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	1	12.7400	0.0032	12.7371	3.5689
No log	2.0	2	9.0310	-0.0002	9.0279	3.0047
No log	3.0	3	7.6487	0.0	7.6461	2.7652
No log	4.0	4	6.6611	0.0	6.6586	2.5804
No log	5.0	5	6.1398	-0.0059	6.1373	2.4774
No log	6.0	6	5.5949	0.0072	5.5925	2.3648
No log	7.0	7	4.9400	0.0069	4.9378	2.2221
No log	8.0	8	4.3698	0.0	4.3676	2.0899
No log	9.0	9	3.8290	0.0	3.8269	1.9562
No log	10.0	10	3.4093	0.0	3.4074	1.8459
No log	11.0	11	3.1985	0.0	3.1966	1.7879
No log	12.0	12	2.9736	0.0	2.9718	1.7239
No log	13.0	13	2.5464	0.0034	2.5446	1.5952
No log	14.0	14	2.3187	0.1405	2.3169	1.5221
No log	15.0	15	2.0979	0.1592	2.0962	1.4478
No log	16.0	16	1.8467	0.0936	1.8450	1.3583
No log	17.0	17	1.8237	-0.0279	1.8222	1.3499
No log	18.0	18	1.6538	-0.0163	1.6524	1.2854
No log	19.0	19	1.4210	0.0106	1.4195	1.1914
No log	20.0	20	1.3093	0.0106	1.3079	1.1436
No log	21.0	21	1.1810	0.0106	1.1796	1.0861
No log	22.0	22	1.1352	0.0	1.1339	1.0648
No log	23.0	23	1.0584	0.0	1.0572	1.0282
No log	24.0	24	0.9915	0.0	0.9904	0.9952
No log	25.0	25	0.8714	0.1918	0.8702	0.9329
No log	26.0	26	0.8374	0.3013	0.8362	0.9144
No log	27.0	27	0.7888	0.4210	0.7876	0.8875
No log	28.0	28	0.7559	0.3981	0.7548	0.8688
No log	29.0	29	0.7768	0.2875	0.7758	0.8808
No log	30.0	30	0.7035	0.3554	0.7026	0.8382
No log	31.0	31	0.6340	0.4522	0.6330	0.7956
No log	32.0	32	0.6064	0.4944	0.6054	0.7781
No log	33.0	33	0.5710	0.4996	0.5701	0.7550
No log	34.0	34	0.5550	0.4935	0.5541	0.7444
No log	35.0	35	0.5347	0.4916	0.5339	0.7307
No log	36.0	36	0.5307	0.5102	0.5300	0.7280
No log	37.0	37	0.4837	0.5417	0.4830	0.6949
No log	38.0	38	0.4746	0.5532	0.4738	0.6883
No log	39.0	39	0.4660	0.5512	0.4652	0.6821
No log	40.0	40	0.4976	0.5363	0.4969	0.7049
No log	41.0	41	0.4766	0.5358	0.4759	0.6899
No log	42.0	42	0.4626	0.6074	0.4618	0.6796
No log	43.0	43	0.4692	0.6315	0.4684	0.6844
No log	44.0	44	0.4583	0.6206	0.4576	0.6764
No log	45.0	45	0.5266	0.6387	0.5259	0.7252
No log	46.0	46	0.5539	0.6278	0.5532	0.7438
No log	47.0	47	0.4953	0.6596	0.4946	0.7033
No log	48.0	48	0.4717	0.6349	0.4709	0.6862
No log	49.0	49	0.4902	0.6320	0.4893	0.6995
No log	50.0	50	0.4692	0.6468	0.4684	0.6844
No log	51.0	51	0.4861	0.6483	0.4853	0.6967
No log	52.0	52	0.5312	0.6295	0.5304	0.7283
No log	53.0	53	0.5081	0.6295	0.5074	0.7123
No log	54.0	54	0.4874	0.6240	0.4866	0.6976
No log	55.0	55	0.4608	0.6378	0.4600	0.6783
No log	56.0	56	0.4611	0.6599	0.4603	0.6785
No log	57.0	57	0.4626	0.6475	0.4619	0.6796
No log	58.0	58	0.4805	0.6592	0.4799	0.6927
No log	59.0	59	0.5041	0.6393	0.5035	0.7096
No log	60.0	60	0.4896	0.6461	0.4889	0.6992
No log	61.0	61	0.4903	0.6259	0.4896	0.6997
No log	62.0	62	0.5138	0.6177	0.5131	0.7163
No log	63.0	63	0.5318	0.5992	0.5311	0.7288
No log	64.0	64	0.5652	0.5944	0.5645	0.7514
No log	65.0	65	0.5388	0.5985	0.5381	0.7336
No log	66.0	66	0.4954	0.6187	0.4947	0.7033
No log	67.0	67	0.4822	0.6242	0.4814	0.6938
No log	68.0	68	0.4872	0.6240	0.4864	0.6975
No log	69.0	69	0.5288	0.6197	0.5282	0.7268
No log	70.0	70	0.5447	0.6052	0.5441	0.7376
No log	71.0	71	0.5766	0.5768	0.5760	0.7590
No log	72.0	72	0.5568	0.6052	0.5562	0.7458
No log	73.0	73	0.5098	0.6287	0.5091	0.7135
No log	74.0	74	0.4897	0.6426	0.4890	0.6993
No log	75.0	75	0.4885	0.6434	0.4878	0.6984
No log	76.0	76	0.5008	0.6220	0.5001	0.7072
No log	77.0	77	0.5330	0.6170	0.5324	0.7296
No log	78.0	78	0.5440	0.5971	0.5434	0.7372
No log	79.0	79	0.5313	0.5943	0.5307	0.7285
No log	80.0	80	0.5078	0.6033	0.5071	0.7121
No log	81.0	81	0.5039	0.6039	0.5032	0.7094
No log	82.0	82	0.5060	0.5860	0.5052	0.7108
No log	83.0	83	0.5096	0.5806	0.5089	0.7134
No log	84.0	84	0.5268	0.5874	0.5261	0.7253
No log	85.0	85	0.5553	0.5964	0.5547	0.7448
No log	86.0	86	0.6019	0.5781	0.6013	0.7755

Framework versions

Transformers 4.47.0
Pytorch 2.5.1+cu121
Datasets 3.3.1
Tokenizers 0.21.0

genki10/BERT_V8_sp10_lw20_ex100_lo50_k1_k1_fold1

BERT_V8_sp10_lw20_ex100_lo50_k1_k1_fold1

Model description

Intended uses & limitations

Training and evaluation data

Training procedure

Training hyperparameters

Training results

Framework versions

genki10/
BERT_V8_sp10_lw20_ex100_lo50_k1_k1_fold1