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	1	15.3334	0.0	15.3334	3.9158
No log	2.0	2	13.3436	0.0	13.3436	3.6529
No log	3.0	3	11.7006	-0.0010	11.7006	3.4206
No log	4.0	4	10.3079	0.0060	10.3079	3.2106
No log	5.0	5	9.6728	0.0018	9.6728	3.1101
No log	6.0	6	9.2583	0.0018	9.2583	3.0427
No log	7.0	7	7.5621	0.0004	7.5621	2.7499
No log	8.0	8	7.6403	-0.0031	7.6403	2.7641
No log	9.0	9	7.1216	-0.0103	7.1216	2.6686
No log	10.0	10	5.7782	0.0057	5.7782	2.4038
No log	11.0	11	4.7685	0.0256	4.7685	2.1837
No log	12.0	12	4.2967	0.0089	4.2967	2.0728
No log	13.0	13	3.7420	0.0128	3.7420	1.9344
No log	14.0	14	3.5629	0.0079	3.5629	1.8876
No log	15.0	15	3.0153	0.0040	3.0153	1.7365
No log	16.0	16	2.4851	0.0519	2.4851	1.5764
No log	17.0	17	2.2380	0.1176	2.2380	1.4960
No log	18.0	18	1.8619	0.0755	1.8619	1.3645
No log	19.0	19	1.6730	0.0672	1.6730	1.2934
No log	20.0	20	1.4176	0.0445	1.4176	1.1906
No log	21.0	21	1.3511	0.0420	1.3511	1.1624
No log	22.0	22	1.2233	0.0420	1.2233	1.1060
No log	23.0	23	1.0072	0.0445	1.0072	1.0036
No log	24.0	24	0.9822	0.0445	0.9822	0.9911
No log	25.0	25	0.8871	0.1475	0.8871	0.9419
No log	26.0	26	0.8175	0.3696	0.8175	0.9042
No log	27.0	27	0.8026	0.3586	0.8026	0.8959
No log	28.0	28	0.7500	0.4113	0.7500	0.8660
No log	29.0	29	0.7285	0.3745	0.7285	0.8535
No log	30.0	30	0.7081	0.3940	0.7081	0.8415
No log	31.0	31	0.6589	0.4237	0.6589	0.8117
No log	32.0	32	0.6443	0.3854	0.6443	0.8027
No log	33.0	33	0.6401	0.4211	0.6401	0.8000
No log	34.0	34	0.6084	0.4392	0.6084	0.7800
No log	35.0	35	0.6073	0.4993	0.6073	0.7793
No log	36.0	36	0.6723	0.5149	0.6723	0.8199
No log	37.0	37	0.6735	0.5167	0.6735	0.8207
No log	38.0	38	0.6072	0.5302	0.6072	0.7793
No log	39.0	39	0.6109	0.5280	0.6109	0.7816
No log	40.0	40	0.6567	0.5303	0.6567	0.8104
No log	41.0	41	0.6570	0.5399	0.6570	0.8105
No log	42.0	42	0.6423	0.5481	0.6423	0.8015
No log	43.0	43	0.6935	0.5404	0.6935	0.8328
No log	44.0	44	0.6596	0.5502	0.6596	0.8122
No log	45.0	45	0.5957	0.5585	0.5957	0.7718
No log	46.0	46	0.6011	0.5504	0.6011	0.7753
No log	47.0	47	0.6560	0.5388	0.6560	0.8100
No log	48.0	48	0.7916	0.4913	0.7916	0.8897
No log	49.0	49	0.8501	0.4753	0.8501	0.9220
No log	50.0	50	0.7381	0.5110	0.7381	0.8591
No log	51.0	51	0.5978	0.5819	0.5978	0.7732
No log	52.0	52	0.5858	0.5852	0.5858	0.7654
No log	53.0	53	0.6435	0.5278	0.6435	0.8022
No log	54.0	54	0.7003	0.5078	0.7003	0.8369
No log	55.0	55	0.6821	0.5158	0.6821	0.8259
No log	56.0	56	0.6279	0.5779	0.6279	0.7924
No log	57.0	57	0.6377	0.5443	0.6377	0.7986
No log	58.0	58	0.7133	0.5061	0.7133	0.8446
No log	59.0	59	0.7697	0.5024	0.7697	0.8773
No log	60.0	60	0.7623	0.5073	0.7623	0.8731
No log	61.0	61	0.6878	0.5355	0.6878	0.8293
No log	62.0	62	0.7114	0.5314	0.7114	0.8435
No log	63.0	63	0.7467	0.5049	0.7467	0.8641
No log	64.0	64	0.7558	0.5034	0.7558	0.8694
No log	65.0	65	0.8306	0.4935	0.8306	0.9114
No log	66.0	66	0.8004	0.4999	0.8004	0.8947
No log	67.0	67	0.7047	0.5394	0.7047	0.8394
No log	68.0	68	0.6810	0.5585	0.6810	0.8252
No log	69.0	69	0.6981	0.5582	0.6981	0.8355
No log	70.0	70	0.7800	0.5124	0.7800	0.8832
No log	71.0	71	0.7972	0.4960	0.7972	0.8929
No log	72.0	72	0.7380	0.5278	0.7380	0.8591
No log	73.0	73	0.6697	0.5575	0.6697	0.8184
No log	74.0	74	0.6613	0.5596	0.6613	0.8132
No log	75.0	75	0.6781	0.5493	0.6781	0.8235
No log	76.0	76	0.7556	0.5229	0.7556	0.8692
No log	77.0	77	0.7996	0.4881	0.7996	0.8942
No log	78.0	78	0.7726	0.5054	0.7726	0.8790
No log	79.0	79	0.7044	0.5439	0.7044	0.8393
No log	80.0	80	0.6953	0.5559	0.6953	0.8339
No log	81.0	81	0.6911	0.5583	0.6911	0.8313
No log	82.0	82	0.7093	0.5542	0.7093	0.8422

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_k1_k1_fold4

BERT_V8_sp10_lw40_ex50_lo100_k1_k1_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_k1_k1_fold4