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	2	11.9804	0.0	11.9778	3.4609
No log	2.0	4	10.1796	0.0066	10.1770	3.1901
No log	3.0	6	8.2961	0.0	8.2937	2.8799
No log	4.0	8	6.1340	0.0086	6.1316	2.4762
No log	5.0	10	4.3624	0.0176	4.3603	2.0881
No log	6.0	12	3.1066	0.0	3.1048	1.7620
No log	7.0	14	2.3007	0.0948	2.2990	1.5162
No log	8.0	16	1.8938	0.0594	1.8922	1.3756
No log	9.0	18	1.3910	0.0315	1.3895	1.1788
No log	10.0	20	1.2490	0.0276	1.2477	1.1170
No log	11.0	22	1.0249	0.0106	1.0237	1.0118
No log	12.0	24	0.8866	0.1168	0.8853	0.9409
No log	13.0	26	0.7635	0.4459	0.7624	0.8732
No log	14.0	28	0.7572	0.4591	0.7563	0.8696
No log	15.0	30	0.6621	0.4761	0.6612	0.8131
No log	16.0	32	1.2940	0.3111	1.2926	1.1369
No log	17.0	34	1.2834	0.3439	1.2819	1.1322
No log	18.0	36	0.6584	0.5014	0.6573	0.8107
No log	19.0	38	0.9802	0.4079	0.9788	0.9893
No log	20.0	40	0.8217	0.4250	0.8203	0.9057
No log	21.0	42	0.6484	0.4571	0.6472	0.8045
No log	22.0	44	0.9879	0.3797	0.9863	0.9931
No log	23.0	46	1.0387	0.3761	1.0372	1.0184
No log	24.0	48	0.8000	0.3743	0.7988	0.8938
No log	25.0	50	1.0772	0.3206	1.0758	1.0372
No log	26.0	52	1.0838	0.3230	1.0825	1.0404
No log	27.0	54	0.9094	0.3710	0.9083	0.9530
No log	28.0	56	1.1588	0.3259	1.1574	1.0758
No log	29.0	58	1.1812	0.3313	1.1796	1.0861
No log	30.0	60	0.9521	0.3794	0.9507	0.9750
No log	31.0	62	1.2077	0.2781	1.2060	1.0982
No log	32.0	64	1.2156	0.2723	1.2139	1.1018
No log	33.0	66	0.9965	0.3580	0.9950	0.9975
No log	34.0	68	1.0430	0.3343	1.0415	1.0205
No log	35.0	70	1.3292	0.2372	1.3276	1.1522
No log	36.0	72	1.2315	0.2564	1.2300	1.1090
No log	37.0	74	0.9529	0.3956	0.9517	0.9755
No log	38.0	76	0.9443	0.4046	0.9431	0.9711
No log	39.0	78	1.3630	0.2498	1.3614	1.1668
No log	40.0	80	1.4785	0.2242	1.4767	1.2152
No log	41.0	82	1.0487	0.3108	1.0472	1.0233
No log	42.0	84	1.0551	0.3508	1.0536	1.0264
No log	43.0	86	1.4008	0.2216	1.3990	1.1828
No log	44.0	88	1.4779	0.2137	1.4761	1.2149
No log	45.0	90	1.0929	0.3004	1.0913	1.0447
No log	46.0	92	1.0334	0.3399	1.0319	1.0158
No log	47.0	94	1.1631	0.2822	1.1615	1.0777
No log	48.0	96	1.0134	0.3432	1.0119	1.0059

Framework versions

Transformers 4.51.1
Pytorch 2.5.1+cu124
Datasets 3.5.0
Tokenizers 0.21.0

genki10/BERT_V8_sp10_lw40_ex50_lo100_k2_k2_fold1

BERT_V8_sp10_lw40_ex50_lo100_k2_k2_fold1

Model description

Intended uses & limitations

Training and evaluation data

Training procedure

Training hyperparameters

Training results

Framework versions

genki10/
BERT_V8_sp10_lw40_ex50_lo100_k2_k2_fold1