learning_rate: 2e-05
train_batch_size: 64
eval_batch_size: 64
seed: 42
optimizer: Use 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	2	10.0686	0.0	10.0688	3.1731
No log	2.0	4	9.5330	0.0	9.5331	3.0876
No log	3.0	6	8.5694	0.0	8.5696	2.9274
No log	4.0	8	6.9213	0.0	6.9217	2.6309
No log	5.0	10	5.4432	0.0183	5.4435	2.3331
No log	6.0	12	4.3323	0.0046	4.3326	2.0815
No log	7.0	14	3.2911	0.0	3.2915	1.8143
No log	8.0	16	2.6201	0.0128	2.6205	1.6188
No log	9.0	18	2.0151	0.0880	2.0155	1.4197
No log	10.0	20	1.4450	0.0551	1.4454	1.2023
No log	11.0	22	1.2025	0.0449	1.2028	1.0967
No log	12.0	24	1.0779	0.0449	1.0783	1.0384
No log	13.0	26	1.2183	0.0449	1.2188	1.1040
No log	14.0	28	1.1817	0.0577	1.1821	1.0872
No log	15.0	30	1.0755	0.1164	1.0758	1.0372
No log	16.0	32	0.9684	0.2690	0.9686	0.9842
No log	17.0	34	0.7673	0.3453	0.7675	0.8761
No log	18.0	36	0.7440	0.3300	0.7442	0.8627
No log	19.0	38	0.6650	0.4312	0.6652	0.8156
No log	20.0	40	0.6449	0.4399	0.6451	0.8032
No log	21.0	42	0.5177	0.4907	0.5177	0.7195
No log	22.0	44	0.5211	0.5258	0.5210	0.7218
No log	23.0	46	0.5028	0.5030	0.5028	0.7091
No log	24.0	48	0.6161	0.4219	0.6162	0.7850
No log	25.0	50	0.7312	0.3724	0.7313	0.8552
No log	26.0	52	0.6451	0.4106	0.6450	0.8031
No log	27.0	54	0.4956	0.5577	0.4955	0.7039
No log	28.0	56	0.5380	0.5236	0.5379	0.7334
No log	29.0	58	0.4906	0.5370	0.4905	0.7004
No log	30.0	60	0.5595	0.5766	0.5593	0.7479
No log	31.0	62	0.7265	0.4306	0.7264	0.8523
No log	32.0	64	0.6387	0.4894	0.6388	0.7992
No log	33.0	66	0.5437	0.5622	0.5437	0.7374
No log	34.0	68	0.5108	0.6032	0.5106	0.7145
No log	35.0	70	0.5060	0.6118	0.5058	0.7112
No log	36.0	72	0.5345	0.5375	0.5346	0.7311
No log	37.0	74	0.5172	0.5452	0.5173	0.7192
No log	38.0	76	0.5116	0.5568	0.5116	0.7152
No log	39.0	78	0.5405	0.5708	0.5405	0.7352
No log	40.0	80	0.5307	0.5686	0.5307	0.7285
No log	41.0	82	0.5119	0.6043	0.5118	0.7154
No log	42.0	84	0.5365	0.5942	0.5364	0.7324
No log	43.0	86	0.5211	0.6021	0.5210	0.7218
No log	44.0	88	0.5251	0.5687	0.5251	0.7246
No log	45.0	90	0.5366	0.5691	0.5366	0.7325
No log	46.0	92	0.5639	0.5544	0.5639	0.7510
No log	47.0	94	0.5555	0.5211	0.5556	0.7454
No log	48.0	96	0.5447	0.5466	0.5447	0.7381
No log	49.0	98	0.5457	0.5597	0.5457	0.7387
No log	50.0	100	0.5543	0.5773	0.5542	0.7444
No log	51.0	102	0.5916	0.5409	0.5916	0.7692
No log	52.0	104	0.6133	0.5111	0.6133	0.7831
No log	53.0	106	0.5690	0.5641	0.5689	0.7543
No log	54.0	108	0.5823	0.5449	0.5824	0.7631
No log	55.0	110	0.6097	0.4938	0.6098	0.7809
No log	56.0	112	0.5973	0.5003	0.5974	0.7729
No log	57.0	114	0.5886	0.5411	0.5887	0.7672
No log	58.0	116	0.5872	0.5173	0.5873	0.7663
No log	59.0	118	0.6621	0.4949	0.6622	0.8137
No log	60.0	120	0.6168	0.5258	0.6169	0.7854
No log	61.0	122	0.5637	0.5745	0.5637	0.7508
No log	62.0	124	0.5711	0.5597	0.5711	0.7557
No log	63.0	126	0.5875	0.5116	0.5876	0.7665
No log	64.0	128	0.5839	0.5097	0.5840	0.7642
No log	65.0	130	0.5819	0.5583	0.5820	0.7629

Framework versions

Transformers 4.47.0
Pytorch 2.5.1+cu121
Datasets 3.3.1
Tokenizers 0.21.0

genki10/BERT_V8_sp20_lw10_ex100_lo00_k1_k1_fold2

BERT_V8_sp20_lw10_ex100_lo00_k1_k1_fold2

Model description

Intended uses & limitations

Training and evaluation data

Training procedure

Training hyperparameters

Training results

Framework versions

genki10/
BERT_V8_sp20_lw10_ex100_lo00_k1_k1_fold2