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	9.6497	0.0018	9.6497	3.1064
No log	2.0	8	6.5310	0.0	6.5310	2.5556
No log	3.0	12	3.3448	0.0079	3.3448	1.8289
No log	4.0	16	1.7432	0.0729	1.7432	1.3203
No log	5.0	20	0.9943	0.0213	0.9943	0.9972
No log	6.0	24	0.8680	0.2238	0.8680	0.9317
No log	7.0	28	0.7165	0.3950	0.7165	0.8465
No log	8.0	32	0.9595	0.2623	0.9595	0.9795
No log	9.0	36	0.6949	0.4178	0.6949	0.8336
No log	10.0	40	1.5503	0.2300	1.5503	1.2451
No log	11.0	44	0.9092	0.3379	0.9092	0.9535
No log	12.0	48	0.5729	0.4865	0.5729	0.7569
No log	13.0	52	0.6861	0.4517	0.6861	0.8283
No log	14.0	56	0.7237	0.4184	0.7237	0.8507
No log	15.0	60	0.6640	0.5037	0.6640	0.8149
No log	16.0	64	0.6260	0.5199	0.6260	0.7912
No log	17.0	68	0.5901	0.5744	0.5901	0.7682
No log	18.0	72	0.6705	0.5022	0.6705	0.8188
No log	19.0	76	0.6931	0.5080	0.6931	0.8325
No log	20.0	80	0.6239	0.5440	0.6239	0.7899
No log	21.0	84	0.8304	0.4529	0.8304	0.9113
No log	22.0	88	0.9434	0.4117	0.9434	0.9713
No log	23.0	92	0.7044	0.5191	0.7044	0.8393
No log	24.0	96	0.9287	0.4259	0.9287	0.9637
No log	25.0	100	0.6406	0.5335	0.6406	0.8003
No log	26.0	104	0.6508	0.4803	0.6508	0.8067
No log	27.0	108	0.7373	0.4272	0.7373	0.8587
No log	28.0	112	0.6163	0.5517	0.6163	0.7850
No log	29.0	116	0.7404	0.4883	0.7404	0.8604
No log	30.0	120	0.7484	0.4826	0.7484	0.8651
No log	31.0	124	0.6918	0.4917	0.6918	0.8317
No log	32.0	128	0.6964	0.5269	0.6964	0.8345
No log	33.0	132	0.6687	0.5247	0.6687	0.8177
No log	34.0	136	0.6518	0.5119	0.6518	0.8074
No log	35.0	140	0.8226	0.4357	0.8226	0.9070
No log	36.0	144	0.7368	0.4729	0.7368	0.8584
No log	37.0	148	0.6509	0.5132	0.6509	0.8068
No log	38.0	152	0.7775	0.4593	0.7775	0.8818
No log	39.0	156	0.7465	0.4879	0.7465	0.8640
No log	40.0	160	0.6496	0.5267	0.6496	0.8060
No log	41.0	164	0.8432	0.4620	0.8432	0.9183
No log	42.0	168	0.7058	0.4970	0.7058	0.8401
No log	43.0	172	0.7015	0.4983	0.7015	0.8376
No log	44.0	176	0.7042	0.4959	0.7042	0.8392
No log	45.0	180	0.7351	0.4612	0.7351	0.8574
No log	46.0	184	0.6532	0.4837	0.6532	0.8082
No log	47.0	188	0.6484	0.4946	0.6484	0.8052

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_lo100_k7_k7_fold4

BERT_V8_sp10_lw40_ex50_lo100_k7_k7_fold4

Model description

Intended uses & limitations

Training and evaluation data

Training procedure

Training hyperparameters

Training results

Framework versions

genki10/
BERT_V8_sp10_lw40_ex50_lo100_k7_k7_fold4