5264	0.7255
No log	14.0	70	0.5702	0.5314	0.5699	0.7549
No log	15.0	75	0.5436	0.5278	0.5432	0.7371
No log	16.0	80	0.6817	0.4377	0.6815	0.8255
No log	17.0	85	0.5479	0.5544	0.5475	0.7400
No log	18.0	90	0.5315	0.5393	0.5312	0.7288
No log	19.0	95	0.5667	0.5189	0.5663	0.7525
No log	20.0	100	0.5598	0.4906	0.5596	0.7480
No log	21.0	105	0.5609	0.5003	0.5607	0.7488
No log	22.0	110	0.5653	0.5091	0.5652	0.7518
No log	23.0	115	0.5155	0.5391	0.5153	0.7178
No log	24.0	120	0.5133	0.5360	0.5131	0.7163
No log	25.0	125	0.5321	0.5025	0.5318	0.7293
No log	26.0	130	0.5997	0.4614	0.5996	0.7743
No log	27.0	135	0.6051	0.5023	0.6050	0.7778
No log	28.0	140	0.5337	0.5187	0.5335	0.7304
No log	29.0	145	0.5858	0.4983	0.5857	0.7653
No log	30.0	150	0.5379	0.4928	0.5378	0.7333
No log	31.0	155	0.5373	0.5160	0.5372	0.7329
No log	32.0	160	0.6084	0.5077	0.6083	0.7799
No log	33.0	165	0.5638	0.4869	0.5636	0.7507
No log	34.0	170	0.5418	0.4970	0.5416	0.7359
No log	35.0	175	0.5474	0.4849	0.5472	0.7397
No log	36.0	180	0.5595	0.4981	0.5594	0.7479
No log	37.0	185	0.6251	0.4702	0.6250	0.7906
No log	38.0	190	0.5888	0.5054	0.5887	0.7673
No log	39.0	195	0.5449	0.4647	0.5448	0.7381
No log	40.0	200	0.5407	0.4905	0.5405	0.7352
No log	41.0	205	0.5604	0.4552	0.5603	0.7485

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_fold2

BERT_V8_sp10_lw40_ex100_lo50_k10_k10_fold2

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_fold2