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	4	9.6613	0.0	9.6587	3.1078
No log	2.0	8	6.6972	0.0018	6.6948	2.5874
No log	3.0	12	3.9451	0.0	3.9433	1.9858
No log	4.0	16	2.2317	0.0376	2.2299	1.4933
No log	5.0	20	1.2186	0.0198	1.2173	1.1033
No log	6.0	24	1.0388	-0.0052	1.0375	1.0186
No log	7.0	28	0.8976	0.1515	0.8966	0.9469
No log	8.0	32	1.2868	0.0379	1.2853	1.1337
No log	9.0	36	1.0118	0.0354	1.0104	1.0052
No log	10.0	40	1.0346	-0.0364	1.0332	1.0165
No log	11.0	44	1.0821	-0.0492	1.0805	1.0395
No log	12.0	48	0.7581	0.3621	0.7568	0.8700
No log	13.0	52	0.8136	0.2622	0.8123	0.9013
No log	14.0	56	0.6156	0.4445	0.6146	0.7840
No log	15.0	60	0.6415	0.4791	0.6404	0.8003
No log	16.0	64	0.5683	0.5155	0.5677	0.7534
No log	17.0	68	0.8588	0.3700	0.8574	0.9260
No log	18.0	72	0.5801	0.5877	0.5796	0.7613
No log	19.0	76	0.8801	0.4190	0.8787	0.9374
No log	20.0	80	0.6241	0.5081	0.6231	0.7894
No log	21.0	84	0.8016	0.3579	0.8007	0.8948
No log	22.0	88	0.6044	0.5388	0.6037	0.7770
No log	23.0	92	0.7107	0.4516	0.7097	0.8424
No log	24.0	96	0.6904	0.4854	0.6898	0.8306
No log	25.0	100	0.9397	0.3172	0.9385	0.9687
No log	26.0	104	0.5835	0.5602	0.5830	0.7635
No log	27.0	108	0.7922	0.4393	0.7913	0.8895
No log	28.0	112	0.7069	0.4708	0.7062	0.8404
No log	29.0	116	0.8323	0.3862	0.8312	0.9117
No log	30.0	120	0.6644	0.4450	0.6636	0.8146
No log	31.0	124	0.8342	0.3535	0.8330	0.9127
No log	32.0	128	0.7102	0.4091	0.7093	0.8422
No log	33.0	132	0.6349	0.4961	0.6341	0.7963
No log	34.0	136	0.7788	0.3902	0.7778	0.8820
No log	35.0	140	0.8288	0.3239	0.8278	0.9098
No log	36.0	144	0.7208	0.4464	0.7198	0.8484
No log	37.0	148	0.7398	0.4165	0.7387	0.8595
No log	38.0	152	0.8040	0.3372	0.8029	0.8960
No log	39.0	156	0.7167	0.3991	0.7158	0.8460
No log	40.0	160	0.7324	0.4133	0.7313	0.8552
No log	41.0	164	0.7315	0.4579	0.7305	0.8547
No log	42.0	168	0.7765	0.4274	0.7754	0.8806
No log	43.0	172	0.7898	0.3534	0.7887	0.8881
No log	44.0	176	0.7671	0.3578	0.7660	0.8752
No log	45.0	180	0.7351	0.4029	0.7340	0.8568
No log	46.0	184	0.7300	0.4069	0.7291	0.8539
No log	47.0	188	0.9102	0.2906	0.9090	0.9534
No log	48.0	192	0.7844	0.4245	0.7833	0.8850

Framework versions

Transformers 4.51.1
Pytorch 2.5.1+cu124
Datasets 3.5.0
Tokenizers 0.21.0

genki10/BERT_V8_sp10_lw40_ex10_lo00_k5_k5_fold1

BERT_V8_sp10_lw40_ex10_lo00_k5_k5_fold1

Model description

Intended uses & limitations

Training and evaluation data

Training procedure

Training hyperparameters

Training results

Framework versions

genki10/
BERT_V8_sp10_lw40_ex10_lo00_k5_k5_fold1