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	1	12.0797	-0.0041	12.0770	3.4752
No log	2.0	2	10.9610	-0.0185	10.9584	3.3104
No log	3.0	3	9.5554	-0.0002	9.5528	3.0908
No log	4.0	4	8.4250	0.0	8.4226	2.9022
No log	5.0	5	7.5199	0.0	7.5176	2.7418
No log	6.0	6	6.7079	0.0	6.7057	2.5895
No log	7.0	7	6.0874	0.0002	6.0851	2.4668
No log	8.0	8	5.4587	0.0178	5.4565	2.3359
No log	9.0	9	4.7309	0.0118	4.7288	2.1746
No log	10.0	10	4.1579	0.0	4.1559	2.0386
No log	11.0	11	3.6843	0.0	3.6823	1.9189
No log	12.0	12	3.2932	0.0	3.2913	1.8142
No log	13.0	13	3.0055	0.0	3.0036	1.7331
No log	14.0	14	2.5999	0.0	2.5981	1.6119
No log	15.0	15	2.2497	0.1660	2.2479	1.4993
No log	16.0	16	2.0128	0.0872	2.0111	1.4181
No log	17.0	17	1.8351	0.0521	1.8335	1.3541
No log	18.0	18	1.7637	0.0211	1.7621	1.3275
No log	19.0	19	1.5431	0.0211	1.5416	1.2416
No log	20.0	20	1.3620	0.0211	1.3605	1.1664
No log	21.0	21	1.2566	0.0211	1.2551	1.1203
No log	22.0	22	1.1584	0.0	1.1569	1.0756
No log	23.0	23	1.0927	0.0	1.0913	1.0447
No log	24.0	24	1.0278	0.0	1.0264	1.0131
No log	25.0	25	0.9431	0.0	0.9417	0.9704
No log	26.0	26	0.8814	0.0263	0.8801	0.9381
No log	27.0	27	0.8275	0.3831	0.8263	0.9090
No log	28.0	28	0.7719	0.5153	0.7706	0.8779
No log	29.0	29	0.7246	0.4986	0.7234	0.8505
No log	30.0	30	0.6891	0.4771	0.6879	0.8294
No log	31.0	31	0.6527	0.5115	0.6515	0.8072
No log	32.0	32	0.6399	0.5407	0.6387	0.7992
No log	33.0	33	0.6078	0.5336	0.6066	0.7789
No log	34.0	34	0.5868	0.5250	0.5857	0.7653
No log	35.0	35	0.6007	0.5341	0.5996	0.7743
No log	36.0	36	0.6286	0.5179	0.6275	0.7921
No log	37.0	37	0.6060	0.5267	0.6049	0.7778
No log	38.0	38	0.5794	0.4888	0.5783	0.7605
No log	39.0	39	0.5667	0.4926	0.5656	0.7521
No log	40.0	40	0.5574	0.5006	0.5564	0.7459
No log	41.0	41	0.5569	0.5511	0.5559	0.7456
No log	42.0	42	0.5477	0.5340	0.5467	0.7394
No log	43.0	43	0.5667	0.5410	0.5656	0.7521
No log	44.0	44	0.5844	0.4812	0.5834	0.7638
No log	45.0	45	0.6053	0.4752	0.6042	0.7773
No log	46.0	46	0.6354	0.5029	0.6343	0.7964
No log	47.0	47	0.6433	0.5007	0.6421	0.8013
No log	48.0	48	0.6058	0.5137	0.6047	0.7776
No log	49.0	49	0.6248	0.5180	0.6236	0.7897
No log	50.0	50	0.6139	0.4895	0.6128	0.7828
No log	51.0	51	0.6151	0.5088	0.6139	0.7835
No log	52.0	52	0.6291	0.5150	0.6279	0.7924
No log	53.0	53	0.6691	0.4875	0.6679	0.8173
No log	54.0	54	0.6914	0.4708	0.6902	0.8308
No log	55.0	55	0.7351	0.4332	0.7338	0.8566
No log	56.0	56	0.7504	0.4237	0.7491	0.8655
No log	57.0	57	0.7659	0.4182	0.7646	0.8744
No log	58.0	58	0.7745	0.4365	0.7732	0.8793
No log	59.0	59	0.7470	0.4334	0.7457	0.8635
No log	60.0	60	0.7403	0.4367	0.7391	0.8597
No log	61.0	61	0.7525	0.4705	0.7513	0.8668
No log	62.0	62	0.7436	0.4737	0.7424	0.8616
No log	63.0	63	0.7202	0.4454	0.7190	0.8479
No log	64.0	64	0.7388	0.4249	0.7375	0.8588
No log	65.0	65	0.7492	0.4215	0.7479	0.8648
No log	66.0	66	0.7404	0.4279	0.7392	0.8597
No log	67.0	67	0.7476	0.4570	0.7464	0.8640
No log	68.0	68	0.7552	0.4812	0.7541	0.8684
No log	69.0	69	0.7331	0.4637	0.7320	0.8555
No log	70.0	70	0.7238	0.4670	0.7226	0.8501
No log	71.0	71	0.7414	0.4440	0.7402	0.8604

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_k1_k1_fold1

BERT_V8_sp10_lw40_ex50_lo100_k1_k1_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_k1_k1_fold1