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	12.1491	0.0010	12.1467	3.4852
No log	2.0	2	9.7884	0.0048	9.7859	3.1282
No log	3.0	3	9.2230	0.0	9.2204	3.0365
No log	4.0	4	8.8147	0.0	8.8122	2.9685
No log	5.0	5	8.3133	0.0	8.3109	2.8829
No log	6.0	6	7.7959	0.0	7.7935	2.7917
No log	7.0	7	7.2923	0.0	7.2900	2.7000
No log	8.0	8	6.8170	0.0	6.8147	2.6105
No log	9.0	9	6.3608	0.0	6.3585	2.5216
No log	10.0	10	5.9163	0.0	5.9141	2.4319
No log	11.0	11	5.4598	0.0113	5.4576	2.3362
No log	12.0	12	4.9784	0.0	4.9763	2.2308
No log	13.0	13	4.4973	0.0	4.4953	2.1202
No log	14.0	14	4.0055	0.0	4.0035	2.0009
No log	15.0	15	3.4052	0.0	3.4033	1.8448
No log	16.0	16	2.8164	0.0	2.8147	1.6777
No log	17.0	17	2.6057	0.0	2.6040	1.6137
No log	18.0	18	2.2329	0.1118	2.2313	1.4937
No log	19.0	19	1.9680	0.0410	1.9664	1.4023
No log	20.0	20	1.7654	0.0340	1.7639	1.3281
No log	21.0	21	1.6316	0.0106	1.6301	1.2768
No log	22.0	22	1.4537	0.0106	1.4522	1.2051
No log	23.0	23	1.3194	0.0106	1.3179	1.1480
No log	24.0	24	1.1608	0.0106	1.1594	1.0768
No log	25.0	25	1.0771	0.0106	1.0758	1.0372
No log	26.0	26	1.0016	0.0	1.0003	1.0001
No log	27.0	27	0.9358	0.0	0.9346	0.9667
No log	28.0	28	0.8939	0.1905	0.8927	0.9448
No log	29.0	29	0.8368	0.2732	0.8356	0.9141
No log	30.0	30	0.7987	0.2829	0.7976	0.8931
No log	31.0	31	0.7426	0.3549	0.7415	0.8611
No log	32.0	32	0.6960	0.4059	0.6950	0.8337
No log	33.0	33	0.6685	0.3960	0.6675	0.8170
No log	34.0	34	0.6128	0.4643	0.6119	0.7822
No log	35.0	35	0.5841	0.4851	0.5831	0.7636
No log	36.0	36	0.5513	0.5046	0.5505	0.7419
No log	37.0	37	0.5333	0.5235	0.5323	0.7296
No log	38.0	38	0.5155	0.5379	0.5145	0.7173
No log	39.0	39	0.5578	0.4960	0.5569	0.7463
No log	40.0	40	0.5203	0.5310	0.5194	0.7207
No log	41.0	41	0.5080	0.5720	0.5070	0.7120
No log	42.0	42	0.5233	0.6013	0.5222	0.7226
No log	43.0	43	0.4735	0.6003	0.4726	0.6875
No log	44.0	44	0.5103	0.5751	0.5096	0.7138
No log	45.0	45	0.4915	0.5954	0.4907	0.7005
No log	46.0	46	0.4864	0.6318	0.4854	0.6967
No log	47.0	47	0.5224	0.6407	0.5212	0.7220
No log	48.0	48	0.4853	0.6673	0.4842	0.6959
No log	49.0	49	0.5567	0.5990	0.5558	0.7455
No log	50.0	50	0.5647	0.5851	0.5638	0.7508
No log	51.0	51	0.5219	0.6319	0.5206	0.7216
No log	52.0	52	0.6237	0.5800	0.6221	0.7887
No log	53.0	53	0.6827	0.5238	0.6809	0.8252
No log	54.0	54	0.6130	0.5713	0.6113	0.7819
No log	55.0	55	0.5789	0.5888	0.5776	0.7600
No log	56.0	56	0.6094	0.5688	0.6082	0.7799
No log	57.0	57	0.6056	0.5728	0.6042	0.7773
No log	58.0	58	0.6092	0.5573	0.6077	0.7795
No log	59.0	59	0.6197	0.5607	0.6180	0.7861
No log	60.0	60	0.5978	0.5750	0.5962	0.7722
No log	61.0	61	0.6033	0.5549	0.6017	0.7757
No log	62.0	62	0.6036	0.5651	0.6020	0.7759
No log	63.0	63	0.5834	0.5853	0.5820	0.7629
No log	64.0	64	0.5803	0.5744	0.5790	0.7609
No log	65.0	65	0.5815	0.5860	0.5802	0.7617
No log	66.0	66	0.5936	0.5890	0.5921	0.7695
No log	67.0	67	0.5917	0.5983	0.5902	0.7683
No log	68.0	68	0.5864	0.6067	0.5851	0.7649
No log	69.0	69	0.5915	0.6103	0.5901	0.7682
No log	70.0	70	0.5992	0.6077	0.5978	0.7731
No log	71.0	71	0.6027	0.5989	0.6013	0.7754
No log	72.0	72	0.6061	0.5970	0.6046	0.7776
No log	73.0	73	0.6066	0.6090	0.6051	0.7779
No log	74.0	74	0.6118	0.6078	0.6103	0.7812
No log	75.0	75	0.6222	0.5788	0.6207	0.7878
No log	76.0	76	0.6342	0.5665	0.6326	0.7954
No log	77.0	77	0.6418	0.5549	0.6402	0.8001
No log	78.0	78	0.6295	0.5757	0.6279	0.7924

Framework versions

Transformers 4.51.1
Pytorch 2.5.1+cu124
Datasets 3.5.0
Tokenizers 0.21.0

genki10/BERT_V8_sp10_lw40_ex50_lo50_k1_k1_fold1

BERT_V8_sp10_lw40_ex50_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_lw40_ex50_lo50_k1_k1_fold1