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	7.6942	0.0	7.6928	2.7736
No log	2.0	8	4.4218	0.0124	4.4208	2.1026
No log	3.0	12	2.6336	0.0475	2.6327	1.6226
No log	4.0	16	1.6189	0.0391	1.6182	1.2721
No log	5.0	20	1.0420	0.0202	1.0414	1.0205
No log	6.0	24	0.8318	0.1586	0.8313	0.9118
No log	7.0	28	0.8125	0.1491	0.8122	0.9012
No log	8.0	32	0.8448	0.3036	0.8447	0.9191
No log	9.0	36	0.7053	0.3064	0.7055	0.8399
No log	10.0	40	1.0351	0.2556	1.0352	1.0174
No log	11.0	44	0.6780	0.4354	0.6783	0.8236
No log	12.0	48	0.9031	0.4491	0.9036	0.9506
No log	13.0	52	0.5686	0.5242	0.5688	0.7542
No log	14.0	56	0.5215	0.5651	0.5215	0.7222
No log	15.0	60	0.5512	0.5594	0.5513	0.7425
No log	16.0	64	0.6156	0.5585	0.6158	0.7847
No log	17.0	68	0.5445	0.5516	0.5447	0.7380
No log	18.0	72	0.5580	0.5393	0.5581	0.7471
No log	19.0	76	0.8333	0.4497	0.8335	0.9130
No log	20.0	80	0.5882	0.5322	0.5883	0.7670
No log	21.0	84	0.6905	0.5075	0.6908	0.8311
No log	22.0	88	0.6350	0.4988	0.6353	0.7971
No log	23.0	92	0.5967	0.4932	0.5969	0.7726
No log	24.0	96	0.5686	0.5013	0.5688	0.7542
No log	25.0	100	0.5580	0.5225	0.5582	0.7471
No log	26.0	104	0.6395	0.5339	0.6397	0.7998
No log	27.0	108	0.5560	0.5287	0.5562	0.7458
No log	28.0	112	0.5531	0.5222	0.5533	0.7438
No log	29.0	116	0.6978	0.5036	0.6979	0.8354
No log	30.0	120	0.5606	0.5395	0.5607	0.7488
No log	31.0	124	0.6726	0.5101	0.6727	0.8202
No log	32.0	128	0.5729	0.4880	0.5730	0.7570
No log	33.0	132	0.5918	0.4820	0.5920	0.7694
No log	34.0	136	0.5886	0.5214	0.5887	0.7673
No log	35.0	140	0.5679	0.5400	0.5681	0.7537
No log	36.0	144	0.7396	0.5127	0.7398	0.8601
No log	37.0	148	0.5919	0.5247	0.5920	0.7694
No log	38.0	152	0.5755	0.5011	0.5757	0.7587
No log	39.0	156	0.6102	0.5090	0.6105	0.7813
No log	40.0	160	0.6096	0.4946	0.6098	0.7809
No log	41.0	164	0.6287	0.4889	0.6289	0.7930
No log	42.0	168	0.6188	0.4987	0.6189	0.7867
No log	43.0	172	0.5848	0.5142	0.5849	0.7648
No log	44.0	176	0.6085	0.5132	0.6087	0.7802

Framework versions

Transformers 4.51.1
Pytorch 2.5.1+cu124
Datasets 3.5.0
Tokenizers 0.21.0

genki10/BERT_V8_sp10_lw20_ex100_lo50_k10_k10_fold3

BERT_V8_sp10_lw20_ex100_lo50_k10_k10_fold3

Model description

Intended uses & limitations

Training and evaluation data

Training procedure

Training hyperparameters

Training results

Framework versions

genki10/
BERT_V8_sp10_lw20_ex100_lo50_k10_k10_fold3