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	10.0451	0.0036	10.0451	3.1694
No log	2.0	2	8.8992	0.0	8.8992	2.9831
No log	3.0	3	8.1001	0.0	8.1001	2.8461
No log	4.0	4	7.5752	0.0	7.5752	2.7523
No log	5.0	5	7.0448	0.0	7.0448	2.6542
No log	6.0	6	6.6507	0.0	6.6507	2.5789
No log	7.0	7	6.2201	0.0015	6.2201	2.4940
No log	8.0	8	5.7864	0.0140	5.7864	2.4055
No log	9.0	9	5.3646	0.0115	5.3646	2.3162
No log	10.0	10	4.9334	0.0115	4.9334	2.2211
No log	11.0	11	4.5187	0.0077	4.5187	2.1257
No log	12.0	12	4.1332	0.0039	4.1332	2.0330
No log	13.0	13	3.7312	0.0039	3.7312	1.9316
No log	14.0	14	3.3214	0.0	3.3214	1.8225
No log	15.0	15	2.9389	0.0	2.9389	1.7143
No log	16.0	16	2.5880	0.0046	2.5880	1.6087
No log	17.0	17	2.2729	0.1139	2.2729	1.5076
No log	18.0	18	1.9976	0.0601	1.9976	1.4134
No log	19.0	19	1.7620	0.0316	1.7620	1.3274
No log	20.0	20	1.5796	0.0316	1.5796	1.2568
No log	21.0	21	1.4358	0.0316	1.4358	1.1982
No log	22.0	22	1.2877	0.0316	1.2877	1.1348
No log	23.0	23	1.1570	0.0316	1.1570	1.0757
No log	24.0	24	1.0499	0.0316	1.0499	1.0246
No log	25.0	25	0.9898	0.0382	0.9898	0.9949
No log	26.0	26	0.9255	0.0484	0.9255	0.9620
No log	27.0	27	0.8199	0.2910	0.8199	0.9055
No log	28.0	28	0.7726	0.3774	0.7726	0.8790
No log	29.0	29	0.7534	0.3881	0.7534	0.8680
No log	30.0	30	0.7096	0.4737	0.7096	0.8424
No log	31.0	31	0.6533	0.4744	0.6533	0.8083
No log	32.0	32	0.6832	0.4853	0.6832	0.8266
No log	33.0	33	0.7066	0.4791	0.7066	0.8406
No log	34.0	34	0.6037	0.5109	0.6037	0.7770
No log	35.0	35	0.6546	0.4886	0.6546	0.8091
No log	36.0	36	0.7044	0.4779	0.7044	0.8393
No log	37.0	37	0.5639	0.4989	0.5639	0.7509
No log	38.0	38	0.5706	0.4959	0.5706	0.7554
No log	39.0	39	0.7449	0.4720	0.7449	0.8631
No log	40.0	40	0.6784	0.5019	0.6784	0.8237
No log	41.0	41	0.5449	0.5115	0.5449	0.7382
No log	42.0	42	0.5488	0.5076	0.5488	0.7408
No log	43.0	43	0.6256	0.4779	0.6256	0.7910
No log	44.0	44	0.6414	0.4819	0.6414	0.8009
No log	45.0	45	0.5738	0.4829	0.5738	0.7575
No log	46.0	46	0.5877	0.4878	0.5877	0.7666
No log	47.0	47	0.5942	0.4717	0.5942	0.7709
No log	48.0	48	0.6092	0.4745	0.6092	0.7805
No log	49.0	49	0.6409	0.4931	0.6409	0.8006
No log	50.0	50	0.6471	0.4783	0.6471	0.8044
No log	51.0	51	0.7203	0.4237	0.7203	0.8487
No log	52.0	52	0.7257	0.4415	0.7257	0.8519
No log	53.0	53	0.6785	0.4711	0.6785	0.8237
No log	54.0	54	0.6811	0.4779	0.6811	0.8253
No log	55.0	55	0.6896	0.4763	0.6896	0.8304
No log	56.0	56	0.7368	0.4690	0.7368	0.8584
No log	57.0	57	0.7269	0.4603	0.7269	0.8526
No log	58.0	58	0.6894	0.5077	0.6894	0.8303
No log	59.0	59	0.6862	0.5127	0.6862	0.8284
No log	60.0	60	0.6835	0.5197	0.6835	0.8267
No log	61.0	61	0.6898	0.5090	0.6898	0.8306
No log	62.0	62	0.6733	0.5079	0.6733	0.8205
No log	63.0	63	0.6724	0.5092	0.6724	0.8200
No log	64.0	64	0.6666	0.5116	0.6666	0.8165
No log	65.0	65	0.6512	0.5138	0.6512	0.8070
No log	66.0	66	0.7037	0.4964	0.7037	0.8388
No log	67.0	67	0.7174	0.4910	0.7174	0.8470
No log	68.0	68	0.6762	0.5237	0.6762	0.8223
No log	69.0	69	0.6928	0.5191	0.6928	0.8324
No log	70.0	70	0.7388	0.4853	0.7388	0.8595
No log	71.0	71	0.7211	0.4904	0.7211	0.8492
No log	72.0	72	0.6838	0.5316	0.6838	0.8269
No log	73.0	73	0.7285	0.5096	0.7285	0.8535
No log	74.0	74	0.7734	0.4788	0.7734	0.8795
No log	75.0	75	0.7523	0.4938	0.7523	0.8674
No log	76.0	76	0.6974	0.5237	0.6974	0.8351
No log	77.0	77	0.6945	0.5239	0.6945	0.8334
No log	78.0	78	0.7288	0.4751	0.7288	0.8537
No log	79.0	79	0.7279	0.4763	0.7279	0.8532
No log	80.0	80	0.6972	0.5318	0.6972	0.8350
No log	81.0	81	0.6827	0.5280	0.6827	0.8262
No log	82.0	82	0.7079	0.5122	0.7079	0.8414
No log	83.0	83	0.7196	0.5121	0.7196	0.8483
No log	84.0	84	0.7040	0.5219	0.7040	0.8391
No log	85.0	85	0.6817	0.5204	0.6817	0.8256
No log	86.0	86	0.6879	0.5304	0.6879	0.8294
No log	87.0	87	0.7054	0.5211	0.7054	0.8399
No log	88.0	88	0.7072	0.5204	0.7072	0.8409
No log	89.0	89	0.6959	0.5301	0.6959	0.8342
No log	90.0	90	0.6863	0.5275	0.6863	0.8284
No log	91.0	91	0.6912	0.5109	0.6912	0.8314
No log	92.0	92	0.7119	0.5223	0.7119	0.8437
No log	93.0	93	0.7262	0.5139	0.7262	0.8521
No log	94.0	94	0.7281	0.5139	0.7281	0.8533
No log	95.0	95	0.7210	0.5114	0.7210	0.8491
No log	96.0	96	0.7107	0.5253	0.7107	0.8430
No log	97.0	97	0.7018	0.5211	0.7018	0.8377
No log	98.0	98	0.6968	0.5117	0.6968	0.8347
No log	99.0	99	0.6951	0.5194	0.6951	0.8337
No log	100.0	100	0.6946	0.5201	0.6946	0.8335

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_lo100_k1_k1_fold0

BERT_V8_sp10_lw40_ex50_lo100_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_ex50_lo100_k1_k1_fold0