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	7.7224	0.0	7.7224	2.7789
No log	2.0	8	5.8390	0.0169	5.8390	2.4164
No log	3.0	12	4.1591	0.0039	4.1591	2.0394
No log	4.0	16	2.5954	0.0031	2.5954	1.6110
No log	5.0	20	1.5304	0.0316	1.5304	1.2371
No log	6.0	24	0.9744	0.0212	0.9744	0.9871
No log	7.0	28	0.7789	0.1419	0.7789	0.8826
No log	8.0	32	0.8594	0.2102	0.8594	0.9270
No log	9.0	36	0.6236	0.2486	0.6236	0.7897
No log	10.0	40	0.7706	0.3606	0.7706	0.8778
No log	11.0	44	0.8019	0.3721	0.8019	0.8955
No log	12.0	48	0.4937	0.4550	0.4937	0.7027
No log	13.0	52	0.7788	0.4196	0.7788	0.8825
No log	14.0	56	0.5919	0.4712	0.5919	0.7693
No log	15.0	60	0.9369	0.3560	0.9369	0.9679
No log	16.0	64	0.5398	0.5132	0.5398	0.7347
No log	17.0	68	0.6136	0.4818	0.6136	0.7833
No log	18.0	72	0.6610	0.4851	0.6610	0.8130
No log	19.0	76	0.6074	0.4882	0.6074	0.7794
No log	20.0	80	0.6087	0.4838	0.6087	0.7802
No log	21.0	84	0.7854	0.4212	0.7854	0.8862
No log	22.0	88	0.7279	0.4319	0.7279	0.8532
No log	23.0	92	0.5768	0.5088	0.5768	0.7595
No log	24.0	96	0.6853	0.4523	0.6853	0.8278
No log	25.0	100	0.8054	0.4000	0.8054	0.8975
No log	26.0	104	0.6023	0.4891	0.6023	0.7761
No log	27.0	108	0.6581	0.4447	0.6581	0.8113
No log	28.0	112	1.0155	0.2684	1.0155	1.0077
No log	29.0	116	0.5848	0.4722	0.5848	0.7647
No log	30.0	120	0.8299	0.3269	0.8299	0.9110
No log	31.0	124	0.5761	0.4958	0.5761	0.7590
No log	32.0	128	0.7968	0.4025	0.7968	0.8926
No log	33.0	132	0.5739	0.4972	0.5739	0.7576
No log	34.0	136	0.7894	0.3795	0.7894	0.8885
No log	35.0	140	0.5880	0.4929	0.5880	0.7668
No log	36.0	144	0.7464	0.4168	0.7464	0.8639
No log	37.0	148	0.5885	0.4875	0.5885	0.7671
No log	38.0	152	0.8569	0.3533	0.8569	0.9257
No log	39.0	156	0.5818	0.4765	0.5818	0.7627
No log	40.0	160	0.6122	0.4900	0.6122	0.7824
No log	41.0	164	0.7609	0.4181	0.7609	0.8723
No log	42.0	168	0.5970	0.4378	0.5970	0.7727
No log	43.0	172	0.7236	0.3986	0.7236	0.8506
No log	44.0	176	0.6166	0.4646	0.6166	0.7852
No log	45.0	180	0.6883	0.4408	0.6883	0.8297
No log	46.0	184	0.6462	0.4639	0.6462	0.8039

Framework versions

Transformers 4.51.1
Pytorch 2.5.1+cu124
Datasets 3.5.0
Tokenizers 0.21.0

genki10/BERT_V8_sp10_lw40_ex100_lo50_k7_k7_fold0

BERT_V8_sp10_lw40_ex100_lo50_k7_k7_fold0

Model description

Intended uses & limitations

Training and evaluation data

Training procedure

Training hyperparameters

Training results

Framework versions

genki10/
BERT_V8_sp10_lw40_ex100_lo50_k7_k7_fold0