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	9.6432	0.0055	9.6435	3.1054
No log	2.0	8	5.8088	0.0333	5.8092	2.4102
No log	3.0	12	3.2315	0.0039	3.2321	1.7978
No log	4.0	16	1.6519	0.0503	1.6525	1.2855
No log	5.0	20	0.9731	0.0	0.9736	0.9867
No log	6.0	24	0.7966	0.1102	0.7971	0.8928
No log	7.0	28	0.7835	0.1312	0.7838	0.8853
No log	8.0	32	0.6727	0.3918	0.6728	0.8203
No log	9.0	36	0.5295	0.4939	0.5294	0.7276
No log	10.0	40	0.9314	0.3474	0.9316	0.9652
No log	11.0	44	0.5071	0.6101	0.5068	0.7119
No log	12.0	48	1.6444	0.2853	1.6446	1.2824
No log	13.0	52	0.5087	0.5540	0.5086	0.7132
No log	14.0	56	0.8502	0.4097	0.8503	0.9221
No log	15.0	60	0.5346	0.5772	0.5345	0.7311
No log	16.0	64	0.8202	0.4221	0.8202	0.9057
No log	17.0	68	0.6910	0.4873	0.6909	0.8312
No log	18.0	72	0.5903	0.5399	0.5900	0.7681
No log	19.0	76	0.5883	0.5288	0.5880	0.7668
No log	20.0	80	0.6063	0.5116	0.6061	0.7785
No log	21.0	84	0.5921	0.5274	0.5920	0.7694
No log	22.0	88	0.5968	0.5288	0.5967	0.7725
No log	23.0	92	0.5845	0.5413	0.5844	0.7645
No log	24.0	96	0.6430	0.4842	0.6430	0.8018
No log	25.0	100	0.6105	0.4946	0.6104	0.7813
No log	26.0	104	0.6237	0.4694	0.6236	0.7897
No log	27.0	108	0.6520	0.4482	0.6519	0.8074
No log	28.0	112	0.5624	0.5438	0.5623	0.7498
No log	29.0	116	0.8327	0.3864	0.8327	0.9125
No log	30.0	120	0.5492	0.5593	0.5491	0.7410
No log	31.0	124	1.0251	0.3189	1.0250	1.0124
No log	32.0	128	0.5668	0.5263	0.5666	0.7527
No log	33.0	132	0.7508	0.3791	0.7507	0.8664
No log	34.0	136	0.6952	0.4284	0.6951	0.8338
No log	35.0	140	0.5576	0.5171	0.5575	0.7467
No log	36.0	144	1.0306	0.3245	1.0306	1.0152
No log	37.0	148	0.5488	0.5388	0.5486	0.7407
No log	38.0	152	0.7493	0.3991	0.7493	0.8656
No log	39.0	156	0.6640	0.4657	0.6639	0.8148
No log	40.0	160	0.5600	0.5291	0.5598	0.7482
No log	41.0	164	0.9352	0.3232	0.9351	0.9670

Framework versions

Transformers 4.51.1
Pytorch 2.5.1+cu124
Datasets 3.5.0
Tokenizers 0.21.0

genki10/BERT_V8_sp10_lw20_ex200_lo50_k10_k10_fold2

BERT_V8_sp10_lw20_ex200_lo50_k10_k10_fold2

Model description

Intended uses & limitations

Training and evaluation data

Training procedure

Training hyperparameters

Training results

Framework versions

genki10/
BERT_V8_sp10_lw20_ex200_lo50_k10_k10_fold2