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	4	6.6336	0.0014	6.6323	2.5753
No log	2.0	8	3.7980	0.0	3.7967	1.9485
No log	3.0	12	2.0750	0.0488	2.0743	1.4402
No log	4.0	16	1.1755	0.0	1.1750	1.0840
No log	5.0	20	0.9606	0.1290	0.9603	0.9799
No log	6.0	24	0.9172	0.2319	0.9168	0.9575
No log	7.0	28	0.8571	0.3088	0.8567	0.9256
No log	8.0	32	1.0449	0.1114	1.0443	1.0219
No log	9.0	36	0.7303	0.3468	0.7301	0.8544
No log	10.0	40	0.6947	0.3514	0.6946	0.8334
No log	11.0	44	0.8181	0.2412	0.8181	0.9045
No log	12.0	48	0.7399	0.2961	0.7400	0.8602
No log	13.0	52	0.8865	0.2538	0.8864	0.9415
No log	14.0	56	0.7359	0.2811	0.7361	0.8580
No log	15.0	60	0.7003	0.2738	0.7005	0.8370
No log	16.0	64	0.6976	0.3452	0.6976	0.8352
No log	17.0	68	0.7034	0.2913	0.7034	0.8387
No log	18.0	72	0.7380	0.3447	0.7376	0.8588
No log	19.0	76	0.8054	0.3595	0.8048	0.8971
No log	20.0	80	0.8229	0.3597	0.8223	0.9068
No log	21.0	84	0.7679	0.4215	0.7674	0.8760
No log	22.0	88	1.0666	0.2744	1.0654	1.0322
No log	23.0	92	0.8110	0.4310	0.8101	0.9000
No log	24.0	96	0.8013	0.4362	0.8003	0.8946
No log	25.0	100	1.2435	0.2859	1.2423	1.1146
No log	26.0	104	0.7738	0.4070	0.7733	0.8794
No log	27.0	108	1.1221	0.2372	1.1211	1.0588
No log	28.0	112	0.9155	0.3149	0.9148	0.9564
No log	29.0	116	0.9194	0.3210	0.9185	0.9584
No log	30.0	120	0.9121	0.3164	0.9112	0.9546
No log	31.0	124	0.8264	0.3703	0.8257	0.9087
No log	32.0	128	0.8868	0.3398	0.8860	0.9413
No log	33.0	132	0.8978	0.3118	0.8971	0.9471
No log	34.0	136	0.9906	0.2797	0.9897	0.9948
No log	35.0	140	0.7567	0.4123	0.7561	0.8695
No log	36.0	144	1.0635	0.2818	1.0625	1.0308
No log	37.0	148	0.8029	0.4341	0.8020	0.8956
No log	38.0	152	0.7922	0.4429	0.7913	0.8896
No log	39.0	156	1.1679	0.2869	1.1668	1.0802
No log	40.0	160	0.7096	0.4750	0.7089	0.8419
No log	41.0	164	1.1309	0.2428	1.1298	1.0629
No log	42.0	168	0.7386	0.4276	0.7379	0.8590
No log	43.0	172	0.9578	0.3021	0.9569	0.9782
No log	44.0	176	0.8322	0.3787	0.8315	0.9118
No log	45.0	180	0.7540	0.4194	0.7532	0.8679
No log	46.0	184	1.0288	0.2751	1.0277	1.0138
No log	47.0	188	0.8674	0.3572	0.8664	0.9308
No log	48.0	192	1.0117	0.3180	1.0106	1.0053
No log	49.0	196	0.7368	0.4525	0.7360	0.8579
No log	50.0	200	1.0865	0.2969	1.0853	1.0418
No log	51.0	204	0.8012	0.4306	0.8002	0.8946
No log	52.0	208	1.1439	0.2634	1.1427	1.0690
No log	53.0	212	0.8365	0.3761	0.8355	0.9141
No log	54.0	216	0.8265	0.3804	0.8256	0.9086
No log	55.0	220	0.8479	0.3783	0.8471	0.9204
No log	56.0	224	1.0630	0.2728	1.0619	1.0305
No log	57.0	228	0.8327	0.3731	0.8318	0.9120
No log	58.0	232	0.9012	0.3621	0.9002	0.9488
No log	59.0	236	0.8124	0.3907	0.8115	0.9008
No log	60.0	240	0.9553	0.3391	0.9543	0.9769
No log	61.0	244	0.8035	0.3957	0.8027	0.8959
No log	62.0	248	1.1446	0.2555	1.1435	1.0693
No log	63.0	252	0.9730	0.3144	0.9720	0.9859
No log	64.0	256	0.7808	0.4083	0.7801	0.8832
No log	65.0	260	1.0293	0.2868	1.0283	1.0141
No log	66.0	264	0.7609	0.4085	0.7602	0.8719
No log	67.0	268	0.9248	0.3206	0.9239	0.9612
No log	68.0	272	0.8582	0.3703	0.8573	0.9259
No log	69.0	276	0.8666	0.3492	0.8657	0.9304
No log	70.0	280	0.8879	0.3299	0.8870	0.9418

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_k5_k5_fold3

BERT_V8_sp20_lw10_ex30_lo00_k5_k5_fold3

Model description

Intended uses & limitations

Training and evaluation data

Training procedure

Training hyperparameters

Training results

Framework versions

genki10/
BERT_V8_sp20_lw10_ex30_lo00_k5_k5_fold3