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	3	8.1968	0.0	8.1968	2.8630
No log	2.0	6	6.8456	0.0	6.8456	2.6164
No log	3.0	9	5.5960	0.0112	5.5960	2.3656
No log	4.0	12	4.3297	0.0039	4.3297	2.0808
No log	5.0	15	3.1675	0.0	3.1675	1.7798
No log	6.0	18	2.1244	0.0653	2.1244	1.4575
No log	7.0	21	1.4168	0.0316	1.4168	1.1903
No log	8.0	24	1.0319	0.0106	1.0319	1.0158
No log	9.0	27	0.7922	0.3710	0.7922	0.8901
No log	10.0	30	0.6887	0.3662	0.6887	0.8299
No log	11.0	33	0.5934	0.4101	0.5934	0.7703
No log	12.0	36	0.5733	0.5120	0.5733	0.7571
No log	13.0	39	0.4892	0.4697	0.4892	0.6994
No log	14.0	42	1.3234	0.2542	1.3234	1.1504
No log	15.0	45	0.5054	0.5432	0.5054	0.7109
No log	16.0	48	0.4909	0.5190	0.4909	0.7007
No log	17.0	51	0.8626	0.3938	0.8626	0.9288
No log	18.0	54	0.5853	0.4689	0.5853	0.7651
No log	19.0	57	0.7991	0.3741	0.7991	0.8939
No log	20.0	60	0.7021	0.4261	0.7021	0.8379
No log	21.0	63	0.5950	0.4916	0.5950	0.7713
No log	22.0	66	0.5581	0.4998	0.5581	0.7471
No log	23.0	69	0.5777	0.5248	0.5777	0.7600
No log	24.0	72	0.6123	0.5112	0.6123	0.7825
No log	25.0	75	0.5795	0.5524	0.5795	0.7613
No log	26.0	78	0.7328	0.4274	0.7328	0.8561
No log	27.0	81	0.5850	0.5011	0.5850	0.7648
No log	28.0	84	0.5730	0.5393	0.5730	0.7570
No log	29.0	87	0.6309	0.5271	0.6309	0.7943
No log	30.0	90	0.5781	0.5240	0.5781	0.7603
No log	31.0	93	0.6625	0.4657	0.6625	0.8139
No log	32.0	96	0.6471	0.4694	0.6471	0.8044
No log	33.0	99	0.5733	0.5077	0.5733	0.7571
No log	34.0	102	0.5823	0.5132	0.5823	0.7631
No log	35.0	105	0.6515	0.4695	0.6515	0.8071
No log	36.0	108	0.6054	0.5034	0.6054	0.7781
No log	37.0	111	0.7043	0.4183	0.7043	0.8392
No log	38.0	114	0.5948	0.4999	0.5948	0.7713
No log	39.0	117	0.6998	0.4336	0.6998	0.8365
No log	40.0	120	0.5773	0.5052	0.5773	0.7598
No log	41.0	123	0.6829	0.4257	0.6829	0.8264
No log	42.0	126	0.5653	0.5077	0.5653	0.7519
No log	43.0	129	0.6448	0.4279	0.6448	0.8030
No log	44.0	132	0.5776	0.4840	0.5776	0.7600
No log	45.0	135	0.6081	0.4764	0.6081	0.7798
No log	46.0	138	0.5722	0.4755	0.5722	0.7565
No log	47.0	141	0.6722	0.4279	0.6722	0.8199
No log	48.0	144	0.6060	0.5014	0.6060	0.7785
No log	49.0	147	0.6895	0.4245	0.6895	0.8304
No log	50.0	150	0.6106	0.4730	0.6106	0.7814
No log	51.0	153	0.6104	0.4741	0.6104	0.7813
No log	52.0	156	0.7257	0.4168	0.7257	0.8519
No log	53.0	159	0.6166	0.4712	0.6166	0.7852
No log	54.0	162	0.8086	0.4019	0.8086	0.8992
No log	55.0	165	0.6016	0.4714	0.6016	0.7756

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_k5_k5_fold0

BERT_V8_sp10_lw40_ex100_lo50_k5_k5_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_k5_k5_fold0