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	10.0444	0.0036	10.0444	3.1693
No log	2.0	2	8.9565	0.0	8.9565	2.9927
No log	3.0	3	8.1327	0.0	8.1327	2.8518
No log	4.0	4	7.5714	0.0	7.5714	2.7516
No log	5.0	5	7.1366	0.0	7.1366	2.6714
No log	6.0	6	6.7874	0.0	6.7874	2.6053
No log	7.0	7	6.3492	-0.0005	6.3492	2.5198
No log	8.0	8	5.9003	0.0195	5.9003	2.4291
No log	9.0	9	5.4895	0.0112	5.4895	2.3430
No log	10.0	10	5.0624	0.0115	5.0624	2.2500
No log	11.0	11	4.6478	0.0077	4.6478	2.1559
No log	12.0	12	4.2952	0.0039	4.2952	2.0725
No log	13.0	13	3.9516	0.0039	3.9516	1.9879
No log	14.0	14	3.5438	0.0	3.5438	1.8825
No log	15.0	15	3.1425	0.0	3.1425	1.7727
No log	16.0	16	2.7888	0.0	2.7888	1.6700
No log	17.0	17	2.4463	0.1259	2.4463	1.5641
No log	18.0	18	2.1650	0.0944	2.1650	1.4714
No log	19.0	19	1.9434	0.0627	1.9434	1.3941
No log	20.0	20	1.6857	0.0316	1.6857	1.2983
No log	21.0	21	1.5046	0.0316	1.5046	1.2266
No log	22.0	22	1.3655	0.0316	1.3655	1.1686
No log	23.0	23	1.2573	0.0316	1.2573	1.1213
No log	24.0	24	1.1709	0.0316	1.1709	1.0821
No log	25.0	25	1.0488	0.0316	1.0488	1.0241
No log	26.0	26	0.9300	0.0316	0.9300	0.9644
No log	27.0	27	0.8645	0.0737	0.8645	0.9298
No log	28.0	28	0.8007	0.3725	0.8007	0.8948
No log	29.0	29	0.8591	0.2261	0.8591	0.9269
No log	30.0	30	0.7649	0.3980	0.7649	0.8746
No log	31.0	31	0.6686	0.4203	0.6686	0.8177
No log	32.0	32	0.6625	0.3577	0.6625	0.8139
No log	33.0	33	0.6085	0.4218	0.6085	0.7801
No log	34.0	34	0.6132	0.4840	0.6132	0.7831
No log	35.0	35	0.6740	0.4911	0.6740	0.8210
No log	36.0	36	0.6018	0.4963	0.6018	0.7757
No log	37.0	37	0.5264	0.5136	0.5264	0.7255
No log	38.0	38	0.5067	0.4969	0.5067	0.7118
No log	39.0	39	0.5290	0.5362	0.5290	0.7273
No log	40.0	40	0.6917	0.5124	0.6917	0.8317
No log	41.0	41	0.6700	0.5104	0.6700	0.8185
No log	42.0	42	0.5061	0.5426	0.5061	0.7114
No log	43.0	43	0.4951	0.5397	0.4951	0.7036
No log	44.0	44	0.5959	0.5190	0.5959	0.7720
No log	45.0	45	0.5660	0.5364	0.5660	0.7523
No log	46.0	46	0.4735	0.5241	0.4735	0.6881
No log	47.0	47	0.4847	0.5550	0.4847	0.6962
No log	48.0	48	0.5926	0.5077	0.5926	0.7698
No log	49.0	49	0.6055	0.4943	0.6055	0.7781
No log	50.0	50	0.5266	0.5615	0.5266	0.7257
No log	51.0	51	0.5111	0.5746	0.5111	0.7149
No log	52.0	52	0.5433	0.5826	0.5433	0.7371
No log	53.0	53	0.5577	0.5606	0.5577	0.7468
No log	54.0	54	0.6024	0.5445	0.6024	0.7762
No log	55.0	55	0.5949	0.5515	0.5949	0.7713
