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	11.7691	0.0082	11.7691	3.4306
No log	2.0	6	8.7214	0.0054	8.7214	2.9532
No log	3.0	9	5.3696	0.0531	5.3696	2.3172
No log	4.0	12	3.3914	0.0115	3.3914	1.8416
No log	5.0	15	2.1522	0.1464	2.1522	1.4670
No log	6.0	18	1.3972	0.0681	1.3972	1.1820
No log	7.0	21	1.0094	0.0418	1.0094	1.0047
No log	8.0	24	0.7633	0.2539	0.7633	0.8737
No log	9.0	27	0.6979	0.2148	0.6979	0.8354
No log	10.0	30	0.6121	0.2868	0.6121	0.7824
No log	11.0	33	0.5016	0.4346	0.5016	0.7082
No log	12.0	36	0.6839	0.5492	0.6839	0.8270
No log	13.0	39	0.6506	0.5561	0.6506	0.8066
No log	14.0	42	0.5037	0.5621	0.5037	0.7097
No log	15.0	45	0.6506	0.5141	0.6506	0.8066
No log	16.0	48	0.4978	0.5733	0.4978	0.7055
No log	17.0	51	0.8404	0.4314	0.8404	0.9168
No log	18.0	54	0.5173	0.5586	0.5173	0.7193
No log	19.0	57	0.5591	0.5133	0.5591	0.7477
No log	20.0	60	0.5620	0.5269	0.5620	0.7497
No log	21.0	63	0.8176	0.4430	0.8176	0.9042
No log	22.0	66	0.5708	0.4803	0.5708	0.7555
No log	23.0	69	0.8710	0.4534	0.8710	0.9333
No log	24.0	72	0.6139	0.5274	0.6139	0.7835
No log	25.0	75	0.6928	0.4926	0.6928	0.8323
No log	26.0	78	0.6443	0.4638	0.6443	0.8027
No log	27.0	81	0.5568	0.4541	0.5568	0.7462
No log	28.0	84	0.7113	0.4461	0.7113	0.8434
No log	29.0	87	0.5712	0.5379	0.5712	0.7558
No log	30.0	90	0.8205	0.4282	0.8205	0.9058
No log	31.0	93	0.5498	0.5744	0.5498	0.7415
No log	32.0	96	0.6798	0.4508	0.6798	0.8245
No log	33.0	99	0.6315	0.4507	0.6315	0.7947
No log	34.0	102	0.5495	0.5130	0.5495	0.7413
No log	35.0	105	0.7596	0.4294	0.7596	0.8715
No log	36.0	108	0.6019	0.4915	0.6019	0.7758
No log	37.0	111	0.6827	0.4620	0.6827	0.8263
No log	38.0	114	0.6307	0.4919	0.6307	0.7942
No log	39.0	117	0.6345	0.4797	0.6345	0.7965
No log	40.0	120	0.5949	0.4878	0.5949	0.7713
No log	41.0	123	0.6277	0.4672	0.6277	0.7922
No log	42.0	126	0.6399	0.4765	0.6399	0.7999
No log	43.0	129	0.6409	0.4543	0.6409	0.8006
No log	44.0	132	0.6536	0.4587	0.6536	0.8084
No log	45.0	135	0.7592	0.4398	0.7592	0.8713
No log	46.0	138	0.6387	0.4818	0.6387	0.7992
No log	47.0	141	0.7350	0.4533	0.7350	0.8573
No log	48.0	144	0.6678	0.4703	0.6678	0.8172
No log	49.0	147	0.6942	0.4664	0.6942	0.8332
No log	50.0	150	0.7172	0.4590	0.7172	0.8469
No log	51.0	153	0.6971	0.4462	0.6971	0.8349
No log	52.0	156	0.6255	0.4641	0.6255	0.7909
No log	53.0	159	0.6182	0.4661	0.6182	0.7863
No log	54.0	162	0.6133	0.4750	0.6133	0.7831
No log	55.0	165	0.7188	0.4599	0.7188	0.8478
No log	56.0	168	0.6425	0.4762	0.6425	0.8016
No log	57.0	171	0.6565	0.4596	0.6565	0.8103
No log	58.0	174	0.6131	0.4652	0.6131	0.7830
No log	59.0	177	0.6653	0.4426	0.6653	0.8157
No log	60.0	180	0.6355	0.4581	0.6355	0.7972
No log	61.0	183	0.6895	0.4428	0.6895	0.8303

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_k7_k7_fold0

BERT_V8_sp10_lw20_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_lw20_ex100_lo50_k7_k7_fold0