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	3	10.5173	0.0048	10.5175	3.2431
No log	2.0	6	7.7869	0.0018	7.7873	2.7906
No log	3.0	9	5.0090	0.0316	5.0094	2.2382
No log	4.0	12	3.5234	0.0078	3.5236	1.8771
No log	5.0	15	2.1097	0.0721	2.1102	1.4527
No log	6.0	18	1.4841	0.0213	1.4845	1.2184
No log	7.0	21	1.2730	0.0213	1.2733	1.1284
No log	8.0	24	1.0368	0.0213	1.0371	1.0184
No log	9.0	27	1.7930	0.1332	1.7931	1.3391
No log	10.0	30	1.0978	0.1406	1.0979	1.0478
No log	11.0	33	1.6110	0.1782	1.6107	1.2691
No log	12.0	36	1.6942	0.1954	1.6938	1.3015
No log	13.0	39	1.5811	0.2110	1.5809	1.2573
No log	14.0	42	1.7638	0.1416	1.7632	1.3279
No log	15.0	45	2.2140	0.0763	2.2133	1.4877
No log	16.0	48	1.9394	0.1143	1.9385	1.3923
No log	17.0	51	1.8475	0.1312	1.8468	1.3590
No log	18.0	54	2.3341	0.1028	2.3331	1.5275
No log	19.0	57	1.7676	0.1594	1.7669	1.3293
No log	20.0	60	1.8937	0.1450	1.8930	1.3759
No log	21.0	63	1.8830	0.1478	1.8826	1.3721
No log	22.0	66	1.8804	0.1738	1.8800	1.3711
No log	23.0	69	1.7553	0.1824	1.7549	1.3247
No log	24.0	72	1.2879	0.2603	1.2874	1.1346
No log	25.0	75	2.4160	0.1049	2.4150	1.5540
No log	26.0	78	1.8467	0.1707	1.8460	1.3587
No log	27.0	81	1.2325	0.2829	1.2321	1.1100
No log	28.0	84	2.4421	0.1161	2.4416	1.5626
No log	29.0	87	1.5756	0.1952	1.5750	1.2550
No log	30.0	90	2.8334	0.0786	2.8322	1.6829
No log	31.0	93	1.4939	0.2223	1.4933	1.2220
No log	32.0	96	2.7050	0.0859	2.7040	1.6444
No log	33.0	99	1.4926	0.2098	1.4921	1.2215
No log	34.0	102	1.7067	0.1732	1.7061	1.3062
No log	35.0	105	2.5081	0.0881	2.5072	1.5834
No log	36.0	108	1.3861	0.2209	1.3854	1.1770
No log	37.0	111	2.2933	0.0910	2.2922	1.5140
No log	38.0	114	2.1659	0.1063	2.1650	1.4714
No log	39.0	117	1.4867	0.1898	1.4860	1.2190
No log	40.0	120	2.5974	0.0621	2.5962	1.6113
No log	41.0	123	1.8884	0.1363	1.8874	1.3738
No log	42.0	126	2.0353	0.1218	2.0342	1.4262
No log	43.0	129	2.1842	0.1013	2.1833	1.4776
No log	44.0	132	1.7042	0.1611	1.7035	1.3052
No log	45.0	135	1.9143	0.1329	1.9137	1.3833
No log	46.0	138	1.5493	0.1824	1.5486	1.2444
No log	47.0	141	1.5156	0.1673	1.5147	1.2307
No log	48.0	144	2.1054	0.0636	2.1041	1.4506
No log	49.0	147	1.9067	0.0938	1.9057	1.3805
No log	50.0	150	1.8447	0.1131	1.8440	1.3579
No log	51.0	153	2.0194	0.0774	2.0185	1.4207
No log	52.0	156	1.9315	0.0773	1.9304	1.3894
No log	53.0	159	2.1257	0.0550	2.1246	1.4576
No log	54.0	162	1.5793	0.1551	1.5787	1.2565
No log	55.0	165	2.1403	0.0889	2.1397	1.4628
No log	56.0	168	1.9336	0.0872	1.9331	1.3904
No log	57.0	171	1.9306	0.0988	1.9300	1.3892

Framework versions

Transformers 4.47.0
Pytorch 2.5.1+cu121
Datasets 3.3.1
Tokenizers 0.21.0

genki10/BERT_V8_sp20_lw10_ex100_lo00_k3_k3_fold2

BERT_V8_sp20_lw10_ex100_lo00_k3_k3_fold2

Model description

Intended uses & limitations

Training and evaluation data

Training procedure

Training hyperparameters

Training results

Framework versions

genki10/
BERT_V8_sp20_lw10_ex100_lo00_k3_k3_fold2