No log	56.0	56	0.5794	0.5820	0.5794	0.7612
No log	57.0	57	0.5808	0.5713	0.5808	0.7621
No log	58.0	58	0.5956	0.5472	0.5956	0.7717
No log	59.0	59	0.5718	0.5673	0.5718	0.7562
No log	60.0	60	0.5572	0.5770	0.5572	0.7465
No log	61.0	61	0.5534	0.5769	0.5534	0.7439
No log	62.0	62	0.5932	0.5242	0.5932	0.7702
No log	63.0	63	0.5923	0.5272	0.5923	0.7696
No log	64.0	64	0.5463	0.5778	0.5463	0.7391
No log	65.0	65	0.5648	0.5806	0.5648	0.7515
No log	66.0	66	0.5916	0.5746	0.5916	0.7692
No log	67.0	67	0.5588	0.6019	0.5588	0.7475
No log	68.0	68	0.5337	0.5999	0.5337	0.7306
No log	69.0	69	0.5427	0.5787	0.5427	0.7367
No log	70.0	70	0.5344	0.5958	0.5344	0.7310
No log	71.0	71	0.5402	0.6127	0.5402	0.7350
No log	72.0	72	0.6086	0.5763	0.6086	0.7801
No log	73.0	73	0.6381	0.5600	0.6381	0.7988
No log	74.0	74	0.6051	0.5839	0.6051	0.7779
No log	75.0	75	0.5511	0.5903	0.5511	0.7423
No log	76.0	76	0.5522	0.5738	0.5522	0.7431
No log	77.0	77	0.5827	0.5335	0.5827	0.7633
No log	78.0	78	0.5836	0.5343	0.5836	0.7640
No log	79.0	79	0.5601	0.5740	0.5601	0.7484
No log	80.0	80	0.5480	0.6018	0.5480	0.7402
No log	81.0	81	0.5544	0.5897	0.5544	0.7446
No log	82.0	82	0.5537	0.5910	0.5537	0.7441
No log	83.0	83	0.5480	0.6068	0.5480	0.7403
No log	84.0	84	0.5455	0.6047	0.5455	0.7386
No log	85.0	85	0.5482	0.5985	0.5482	0.7404
No log	86.0	86	0.5492	0.6053	0.5492	0.7411
No log	87.0	87	0.5551	0.6078	0.5551	0.7450
No log	88.0	88	0.5588	0.6062	0.5588	0.7475
No log	89.0	89	0.5608	0.6058	0.5608	0.7489
No log	90.0	90	0.5616	0.6030	0.5616	0.7494
No log	91.0	91	0.5643	0.6047	0.5643	0.7512
No log	92.0	92	0.5654	0.6047	0.5654	0.7519
No log	93.0	93	0.5660	0.6078	0.5660	0.7523
No log	94.0	94	0.5698	0.6028	0.5698	0.7549
No log	95.0	95	0.5743	0.5945	0.5743	0.7578
No log	96.0	96	0.5745	0.5945	0.5745	0.7580
No log	97.0	97	0.5723	0.6054	0.5723	0.7565
No log	98.0	98	0.5697	0.6007	0.5697	0.7548
No log	99.0	99	0.5681	0.6037	0.5681	0.7537
No log	100.0	100	0.5675	0.6040	0.5675	0.7533

Framework versions

Transformers 4.51.1
Pytorch 2.5.1+cu124
Datasets 3.5.0
Tokenizers 0.21.0

genki10/BERT_V8_sp10_lw40_ex100_lo50_k1_k1_fold0

BERT_V8_sp10_lw40_ex100_lo50_k1_k1_fold0

Model description

Intended uses & limitations

Training and evaluation data

Training procedure

Training hyperparameters

Training results

Framework versions

genki10/
BERT_V8_sp10_lw40_ex100_lo50_k1_k1_fold0