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	11.6213	0.0266	11.6197	3.4088
No log	2.0	2	10.0897	0.0054	10.0882	3.1762
No log	3.0	3	8.6692	0.0	8.6679	2.9441
No log	4.0	4	7.2347	0.0	7.2335	2.6895
No log	5.0	5	6.1814	0.0491	6.1804	2.4860
No log	6.0	6	5.5810	0.0515	5.5800	2.3622
No log	7.0	7	5.0273	0.0334	5.0264	2.2420
No log	8.0	8	4.4081	0.0171	4.4071	2.0993
No log	9.0	9	3.8864	0.0124	3.8854	1.9712
No log	10.0	10	3.4673	0.0	3.4664	1.8618
No log	11.0	11	3.0513	0.0	3.0504	1.7465
No log	12.0	12	2.6871	-0.0011	2.6862	1.6390
No log	13.0	13	2.3812	0.1903	2.3803	1.5428
No log	14.0	14	2.1282	0.1021	2.1274	1.4586
No log	15.0	15	1.9102	0.0528	1.9094	1.3818
No log	16.0	16	1.6614	0.0488	1.6607	1.2887
No log	17.0	17	1.4862	0.0488	1.4856	1.2188
No log	18.0	18	1.3895	0.0488	1.3889	1.1785
No log	19.0	19	1.2304	0.0391	1.2298	1.1089
No log	20.0	20	1.1159	0.0391	1.1153	1.0561
No log	21.0	21	0.9988	0.0329	0.9983	0.9991
No log	22.0	22	0.9203	0.0934	0.9198	0.9590
No log	23.0	23	0.8761	0.3011	0.8757	0.9358
No log	24.0	24	0.8254	0.3721	0.8249	0.9083
No log	25.0	25	0.7666	0.3700	0.7662	0.8754
No log	26.0	26	0.7164	0.3934	0.7160	0.8462
No log	27.0	27	0.7062	0.3507	0.7060	0.8402
No log	28.0	28	0.6883	0.3523	0.6881	0.8295
No log	29.0	29	0.6318	0.3956	0.6317	0.7948
No log	30.0	30	0.6240	0.4628	0.6239	0.7899
No log	31.0	31	0.6048	0.4887	0.6048	0.7777
No log	32.0	32	0.5794	0.4888	0.5795	0.7613
No log	33.0	33	0.5732	0.4872	0.5734	0.7572
No log	34.0	34	0.5692	0.5239	0.5694	0.7546
No log	35.0	35	0.6019	0.5632	0.6020	0.7759
No log	36.0	36	0.6612	0.5416	0.6614	0.8132
No log	37.0	37	0.6548	0.5392	0.6549	0.8093
No log	38.0	38	0.5921	0.5577	0.5922	0.7695
No log	39.0	39	0.5395	0.5885	0.5396	0.7345
No log	40.0	40	0.5416	0.5924	0.5417	0.7360
No log	41.0	41	0.5704	0.5709	0.5704	0.7553
No log	42.0	42	0.6234	0.5609	0.6234	0.7896
No log	43.0	43	0.6071	0.5714	0.6071	0.7791
No log	44.0	44	0.5752	0.5948	0.5752	0.7584
No log	45.0	45	0.6151	0.5860	0.6150	0.7842
No log	46.0	46	0.7539	0.5167	0.7538	0.8682
No log	47.0	47	0.7796	0.5158	0.7795	0.8829
No log	48.0	48	0.6934	0.5545	0.6933	0.8326
No log	49.0	49	0.6427	0.5881	0.6427	0.8017
No log	50.0	50	0.6593	0.5858	0.6592	0.8119
No log	51.0	51	0.6938	0.5558	0.6936	0.8328
No log	52.0	52	0.6639	0.5693	0.6638	0.8147
No log	53.0	53	0.6230	0.5731	0.6229	0.7892
No log	54.0	54	0.6194	0.5775	0.6193	0.7870
