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	3	9.4632	0.0	9.4608	3.0758
No log	2.0	6	8.2700	0.0	8.2676	2.8753
No log	3.0	9	6.2780	0.0	6.2757	2.5051
No log	4.0	12	4.3185	0.0079	4.3164	2.0776
No log	5.0	15	3.0800	0.0	3.0780	1.7544
No log	6.0	18	2.6166	-0.0143	2.6150	1.6171
No log	7.0	21	1.7477	0.0714	1.7459	1.3213
No log	8.0	24	1.1906	0.0	1.1892	1.0905
No log	9.0	27	0.9498	0.0408	0.9486	0.9740
No log	10.0	30	0.8857	0.0873	0.8845	0.9405
No log	11.0	33	0.9526	0.0518	0.9516	0.9755
No log	12.0	36	0.8775	0.0660	0.8764	0.9362
No log	13.0	39	0.7233	0.3570	0.7220	0.8497
No log	14.0	42	0.6229	0.3636	0.6217	0.7885
No log	15.0	45	0.5611	0.4404	0.5600	0.7483
No log	16.0	48	0.5245	0.5021	0.5234	0.7235
No log	17.0	51	0.5161	0.5301	0.5150	0.7176
No log	18.0	54	0.5475	0.5768	0.5466	0.7393
No log	19.0	57	0.7942	0.4814	0.7926	0.8903
No log	20.0	60	0.7348	0.4954	0.7333	0.8563
No log	21.0	63	0.6715	0.5494	0.6708	0.8190
No log	22.0	66	0.5812	0.5952	0.5803	0.7618
No log	23.0	69	0.5832	0.5299	0.5819	0.7628
No log	24.0	72	0.4788	0.6419	0.4778	0.6912
No log	25.0	75	0.4698	0.6509	0.4686	0.6846
No log	26.0	78	0.5189	0.5675	0.5177	0.7195
No log	27.0	81	1.0752	0.4576	1.0747	1.0367
No log	28.0	84	0.9814	0.4810	0.9809	0.9904
No log	29.0	87	0.6610	0.5205	0.6597	0.8122
No log	30.0	90	0.5691	0.5586	0.5678	0.7535
No log	31.0	93	0.8184	0.5261	0.8178	0.9043
No log	32.0	96	0.6114	0.5778	0.6106	0.7814
No log	33.0	99	0.6974	0.5098	0.6958	0.8342
No log	34.0	102	0.5689	0.5798	0.5675	0.7533
No log	35.0	105	0.7121	0.5679	0.7115	0.8435
No log	36.0	108	0.5104	0.6506	0.5096	0.7138
No log	37.0	111	0.6620	0.5335	0.6604	0.8126
No log	38.0	114	0.5797	0.5968	0.5783	0.7604
No log	39.0	117	0.8248	0.5488	0.8241	0.9078
No log	40.0	120	0.7058	0.5467	0.7050	0.8396
No log	41.0	123	0.5366	0.5750	0.5355	0.7318
No log	42.0	126	0.6123	0.5760	0.6114	0.7819
No log	43.0	129	0.6154	0.5774	0.6146	0.7839
No log	44.0	132	0.4990	0.6101	0.4979	0.7056
No log	45.0	135	0.5158	0.5659	0.5147	0.7174
No log	46.0	138	0.7640	0.5368	0.7633	0.8737
No log	47.0	141	0.6649	0.5417	0.6642	0.8150
No log	48.0	144	0.5512	0.5602	0.5499	0.7416
No log	49.0	147	0.5279	0.5542	0.5267	0.7257
No log	50.0	150	0.5712	0.5709	0.5703	0.7552
No log	51.0	153	0.5571	0.5766	0.5563	0.7458
No log	52.0	156	0.5078	0.6376	0.5068	0.7119
No log	53.0	159	0.5511	0.6019	0.5499	0.7416
No log	54.0	162	0.5752	0.5903	0.5741	0.7577
No log	55.0	165	0.5445	0.5728	0.5434	0.7372

Framework versions

Transformers 4.47.0
Pytorch 2.5.1+cu121
Datasets 3.3.1
Tokenizers 0.21.0

genki10/BERT_V8_sp10_lw20_ex100_lo50_k5_k5_fold1

BERT_V8_sp10_lw20_ex100_lo50_k5_k5_fold1

Model description

Intended uses & limitations

Training and evaluation data

Training procedure

Training hyperparameters

Training results

Framework versions

genki10/
BERT_V8_sp10_lw20_ex100_lo50_k5_k5_fold1