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	4	10.4099	0.0018	10.4099	3.2264
No log	2.0	8	8.1368	0.0	8.1368	2.8525
No log	3.0	12	7.2929	0.0	7.2929	2.7005
No log	4.0	16	5.2939	0.0165	5.2939	2.3009
No log	5.0	20	3.8533	0.0040	3.8533	1.9630
No log	6.0	24	2.0041	0.0887	2.0041	1.4157
No log	7.0	28	1.2662	0.0107	1.2662	1.1252
No log	8.0	32	0.8879	0.2156	0.8879	0.9423
No log	9.0	36	0.8351	0.1960	0.8351	0.9138
No log	10.0	40	0.7052	0.2719	0.7052	0.8397
No log	11.0	44	0.6649	0.3242	0.6649	0.8154
No log	12.0	48	0.6726	0.4118	0.6726	0.8201
No log	13.0	52	0.7341	0.4296	0.7341	0.8568
No log	14.0	56	0.6217	0.5878	0.6217	0.7884
No log	15.0	60	0.9341	0.4726	0.9341	0.9665
No log	16.0	64	0.7299	0.5648	0.7299	0.8543
No log	17.0	68	1.1325	0.4157	1.1325	1.0642
No log	18.0	72	0.6914	0.5850	0.6914	0.8315
No log	19.0	76	1.1392	0.4199	1.1392	1.0673
No log	20.0	80	0.7052	0.5732	0.7052	0.8398
No log	21.0	84	0.6966	0.5727	0.6966	0.8346
No log	22.0	88	0.6837	0.5381	0.6837	0.8269
No log	23.0	92	0.5818	0.5676	0.5818	0.7628
No log	24.0	96	0.7316	0.5560	0.7316	0.8553
No log	25.0	100	0.6526	0.5887	0.6526	0.8078
No log	26.0	104	0.6431	0.5472	0.6431	0.8019
No log	27.0	108	0.6110	0.5399	0.6110	0.7817
No log	28.0	112	0.5709	0.5751	0.5709	0.7556
No log	29.0	116	0.6790	0.5022	0.6790	0.8240
No log	30.0	120	0.5531	0.5934	0.5531	0.7437
No log	31.0	124	0.8148	0.4963	0.8148	0.9027
No log	32.0	128	0.5466	0.5435	0.5466	0.7393
No log	33.0	132	0.6914	0.4975	0.6914	0.8315
No log	34.0	136	0.5494	0.5806	0.5494	0.7412
No log	35.0	140	0.7592	0.5099	0.7592	0.8713
No log	36.0	144	0.5703	0.5428	0.5703	0.7552
No log	37.0	148	0.6912	0.5279	0.6912	0.8314
No log	38.0	152	0.5897	0.5314	0.5897	0.7679
No log	39.0	156	0.6947	0.4817	0.6947	0.8335
No log	40.0	160	0.6515	0.5221	0.6515	0.8072
No log	41.0	164	0.6854	0.5217	0.6854	0.8279
No log	42.0	168	0.7254	0.4951	0.7254	0.8517
No log	43.0	172	0.5640	0.5591	0.5640	0.7510
No log	44.0	176	0.7006	0.4882	0.7006	0.8370
No log	45.0	180	0.5444	0.5638	0.5444	0.7378
No log	46.0	184	0.6956	0.5122	0.6956	0.8340
No log	47.0	188	0.6158	0.5218	0.6158	0.7847
No log	48.0	192	0.5970	0.5346	0.5970	0.7726
No log	49.0	196	0.7237	0.4953	0.7237	0.8507
No log	50.0	200	0.5770	0.5387	0.5770	0.7596
No log	51.0	204	0.7132	0.5138	0.7132	0.8445
No log	52.0	208	0.5825	0.5350	0.5825	0.7632
No log	53.0	212	0.6398	0.5277	0.6398	0.7999
No log	54.0	216	0.5623	0.5278	0.5623	0.7498
No log	55.0	220	0.6726	0.4979	0.6726	0.8201
No log	56.0	224	0.5862	0.5532	0.5862	0.7656
No log	57.0	228	0.6466	0.5139	0.6466	0.8041
No log	58.0	232	0.6041	0.5087	0.6041	0.7773
No log	59.0	236	0.6360	0.5022	0.6360	0.7975
No log	60.0	240	0.6252	0.5331	0.6252	0.7907

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_lo100_k7_k7_fold4

BERT_V8_sp10_lw20_ex100_lo100_k7_k7_fold4

Model description

Intended uses & limitations

Training and evaluation data

Training procedure

Training hyperparameters

Training results

Framework versions

genki10/
BERT_V8_sp10_lw20_ex100_lo100_k7_k7_fold4