No log	55.0	55	0.6612	0.5720	0.6611	0.8131
No log	56.0	56	0.6585	0.5720	0.6585	0.8115
No log	57.0	57	0.6154	0.5680	0.6154	0.7844
No log	58.0	58	0.6110	0.5740	0.6109	0.7816
No log	59.0	59	0.6088	0.5761	0.6087	0.7802
No log	60.0	60	0.6501	0.5587	0.6500	0.8062
No log	61.0	61	0.6491	0.5490	0.6490	0.8056
No log	62.0	62	0.6138	0.5593	0.6137	0.7834
No log	63.0	63	0.5927	0.5892	0.5926	0.7698
No log	64.0	64	0.5985	0.5806	0.5984	0.7736
No log	65.0	65	0.6330	0.5543	0.6329	0.7955
No log	66.0	66	0.7352	0.5206	0.7351	0.8574
No log	67.0	67	0.7811	0.5042	0.7810	0.8837
No log	68.0	68	0.7415	0.5191	0.7414	0.8610
No log	69.0	69	0.6542	0.5556	0.6541	0.8088
No log	70.0	70	0.5884	0.6035	0.5883	0.7670
No log	71.0	71	0.5816	0.6145	0.5815	0.7626
No log	72.0	72	0.5766	0.6107	0.5765	0.7593
No log	73.0	73	0.5752	0.5995	0.5750	0.7583
No log	74.0	74	0.6076	0.5882	0.6075	0.7794
No log	75.0	75	0.6428	0.5517	0.6427	0.8017
No log	76.0	76	0.6449	0.5562	0.6447	0.8030
No log	77.0	77	0.6194	0.5823	0.6193	0.7869
No log	78.0	78	0.5846	0.5854	0.5844	0.7645
No log	79.0	79	0.5730	0.6030	0.5729	0.7569
No log	80.0	80	0.5734	0.6023	0.5732	0.7571
No log	81.0	81	0.5851	0.5961	0.5850	0.7648
No log	82.0	82	0.6012	0.5867	0.6010	0.7753
No log	83.0	83	0.6030	0.5920	0.6028	0.7764
No log	84.0	84	0.5931	0.5982	0.5930	0.7700
No log	85.0	85	0.5810	0.6097	0.5808	0.7621
No log	86.0	86	0.5776	0.6100	0.5774	0.7599
No log	87.0	87	0.5793	0.6100	0.5791	0.7610
No log	88.0	88	0.5829	0.6082	0.5828	0.7634
No log	89.0	89	0.5852	0.6097	0.5851	0.7649
No log	90.0	90	0.5928	0.5940	0.5927	0.7698
No log	91.0	91	0.5995	0.5936	0.5994	0.7742
No log	92.0	92	0.5995	0.5916	0.5994	0.7742
No log	93.0	93	0.6029	0.5882	0.6028	0.7764
No log	94.0	94	0.6034	0.5780	0.6032	0.7767
No log	95.0	95	0.6001	0.5818	0.6000	0.7746
No log	96.0	96	0.5943	0.5789	0.5941	0.7708
No log	97.0	97	0.5924	0.5782	0.5922	0.7696
No log	98.0	98	0.5894	0.5843	0.5892	0.7676
No log	99.0	99	0.5870	0.5897	0.5869	0.7661
No log	100.0	100	0.5855	0.5971	0.5853	0.7651

Framework versions

Transformers 4.47.0
Pytorch 2.5.1+cu121
Datasets 3.3.1
Tokenizers 0.21.0

genki10/BERT_V8_sp10_lw20_ex200_lo50_k1_k1_fold3

BERT_V8_sp10_lw20_ex200_lo50_k1_k1_fold3

Model description

Intended uses & limitations

Training and evaluation data

Training procedure

Training hyperparameters

Training results

Framework versions

genki10/
BERT_V8_sp10_lw20_ex200_lo50_k1_k1_fold3