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	7.9555	0.0	7.9541	2.8203
No log	2.0	8	4.4437	0.0124	4.4426	2.1077
No log	3.0	12	2.6921	0.0170	2.6912	1.6405
No log	4.0	16	1.6471	0.0365	1.6463	1.2831
No log	5.0	20	1.0985	0.0202	1.0979	1.0478
No log	6.0	24	0.9042	0.1099	0.9036	0.9506
No log	7.0	28	0.7247	0.2829	0.7244	0.8511
No log	8.0	32	0.6560	0.3957	0.6557	0.8098
No log	9.0	36	0.5803	0.4292	0.5802	0.7617
No log	10.0	40	0.5727	0.4893	0.5728	0.7569
No log	11.0	44	0.5781	0.4705	0.5785	0.7606
No log	12.0	48	0.5484	0.5329	0.5487	0.7407
No log	13.0	52	0.5386	0.5621	0.5389	0.7341
No log	14.0	56	0.5526	0.5372	0.5528	0.7435
No log	15.0	60	0.5650	0.5488	0.5651	0.7517
No log	16.0	64	0.8323	0.4532	0.8325	0.9124
No log	17.0	68	0.5702	0.5267	0.5704	0.7552
No log	18.0	72	0.8470	0.4201	0.8472	0.9205
No log	19.0	76	0.7041	0.5036	0.7042	0.8392
No log	20.0	80	0.6060	0.5191	0.6061	0.7785
No log	21.0	84	0.6083	0.4970	0.6084	0.7800
No log	22.0	88	0.8609	0.3460	0.8611	0.9280
No log	23.0	92	0.5911	0.5121	0.5913	0.7689
No log	24.0	96	0.8814	0.3550	0.8815	0.9389
No log	25.0	100	0.5808	0.4998	0.5809	0.7622
No log	26.0	104	0.5771	0.5186	0.5774	0.7598
No log	27.0	108	0.7680	0.4008	0.7682	0.8765
No log	28.0	112	0.6251	0.5153	0.6253	0.7908
No log	29.0	116	0.6301	0.5041	0.6304	0.7940
No log	30.0	120	0.6901	0.4705	0.6904	0.8309
No log	31.0	124	0.6229	0.5029	0.6231	0.7894
No log	32.0	128	0.5595	0.5592	0.5597	0.7481
No log	33.0	132	0.7436	0.4517	0.7437	0.8624
No log	34.0	136	0.5489	0.5415	0.5490	0.7410
No log	35.0	140	0.6844	0.4723	0.6846	0.8274
No log	36.0	144	0.5521	0.5291	0.5523	0.7432
No log	37.0	148	0.7361	0.4307	0.7362	0.8580
No log	38.0	152	0.6423	0.5053	0.6425	0.8015
No log	39.0	156	0.5665	0.5455	0.5667	0.7528
No log	40.0	160	0.8622	0.3808	0.8624	0.9287
No log	41.0	164	0.5599	0.5300	0.5601	0.7484
No log	42.0	168	0.7082	0.4515	0.7083	0.8416
No log	43.0	172	0.6354	0.4943	0.6356	0.7972

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_fold3

BERT_V8_sp10_lw40_ex50_lo50_k7_k7_fold3

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_fold3