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	8.2004	0.0	8.2004	2.8636
No log	2.0	8	5.6015	0.0177	5.6015	2.3667
No log	3.0	12	3.5900	0.0115	3.5900	1.8947
No log	4.0	16	2.1505	0.0798	2.1505	1.4665
No log	5.0	20	1.2956	0.0316	1.2956	1.1382
No log	6.0	24	0.8233	0.3833	0.8233	0.9074
No log	7.0	28	0.7144	0.1696	0.7144	0.8452
No log	8.0	32	0.6135	0.4740	0.6135	0.7832
No log	9.0	36	0.4696	0.4758	0.4696	0.6853
No log	10.0	40	0.5206	0.3962	0.5206	0.7215
No log	11.0	44	0.5220	0.5003	0.5220	0.7225
No log	12.0	48	0.5628	0.5248	0.5628	0.7502
No log	13.0	52	0.4904	0.5767	0.4904	0.7003
No log	14.0	56	0.5029	0.5883	0.5029	0.7092
No log	15.0	60	0.4519	0.6139	0.4519	0.6722
No log	16.0	64	0.4677	0.6541	0.4677	0.6839
No log	17.0	68	0.4845	0.6119	0.4845	0.6961
No log	18.0	72	0.5204	0.5714	0.5204	0.7214
No log	19.0	76	0.4752	0.5466	0.4752	0.6893
No log	20.0	80	0.4689	0.5884	0.4689	0.6848
No log	21.0	84	0.4810	0.5798	0.4810	0.6935
No log	22.0	88	0.5089	0.5644	0.5089	0.7134
No log	23.0	92	0.4829	0.5345	0.4829	0.6949
No log	24.0	96	0.4880	0.5151	0.4880	0.6985
No log	25.0	100	0.4882	0.5734	0.4882	0.6987
No log	26.0	104	0.5030	0.5372	0.5030	0.7092
No log	27.0	108	0.4951	0.5369	0.4951	0.7036
No log	28.0	112	0.4945	0.5561	0.4945	0.7032
No log	29.0	116	0.4862	0.5433	0.4862	0.6973
No log	30.0	120	0.4891	0.5386	0.4891	0.6994
No log	31.0	124	0.5631	0.5404	0.5631	0.7504
No log	32.0	128	0.5209	0.5318	0.5209	0.7218
No log	33.0	132	0.5680	0.5248	0.5680	0.7536
No log	34.0	136	0.6196	0.5295	0.6196	0.7871
No log	35.0	140	0.4902	0.5406	0.4902	0.7001
No log	36.0	144	0.4847	0.5243	0.4847	0.6962
No log	37.0	148	0.4929	0.5677	0.4929	0.7021
No log	38.0	152	0.4799	0.5559	0.4799	0.6927
No log	39.0	156	0.4735	0.5293	0.4735	0.6881
No log	40.0	160	0.4715	0.5617	0.4715	0.6866
No log	41.0	164	0.4951	0.5485	0.4951	0.7036
No log	42.0	168	0.4790	0.5561	0.4790	0.6921
No log	43.0	172	0.4968	0.4875	0.4968	0.7049
No log	44.0	176	0.5108	0.4892	0.5108	0.7147
No log	45.0	180	0.4963	0.5535	0.4963	0.7045
No log	46.0	184	0.4912	0.5551	0.4912	0.7009

Framework versions

Transformers 4.51.1
Pytorch 2.5.1+cu124
Datasets 3.5.0
Tokenizers 0.21.0

genki10/BERT_V8_sp10_lw20_ex200_lo50_k10_k10_fold0

BERT_V8_sp10_lw20_ex200_lo50_k10_k10_fold0

Model description

Intended uses & limitations

Training and evaluation data

Training procedure

Training hyperparameters

Training results

Framework versions

genki10/
BERT_V8_sp10_lw20_ex200_lo50_k10_k10_fold0