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	8.5839	0.0	8.5821	2.9295
No log	2.0	8	6.0300	0.0709	6.0286	2.4553
No log	3.0	12	4.1343	0.0	4.1332	2.0330
No log	4.0	16	2.6715	0.0006	2.6706	1.6342
No log	5.0	20	1.7381	0.0102	1.7374	1.3181
No log	6.0	24	1.1785	0.0102	1.1778	1.0853
No log	7.0	28	1.5379	0.0365	1.5371	1.2398
No log	8.0	32	0.9220	0.2034	0.9215	0.9599
No log	9.0	36	1.0687	0.0938	1.0682	1.0335
No log	10.0	40	1.0157	0.0681	1.0152	1.0076
No log	11.0	44	0.7578	0.4748	0.7575	0.8703
No log	12.0	48	1.6371	0.2476	1.6370	1.2795
No log	13.0	52	0.7247	0.4725	0.7246	0.8512
No log	14.0	56	0.9827	0.2950	0.9827	0.9913
No log	15.0	60	0.6083	0.5104	0.6084	0.7800
No log	16.0	64	0.6316	0.4670	0.6320	0.7950
No log	17.0	68	0.5476	0.5240	0.5480	0.7403
No log	18.0	72	0.6088	0.4768	0.6093	0.7806
No log	19.0	76	0.5844	0.5288	0.5850	0.7648
No log	20.0	80	0.5985	0.5451	0.5992	0.7741
No log	21.0	84	0.9992	0.4034	0.9999	0.9999
No log	22.0	88	0.6089	0.5705	0.6097	0.7809
No log	23.0	92	1.5037	0.2589	1.5044	1.2265
No log	24.0	96	0.6304	0.5235	0.6313	0.7945
No log	25.0	100	0.8912	0.4388	0.8920	0.9444
No log	26.0	104	0.8180	0.4576	0.8186	0.9047
No log	27.0	108	0.7510	0.4732	0.7517	0.8670
No log	28.0	112	0.7625	0.4948	0.7630	0.8735
No log	29.0	116	0.6350	0.5525	0.6357	0.7973
No log	30.0	120	1.0179	0.3785	1.0187	1.0093
No log	31.0	124	0.7272	0.5222	0.7276	0.8530
No log	32.0	128	0.6626	0.5545	0.6632	0.8144
No log	33.0	132	1.1789	0.3705	1.1798	1.0862
No log	34.0	136	0.6355	0.5801	0.6362	0.7976
No log	35.0	140	0.9449	0.3946	0.9457	0.9724
No log	36.0	144	0.5958	0.5485	0.5963	0.7722
No log	37.0	148	0.8701	0.4224	0.8707	0.9331
No log	38.0	152	0.6994	0.5074	0.7001	0.8367
No log	39.0	156	0.8477	0.4468	0.8483	0.9211
No log	40.0	160	0.7240	0.5023	0.7246	0.8512
No log	41.0	164	0.7901	0.4773	0.7908	0.8892
No log	42.0	168	0.6615	0.5208	0.6622	0.8137
No log	43.0	172	0.7933	0.4805	0.7941	0.8911
No log	44.0	176	0.6734	0.5119	0.6740	0.8210
No log	45.0	180	0.7074	0.5018	0.7079	0.8414
No log	46.0	184	0.7233	0.4913	0.7240	0.8509
No log	47.0	188	0.7581	0.4888	0.7588	0.8711
No log	48.0	192	0.7903	0.4890	0.7910	0.8894
No log	49.0	196	0.6472	0.5459	0.6477	0.8048
No log	50.0	200	0.8541	0.4851	0.8546	0.9245
No log	51.0	204	0.6814	0.5246	0.6820	0.8258
No log	52.0	208	0.9209	0.4201	0.9216	0.9600
No log	53.0	212	0.6695	0.5344	0.6702	0.8186
No log	54.0	216	0.7256	0.5243	0.7263	0.8522
No log	55.0	220	0.8832	0.4803	0.8840	0.9402
No log	56.0	224	0.6644	0.5242	0.6650	0.8155
No log	57.0	228	0.8026	0.4920	0.8032	0.8962
No log	58.0	232	0.7763	0.4850	0.7769	0.8814
No log	59.0	236	0.6931	0.4931	0.6937	0.8329
No log	60.0	240	0.8081	0.4678	0.8087	0.8993
No log	61.0	244	0.6928	0.5230	0.6934	0.8327
No log	62.0	248	0.7288	0.5220	0.7294	0.8540
No log	63.0	252	0.7885	0.4883	0.7891	0.8883
No log	64.0	256	0.7578	0.5060	0.7584	0.8709

Framework versions

Transformers 4.51.1
Pytorch 2.5.1+cu124
Datasets 3.5.0
Tokenizers 0.21.0

genki10/BERT_V8_sp10_lw40_ex10_lo00_k5_k5_fold3

BERT_V8_sp10_lw40_ex10_lo00_k5_k5_fold3

Model description

Intended uses & limitations

Training and evaluation data

Training procedure

Training hyperparameters

Training results

Framework versions

genki10/
BERT_V8_sp10_lw40_ex10_lo00_k5_k5_fold3