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	2	8.5805	0.0	8.5787	2.9289
No log	2.0	4	7.3491	0.0	7.3474	2.7106
No log	3.0	6	5.6912	0.0480	5.6899	2.3853
No log	4.0	8	4.4595	0.0161	4.4583	2.1115
No log	5.0	10	3.6397	0.0076	3.6385	1.9075
No log	6.0	12	3.5662	0.0076	3.5655	1.8883
No log	7.0	14	2.4293	0.1168	2.4283	1.5583
No log	8.0	16	2.1952	0.0374	2.1941	1.4813
No log	9.0	18	1.6956	0.0488	1.6947	1.3018
No log	10.0	20	1.4345	0.0831	1.4339	1.1975
No log	11.0	22	1.2492	0.0558	1.2485	1.1174
No log	12.0	24	1.1139	0.0897	1.1134	1.0552
No log	13.0	26	1.0394	0.0932	1.0389	1.0193
No log	14.0	28	1.0879	0.1607	1.0879	1.0430
No log	15.0	30	1.1229	0.1403	1.1224	1.0595
No log	16.0	32	0.9273	0.2731	0.9271	0.9629
No log	17.0	34	1.1289	0.3361	1.1290	1.0625
No log	18.0	36	0.7382	0.3997	0.7383	0.8592
No log	19.0	38	0.8592	0.2780	0.8591	0.9269
No log	20.0	40	0.8176	0.3357	0.8177	0.9043
No log	21.0	42	1.2843	0.2854	1.2843	1.1333
No log	22.0	44	1.1381	0.3644	1.1381	1.0668
No log	23.0	46	0.7642	0.4047	0.7646	0.8744
No log	24.0	48	0.7248	0.4293	0.7252	0.8516
No log	25.0	50	0.9992	0.3877	0.9993	0.9997
No log	26.0	52	0.8854	0.4287	0.8855	0.9410
No log	27.0	54	0.7323	0.3864	0.7328	0.8560
No log	28.0	56	0.7337	0.4095	0.7342	0.8568
No log	29.0	58	0.6681	0.4945	0.6682	0.8175
No log	30.0	60	0.6636	0.4871	0.6638	0.8147
No log	31.0	62	0.7919	0.3955	0.7924	0.8902
No log	32.0	64	0.7116	0.4721	0.7122	0.8439
No log	33.0	66	0.7477	0.5163	0.7481	0.8649
No log	34.0	68	0.7744	0.5208	0.7748	0.8802
No log	35.0	70	0.8088	0.4699	0.8095	0.8997
No log	36.0	72	0.7959	0.5150	0.7966	0.8925
No log	37.0	74	0.7567	0.5228	0.7572	0.8701
No log	38.0	76	0.7342	0.4797	0.7348	0.8572
No log	39.0	78	0.6911	0.5215	0.6915	0.8316
No log	40.0	80	0.6313	0.5538	0.6316	0.7947
No log	41.0	82	0.6781	0.5149	0.6785	0.8237
No log	42.0	84	0.6746	0.5364	0.6751	0.8216
No log	43.0	86	0.6758	0.5696	0.6761	0.8222
No log	44.0	88	0.6935	0.5796	0.6939	0.8330
No log	45.0	90	0.7246	0.5293	0.7253	0.8516
No log	46.0	92	0.7462	0.5372	0.7470	0.8643
No log	47.0	94	0.7749	0.5337	0.7754	0.8806
No log	48.0	96	0.8430	0.5260	0.8435	0.9184
No log	49.0	98	0.7258	0.5529	0.7265	0.8523
No log	50.0	100	0.8456	0.4750	0.8464	0.9200
No log	51.0	102	0.7648	0.5466	0.7654	0.8749
No log	52.0	104	0.6953	0.5583	0.6955	0.8340
No log	53.0	106	0.7044	0.5577	0.7045	0.8394
No log	54.0	108	0.7799	0.5411	0.7801	0.8832
No log	55.0	110	0.9102	0.4712	0.9106	0.9543
No log	56.0	112	0.7775	0.5347	0.7777	0.8819
No log	57.0	114	0.7204	0.5622	0.7205	0.8488
No log	58.0	116	0.7198	0.5598	0.7200	0.8485
No log	59.0	118	0.7865	0.5128	0.7869	0.8871
No log	60.0	120	0.7426	0.5355	0.7429	0.8619
No log	61.0	122	0.7152	0.5736	0.7154	0.8458
No log	62.0	124	0.7152	0.5815	0.7153	0.8457
No log	63.0	126	0.7964	0.5520	0.7966	0.8925
No log	64.0	128	0.8798	0.5030	0.8802	0.9382
No log	65.0	130	0.8938	0.5006	0.8942	0.9456
No log	66.0	132	0.7815	0.5396	0.7817	0.8841
No log	67.0	134	0.7298	0.5851	0.7299	0.8543
No log	68.0	136	0.7173	0.5825	0.7173	0.8469
No log	69.0	138	0.7799	0.5434	0.7800	0.8832
No log	70.0	140	0.8983	0.4915	0.8985	0.9479
No log	71.0	142	0.7909	0.5025	0.7910	0.8894
No log	72.0	144	0.6821	0.5541	0.6822	0.8259
No log	73.0	146	0.6893	0.5586	0.6893	0.8302
No log	74.0	148	0.7454	0.5388	0.7454	0.8634
No log	75.0	150	0.7467	0.5425	0.7468	0.8641
No log	76.0	152	0.7772	0.5203	0.7773	0.8817
No log	77.0	154	0.7995	0.5254	0.7996	0.8942
No log	78.0	156	0.7925	0.5425	0.7925	0.8902
No log	79.0	158	0.7753	0.5559	0.7753	0.8805
No log	80.0	160	0.7819	0.5312	0.7820	0.8843
No log	81.0	162	0.7848	0.5318	0.7850	0.8860
No log	82.0	164	0.7468	0.5268	0.7469	0.8643
No log	83.0	166	0.6848	0.5551	0.6850	0.8276
No log	84.0	168	0.6652	0.5631	0.6653	0.8156
No log	85.0	170	0.6785	0.5552	0.6786	0.8237
No log	86.0	172	0.7209	0.5572	0.7210	0.8491
No log	87.0	174	0.7919	0.5503	0.7921	0.8900
No log	88.0	176	0.8274	0.5432	0.8276	0.9097
No log	89.0	178	0.8619	0.5325	0.8621	0.9285
No log	90.0	180	0.8628	0.5431	0.8631	0.9290
No log	91.0	182	0.8542	0.5446	0.8545	0.9244
No log	92.0	184	0.8579	0.5418	0.8581	0.9264
No log	93.0	186	0.8606	0.5455	0.8608	0.9278
No log	94.0	188	0.8494	0.5452	0.8496	0.9217
No log	95.0	190	0.8475	0.5450	0.8478	0.9207
No log	96.0	192	0.8443	0.5496	0.8445	0.9190
No log	97.0	194	0.8306	0.5501	0.8309	0.9115

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_k1_k1_fold3

BERT_V8_sp20_lw10_ex100_lo00_k1_k1_fold3

Model description

Intended uses & limitations

Training and evaluation data

Training procedure

Training hyperparameters

Training results

Framework versions

genki10/
BERT_V8_sp20_lw10_ex100_lo00_k1_k1_fold3