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	9.3653	0.0018	9.3653	3.0603
No log	2.0	8	5.8319	0.0113	5.8319	2.4149
No log	3.0	12	3.4092	0.0040	3.4092	1.8464
No log	4.0	16	1.7507	0.0908	1.7507	1.3231
No log	5.0	20	1.1250	0.0316	1.1250	1.0607
No log	6.0	24	0.8482	0.2792	0.8482	0.9210
No log	7.0	28	1.1061	0.0316	1.1061	1.0517
No log	8.0	32	0.9914	0.1527	0.9914	0.9957
No log	9.0	36	1.8042	0.1616	1.8042	1.3432
No log	10.0	40	1.1546	0.2458	1.1546	1.0745
No log	11.0	44	1.1145	0.2876	1.1145	1.0557
No log	12.0	48	0.7548	0.4043	0.7548	0.8688
No log	13.0	52	1.0260	0.3586	1.0260	1.0129
No log	14.0	56	0.8844	0.4452	0.8844	0.9404
No log	15.0	60	1.0248	0.4442	1.0248	1.0123
No log	16.0	64	1.0647	0.4264	1.0647	1.0318
No log	17.0	68	1.1097	0.3837	1.1097	1.0534
No log	18.0	72	2.1023	0.1977	2.1023	1.4499
No log	19.0	76	1.2385	0.3587	1.2385	1.1129
No log	20.0	80	1.0911	0.3820	1.0911	1.0445
No log	21.0	84	1.8978	0.2029	1.8978	1.3776
No log	22.0	88	0.9590	0.4335	0.9590	0.9793
No log	23.0	92	1.8143	0.2221	1.8143	1.3470
No log	24.0	96	0.9446	0.4261	0.9446	0.9719
No log	25.0	100	1.7322	0.2347	1.7322	1.3161
No log	26.0	104	1.0130	0.3782	1.0130	1.0065
No log	27.0	108	1.8488	0.2152	1.8488	1.3597
No log	28.0	112	0.9693	0.4176	0.9693	0.9845
No log	29.0	116	1.2769	0.3300	1.2769	1.1300
No log	30.0	120	1.5951	0.2885	1.5951	1.2630
No log	31.0	124	1.4424	0.3102	1.4424	1.2010
No log	32.0	128	1.6413	0.2491	1.6413	1.2811
No log	33.0	132	1.1535	0.3441	1.1535	1.0740
No log	34.0	136	1.3022	0.3260	1.3022	1.1412
No log	35.0	140	1.6692	0.2624	1.6692	1.2920
No log	36.0	144	1.5020	0.2941	1.5020	1.2256
No log	37.0	148	1.4052	0.2803	1.4052	1.1854
No log	38.0	152	1.3310	0.2755	1.3310	1.1537
No log	39.0	156	1.0338	0.3418	1.0338	1.0167
No log	40.0	160	1.4617	0.2312	1.4617	1.2090
No log	41.0	164	1.1626	0.3018	1.1626	1.0782
No log	42.0	168	1.0312	0.3627	1.0312	1.0155
No log	43.0	172	1.3582	0.2718	1.3582	1.1654
No log	44.0	176	1.3477	0.2946	1.3477	1.1609

Framework versions

Transformers 4.51.1
Pytorch 2.5.1+cu124
Datasets 3.5.0
Tokenizers 0.21.0

genki10/BERT_V8_sp10_lw40_ex100_lo00_k5_k5_fold4

BERT_V8_sp10_lw40_ex100_lo00_k5_k5_fold4

Model description

Intended uses & limitations

Training and evaluation data

Training procedure

Training hyperparameters

Training results

Framework versions

genki10/
BERT_V8_sp10_lw40_ex100_lo00_k5_k5_fold4