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	2	7.5569	0.0	7.5549	2.7486
No log	2.0	4	6.4703	0.0	6.4682	2.5433
No log	3.0	6	5.6441	0.0249	5.6419	2.3753
No log	4.0	8	5.0891	0.0	5.0870	2.2554
No log	5.0	10	4.4676	0.0	4.4656	2.1132
No log	6.0	12	4.1538	0.0	4.1519	2.0376
No log	7.0	14	3.7635	0.0	3.7617	1.9395
No log	8.0	16	3.0898	0.0	3.0879	1.7573
No log	9.0	18	2.6029	0.0	2.6011	1.6128
No log	10.0	20	2.2023	0.1817	2.2007	1.4835
No log	11.0	22	1.8525	0.0645	1.8509	1.3605
No log	12.0	24	1.5156	0.0645	1.5142	1.2305
No log	13.0	26	1.2303	0.0418	1.2289	1.1086
No log	14.0	28	1.1340	0.0106	1.1326	1.0642
No log	15.0	30	0.9329	0.0211	0.9316	0.9652
No log	16.0	32	0.8583	0.0780	0.8570	0.9258
No log	17.0	34	0.7236	0.4851	0.7225	0.8500
No log	18.0	36	0.7551	0.3683	0.7540	0.8683
No log	19.0	38	0.7838	0.3429	0.7827	0.8847
No log	20.0	40	0.6540	0.4338	0.6530	0.8081
No log	21.0	42	0.8532	0.4217	0.8523	0.9232
No log	22.0	44	1.5027	0.2433	1.5017	1.2254
No log	23.0	46	1.3250	0.2659	1.3241	1.1507
No log	24.0	48	0.5841	0.5667	0.5833	0.7637
No log	25.0	50	0.6087	0.4488	0.6077	0.7796
No log	26.0	52	0.6014	0.4357	0.6006	0.7750
No log	27.0	54	0.5307	0.5539	0.5300	0.7280
No log	28.0	56	1.3288	0.2973	1.3278	1.1523
No log	29.0	58	1.1949	0.3443	1.1939	1.0927
No log	30.0	60	0.5804	0.5206	0.5796	0.7613
No log	31.0	62	0.5870	0.4845	0.5862	0.7656
No log	32.0	64	0.6277	0.4942	0.6266	0.7916
No log	33.0	66	1.1990	0.3002	1.1974	1.0943
No log	34.0	68	1.8079	0.2246	1.8062	1.3439
No log	35.0	70	1.6054	0.2606	1.6038	1.2664
No log	36.0	72	0.7807	0.4580	0.7795	0.8829
No log	37.0	74	0.6629	0.4161	0.6621	0.8137
No log	38.0	76	0.8126	0.3550	0.8119	0.9011
No log	39.0	78	0.7571	0.3961	0.7566	0.8698
No log	40.0	80	0.6306	0.4896	0.6299	0.7937
No log	41.0	82	0.9763	0.3887	0.9752	0.9875
No log	42.0	84	0.8439	0.4325	0.8429	0.9181
No log	43.0	86	0.5783	0.5664	0.5777	0.7601
No log	44.0	88	0.7021	0.5262	0.7018	0.8377
No log	45.0	90	0.7565	0.4898	0.7562	0.8696
No log	46.0	92	0.6310	0.5732	0.6302	0.7939
No log	47.0	94	0.9990	0.3878	0.9978	0.9989
No log	48.0	96	1.6444	0.2392	1.6429	1.2818
No log	49.0	98	1.8084	0.2323	1.8070	1.3442
No log	50.0	100	1.2496	0.3287	1.2485	1.1173
No log	51.0	102	0.6838	0.5683	0.6830	0.8265
No log	52.0	104	0.7604	0.5060	0.7601	0.8718
No log	53.0	106	0.8448	0.4766	0.8446	0.9190
No log	54.0	108	0.7313	0.4884	0.7310	0.8550
No log	55.0	110	0.6410	0.5495	0.6405	0.8003
