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	11.3139	-0.0044	11.3112	3.3632
No log	2.0	6	6.8977	0.0002	6.8957	2.6260
No log	3.0	9	4.7262	0.0088	4.7243	2.1735
No log	4.0	12	3.4468	0.0104	3.4450	1.8561
No log	5.0	15	2.7983	-0.0493	2.7965	1.6723
No log	6.0	18	1.8271	0.0691	1.8255	1.3511
No log	7.0	21	1.3226	0.0812	1.3212	1.1494
No log	8.0	24	0.9133	0.0817	0.9121	0.9550
No log	9.0	27	0.8606	0.1990	0.8596	0.9271
No log	10.0	30	0.8746	0.1434	0.8736	0.9347
No log	11.0	33	0.7253	0.4380	0.7243	0.8511
No log	12.0	36	0.9748	0.4538	0.9736	0.9867
No log	13.0	39	0.8921	0.2896	0.8911	0.9440
No log	14.0	42	0.7433	0.4697	0.7425	0.8617
No log	15.0	45	0.7303	0.4354	0.7294	0.8541
No log	16.0	48	0.7536	0.3788	0.7528	0.8677
No log	17.0	51	0.6688	0.4807	0.6681	0.8173
No log	18.0	54	1.0992	0.1527	1.0984	1.0480
No log	19.0	57	0.6653	0.5347	0.6645	0.8152
No log	20.0	60	0.6544	0.4980	0.6538	0.8086
No log	21.0	63	1.1426	0.1593	1.1419	1.0686
No log	22.0	66	0.6254	0.5168	0.6250	0.7906
No log	23.0	69	0.9626	0.2996	0.9622	0.9809
No log	24.0	72	0.6571	0.4791	0.6567	0.8104
No log	25.0	75	1.3000	0.0615	1.2992	1.1398
No log	26.0	78	0.8468	0.3924	0.8465	0.9201
No log	27.0	81	0.6915	0.5477	0.6912	0.8314
No log	28.0	84	1.4097	0.0221	1.4087	1.1869
No log	29.0	87	1.0450	0.2970	1.0447	1.0221
No log	30.0	90	0.9330	0.3902	0.9329	0.9659
No log	31.0	93	1.0729	0.2920	1.0726	1.0357
No log	32.0	96	0.8521	0.4646	0.8520	0.9230
No log	33.0	99	1.2962	0.1348	1.2956	1.1382
No log	34.0	102	0.8837	0.4436	0.8835	0.9400
No log	35.0	105	1.1458	0.2754	1.1455	1.0703
No log	36.0	108	1.0560	0.3267	1.0560	1.0276
No log	37.0	111	1.2457	0.2437	1.2455	1.1160
No log	38.0	114	1.1581	0.2915	1.1580	1.0761
No log	39.0	117	1.4833	0.1085	1.4828	1.2177
No log	40.0	120	1.1876	0.3277	1.1877	1.0898
No log	41.0	123	1.6484	0.0477	1.6476	1.2836
No log	42.0	126	1.1228	0.3597	1.1229	1.0597
No log	43.0	129	1.0622	0.4077	1.0624	1.0307
No log	44.0	132	1.3379	0.2459	1.3375	1.1565
No log	45.0	135	1.3351	0.1919	1.3344	1.1552
No log	46.0	138	1.3239	0.2084	1.3234	1.1504
No log	47.0	141	1.3241	0.2726	1.3239	1.1506
No log	48.0	144	1.6057	0.1138	1.6051	1.2669
No log	49.0	147	1.5563	0.1679	1.5559	1.2473
No log	50.0	150	1.6933	0.0740	1.6924	1.3009
No log	51.0	153	1.4271	0.2239	1.4267	1.1944
No log	52.0	156	1.5478	0.1642	1.5472	1.2439
No log	53.0	159	1.5874	0.1765	1.5869	1.2597
No log	54.0	162	1.4542	0.2611	1.4540	1.2058
No log	55.0	165	1.4236	0.2719	1.4235	1.1931
No log	56.0	168	1.7898	0.0431	1.7887	1.3374
No log	57.0	171	1.8195	0.0533	1.8186	1.3486

Framework versions

Transformers 4.47.0
Pytorch 2.5.1+cu121
Datasets 3.3.1
Tokenizers 0.21.0

genki10/BERT_V8_sp20_lw10_ex30_lo00_k3_k3_fold1

BERT_V8_sp20_lw10_ex30_lo00_k3_k3_fold1

Model description

Intended uses & limitations

Training and evaluation data

Training procedure

Training hyperparameters

Training results

Framework versions

genki10/
BERT_V8_sp20_lw10_ex30_lo00_k3_k3_fold1