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	2	11.3038	0.0114	11.3038	3.3621
No log	2.0	4	9.8573	0.0018	9.8573	3.1396
No log	3.0	6	8.3753	0.0	8.3753	2.8940
No log	4.0	8	6.5531	0.0008	6.5531	2.5599
No log	5.0	10	4.6275	0.0211	4.6275	2.1512
No log	6.0	12	3.5255	0.0115	3.5255	1.8776
No log	7.0	14	2.3361	0.1726	2.3361	1.5284
No log	8.0	16	1.8726	0.0871	1.8726	1.3684
No log	9.0	18	1.2413	0.0382	1.2413	1.1141
No log	10.0	20	0.9619	0.0316	0.9619	0.9808
No log	11.0	22	0.8455	0.2102	0.8455	0.9195
No log	12.0	24	0.7609	0.3260	0.7609	0.8723
No log	13.0	26	0.7183	0.4467	0.7183	0.8475
No log	14.0	28	0.8463	0.3123	0.8463	0.9200
No log	15.0	30	0.7664	0.4687	0.7664	0.8755
No log	16.0	32	0.6199	0.5073	0.6199	0.7873
No log	17.0	34	0.8127	0.4286	0.8127	0.9015
No log	18.0	36	0.6228	0.5401	0.6228	0.7892
No log	19.0	38	0.8050	0.4726	0.8050	0.8972
No log	20.0	40	1.1597	0.2958	1.1597	1.0769
No log	21.0	42	0.6005	0.5300	0.6005	0.7749
No log	22.0	44	0.6208	0.5022	0.6208	0.7879
No log	23.0	46	0.6660	0.5133	0.6660	0.8161
No log	24.0	48	0.5510	0.5148	0.5510	0.7423
No log	25.0	50	0.6383	0.5243	0.6383	0.7989
No log	26.0	52	0.5363	0.5987	0.5363	0.7323
No log	27.0	54	0.6062	0.5391	0.6062	0.7786
No log	28.0	56	0.7197	0.5046	0.7197	0.8483
No log	29.0	58	0.5805	0.5461	0.5805	0.7619
No log	30.0	60	0.7527	0.4893	0.7527	0.8676
No log	31.0	62	0.8208	0.4522	0.8208	0.9060
No log	32.0	64	0.6683	0.5319	0.6683	0.8175
No log	33.0	66	0.7314	0.4998	0.7314	0.8552
No log	34.0	68	0.8011	0.4833	0.8011	0.8950
No log	35.0	70	0.9724	0.4029	0.9724	0.9861
No log	36.0	72	0.7480	0.4713	0.7480	0.8648
No log	37.0	74	0.9124	0.3884	0.9124	0.9552
No log	38.0	76	0.7406	0.4737	0.7406	0.8606
No log	39.0	78	0.8346	0.4376	0.8346	0.9135
No log	40.0	80	0.6925	0.4632	0.6925	0.8322
No log	41.0	82	0.7810	0.4610	0.7810	0.8837
No log	42.0	84	0.7065	0.4673	0.7065	0.8405
No log	43.0	86	0.8782	0.4169	0.8782	0.9371
No log	44.0	88	0.7802	0.4590	0.7802	0.8833
No log	45.0	90	0.9677	0.3760	0.9677	0.9837
No log	46.0	92	0.8741	0.4133	0.8741	0.9349
No log	47.0	94	0.8541	0.4163	0.8541	0.9242
No log	48.0	96	0.7607	0.4545	0.7607	0.8722
No log	49.0	98	0.8707	0.4327	0.8707	0.9331
No log	50.0	100	0.9429	0.3898	0.9429	0.9710
No log	51.0	102	0.6345	0.4571	0.6345	0.7966
No log	52.0	104	0.6142	0.4669	0.6142	0.7837
No log	53.0	106	0.9018	0.3931	0.9018	0.9496
No log	54.0	108	0.9960	0.3620	0.9960	0.9980
No log	55.0	110	0.6892	0.4465	0.6892	0.8302
No log	56.0	112	0.6492	0.4519	0.6492	0.8057

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_k3_k3_fold0

BERT_V8_sp10_lw20_ex200_lo100_k3_k3_fold0

Model description

Intended uses & limitations

Training and evaluation data

Training procedure

Training hyperparameters

Training results

Framework versions

genki10/
BERT_V8_sp10_lw20_ex200_lo100_k3_k3_fold0