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	6.8171	0.0	6.8157	2.6107
No log	2.0	8	4.0403	0.0114	4.0392	2.0098
No log	3.0	12	2.4387	0.1337	2.4379	1.5614
No log	4.0	16	1.4555	0.0365	1.4548	1.2061
No log	5.0	20	0.9859	0.0202	0.9853	0.9926
No log	6.0	24	0.8032	0.3558	0.8028	0.8960
No log	7.0	28	0.8494	0.3292	0.8490	0.9214
No log	8.0	32	0.8882	0.3107	0.8880	0.9423
No log	9.0	36	0.6265	0.4124	0.6265	0.7915
No log	10.0	40	0.6275	0.4002	0.6277	0.7923
No log	11.0	44	0.6450	0.4496	0.6453	0.8033
No log	12.0	48	0.6097	0.4796	0.6099	0.7809
No log	13.0	52	0.7460	0.4153	0.7463	0.8639
No log	14.0	56	0.5974	0.5251	0.5976	0.7731
No log	15.0	60	0.6732	0.4782	0.6736	0.8207
No log	16.0	64	0.6860	0.4797	0.6864	0.8285
No log	17.0	68	0.7006	0.4750	0.7010	0.8373
No log	18.0	72	0.7161	0.4719	0.7163	0.8464
No log	19.0	76	0.8619	0.4327	0.8622	0.9285
No log	20.0	80	0.7909	0.4535	0.7914	0.8896
No log	21.0	84	0.7059	0.4680	0.7063	0.8404
No log	22.0	88	0.8575	0.4103	0.8578	0.9262
No log	23.0	92	0.6410	0.5089	0.6412	0.8007
No log	24.0	96	0.6702	0.4863	0.6702	0.8187
No log	25.0	100	0.9132	0.3558	0.9133	0.9557
No log	26.0	104	0.7534	0.4632	0.7538	0.8682
No log	27.0	108	0.7441	0.4490	0.7444	0.8628
No log	28.0	112	0.9128	0.3609	0.9130	0.9555
No log	29.0	116	0.7136	0.4826	0.7139	0.8449
No log	30.0	120	0.8225	0.4206	0.8227	0.9070
No log	31.0	124	0.7525	0.4466	0.7527	0.8676
No log	32.0	128	1.0623	0.3219	1.0625	1.0308
No log	33.0	132	0.8350	0.4261	0.8353	0.9140
No log	34.0	136	0.8637	0.4118	0.8640	0.9295
No log	35.0	140	0.9008	0.3573	0.9011	0.9493
No log	36.0	144	0.8245	0.4010	0.8249	0.9082
No log	37.0	148	0.6951	0.4622	0.6955	0.8340
No log	38.0	152	0.8278	0.3965	0.8281	0.9100
No log	39.0	156	0.7041	0.4428	0.7045	0.8394
No log	40.0	160	0.9425	0.3429	0.9427	0.9709
No log	41.0	164	0.6662	0.4652	0.6665	0.8164
No log	42.0	168	1.1218	0.3032	1.1221	1.0593
No log	43.0	172	0.7284	0.4661	0.7287	0.8536
No log	44.0	176	0.8728	0.3922	0.8730	0.9343

Framework versions

Transformers 4.47.0
Pytorch 2.5.1+cu121
Datasets 3.3.1
Tokenizers 0.21.0

genki10/BERT_V8_sp10_lw20_ex200_lo100_k7_k7_fold3

BERT_V8_sp10_lw20_ex200_lo100_k7_k7_fold3

Model description

Intended uses & limitations

Training and evaluation data

Training procedure

Training hyperparameters

Training results

Framework versions

genki10/
BERT_V8_sp10_lw20_ex200_lo100_k7_k7_fold3