No log	56.0	112	0.6801	0.5583	0.6794	0.8242
No log	57.0	114	0.7370	0.4971	0.7362	0.8580
No log	58.0	116	0.6289	0.5819	0.6282	0.7926
No log	59.0	118	0.5580	0.5982	0.5575	0.7467
No log	60.0	120	0.5610	0.6234	0.5606	0.7487
No log	61.0	122	0.5631	0.5996	0.5626	0.7500
No log	62.0	124	0.6004	0.5686	0.5995	0.7743
No log	63.0	126	0.6497	0.5122	0.6487	0.8054
No log	64.0	128	0.5871	0.5884	0.5863	0.7657
No log	65.0	130	0.5973	0.5703	0.5968	0.7725
No log	66.0	132	0.6651	0.5382	0.6646	0.8153
No log	67.0	134	0.6292	0.5455	0.6287	0.7929
No log	68.0	136	0.5798	0.6199	0.5791	0.7610
No log	69.0	138	0.6374	0.5381	0.6364	0.7977
No log	70.0	140	0.7400	0.4652	0.7388	0.8595
No log	71.0	142	0.7526	0.4692	0.7515	0.8669
No log	72.0	144	0.6504	0.5085	0.6494	0.8059
No log	73.0	146	0.5549	0.6268	0.5541	0.7444
No log	74.0	148	0.5854	0.5754	0.5848	0.7647
No log	75.0	150	0.6354	0.5732	0.6350	0.7969
No log	76.0	152	0.6052	0.5898	0.6048	0.7777
No log	77.0	154	0.5556	0.6302	0.5549	0.7449
No log	78.0	156	0.6330	0.5472	0.6321	0.7950
No log	79.0	158	0.7449	0.5176	0.7439	0.8625
No log	80.0	160	0.7420	0.5166	0.7410	0.8608
No log	81.0	162	0.6888	0.5485	0.6878	0.8293
No log	82.0	164	0.6162	0.5633	0.6153	0.7844
No log	83.0	166	0.5638	0.6478	0.5632	0.7505
No log	84.0	168	0.5816	0.6188	0.5811	0.7623
No log	85.0	170	0.6003	0.6118	0.5999	0.7745
No log	86.0	172	0.6141	0.5888	0.6136	0.7833
No log	87.0	174	0.6093	0.6007	0.6088	0.7803
No log	88.0	176	0.5930	0.6303	0.5923	0.7696
No log	89.0	178	0.6065	0.5916	0.6057	0.7783
No log	90.0	180	0.6414	0.5685	0.6405	0.8003
No log	91.0	182	0.6765	0.5308	0.6755	0.8219
No log	92.0	184	0.6912	0.5344	0.6902	0.8308
No log	93.0	186	0.6757	0.5276	0.6747	0.8214
No log	94.0	188	0.6519	0.5395	0.6509	0.8068
No log	95.0	190	0.6358	0.5609	0.6349	0.7968
No log	96.0	192	0.6201	0.5724	0.6192	0.7869
No log	97.0	194	0.6078	0.5847	0.6070	0.7791
No log	98.0	196	0.6000	0.5908	0.5992	0.7741
No log	99.0	198	0.5971	0.5921	0.5963	0.7722
No log	100.0	200	0.5963	0.5935	0.5955	0.7717

Framework versions

Transformers 4.51.1
Pytorch 2.5.1+cu124
Datasets 3.5.0
Tokenizers 0.21.0

genki10/BERT_V8_sp10_lw40_ex30_lo00_k1_k1_fold1

BERT_V8_sp10_lw40_ex30_lo00_k1_k1_fold1

Model description

Intended uses & limitations

Training and evaluation data

Training procedure

Training hyperparameters

Training results

Framework versions

genki10/
BERT_V8_sp10_lw40_ex30_lo00_k1_k1_fold1