learning_rate: 2e-05
train_batch_size: 64
eval_batch_size: 64
seed: 42
optimizer: Use 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	7.0779	0.0	7.0779	2.6604
No log	2.0	10	4.9359	0.0115	4.9359	2.2217
No log	3.0	15	2.8445	0.0	2.8445	1.6866
No log	4.0	20	1.4820	0.0316	1.4820	1.2174
No log	5.0	25	0.9369	0.0316	0.9369	0.9679
No log	6.0	30	1.4332	0.0897	1.4332	1.1972
No log	7.0	35	0.9664	0.0783	0.9664	0.9830
No log	8.0	40	1.4035	0.1928	1.4035	1.1847
No log	9.0	45	0.9962	0.2895	0.9962	0.9981
No log	10.0	50	0.6948	0.3403	0.6948	0.8336
No log	11.0	55	0.6851	0.3510	0.6851	0.8277
No log	12.0	60	0.9042	0.3461	0.9042	0.9509
No log	13.0	65	0.7462	0.4511	0.7462	0.8638
No log	14.0	70	1.1493	0.2532	1.1493	1.0720
No log	15.0	75	1.0605	0.2488	1.0605	1.0298
No log	16.0	80	1.0499	0.2812	1.0499	1.0247
No log	17.0	85	1.4007	0.1955	1.4007	1.1835
No log	18.0	90	0.7178	0.4285	0.7178	0.8472
No log	19.0	95	1.1891	0.2472	1.1891	1.0904
No log	20.0	100	1.4401	0.1866	1.4401	1.2000
No log	21.0	105	0.8365	0.3317	0.8365	0.9146
No log	22.0	110	1.6442	0.1752	1.6442	1.2823
No log	23.0	115	0.8020	0.3557	0.8020	0.8955
No log	24.0	120	1.5819	0.1806	1.5819	1.2577
No log	25.0	125	1.0805	0.2458	1.0805	1.0395
No log	26.0	130	0.9967	0.2624	0.9967	0.9984
No log	27.0	135	1.5526	0.1574	1.5526	1.2460
No log	28.0	140	0.8376	0.3228	0.8376	0.9152
No log	29.0	145	1.0133	0.2486	1.0133	1.0066
No log	30.0	150	1.0319	0.2490	1.0319	1.0158
No log	31.0	155	1.2032	0.2388	1.2032	1.0969
No log	32.0	160	1.2888	0.2406	1.2888	1.1353
No log	33.0	165	1.0319	0.2842	1.0319	1.0158
No log	34.0	170	0.9641	0.3265	0.9641	0.9819
No log	35.0	175	1.0450	0.2530	1.0450	1.0223
No log	36.0	180	1.1258	0.2622	1.1258	1.0611
No log	37.0	185	0.8438	0.3279	0.8438	0.9186
No log	38.0	190	1.1415	0.2101	1.1415	1.0684
No log	39.0	195	0.9968	0.2281	0.9968	0.9984
No log	40.0	200	0.9720	0.2457	0.9720	0.9859
No log	41.0	205	1.0927	0.2176	1.0927	1.0453
No log	42.0	210	1.2844	0.1993	1.2844	1.1333
No log	43.0	215	0.8716	0.2888	0.8716	0.9336

Framework versions

Transformers 4.47.0
Pytorch 2.5.1+cu121
Datasets 3.3.1
Tokenizers 0.21.0

genki10/BERT_V8_sp20_lw10_ex50_lo00_k7_k7_fold0

BERT_V8_sp20_lw10_ex50_lo00_k7_k7_fold0

Model description

Intended uses & limitations

Training and evaluation data

Training procedure

Training hyperparameters

Training results

Framework versions

genki10/
BERT_V8_sp20_lw10_ex50_lo00_k7_k7_fold0