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	12.2586	-0.0044	12.2586	3.5012
No log	2.0	2	11.2152	-0.0232	11.2152	3.3489
No log	3.0	3	9.9296	-0.0001	9.9296	3.1511
No log	4.0	4	8.8401	0.0018	8.8401	2.9732
No log	5.0	5	7.9490	0.0018	7.9490	2.8194
No log	6.0	6	7.1076	0.0018	7.1076	2.6660
No log	7.0	7	6.4151	0.0018	6.4151	2.5328
No log	8.0	8	5.7251	0.0331	5.7251	2.3927
No log	9.0	9	4.9777	0.0128	4.9777	2.2311
No log	10.0	10	4.4202	0.0118	4.4202	2.1024
No log	11.0	11	3.9009	0.0040	3.9009	1.9751
No log	12.0	12	3.4894	0.0040	3.4894	1.8680
No log	13.0	13	3.2435	0.0040	3.2435	1.8010
No log	14.0	14	2.7536	0.0040	2.7536	1.6594
No log	15.0	15	2.4098	0.0817	2.4098	1.5524
No log	16.0	16	2.1872	0.1737	2.1872	1.4789
No log	17.0	17	1.9374	0.0533	1.9374	1.3919
No log	18.0	18	1.8313	0.0470	1.8313	1.3533
No log	19.0	19	1.6883	0.0316	1.6883	1.2993
No log	20.0	20	1.4718	0.0212	1.4718	1.2132
No log	21.0	21	1.3348	0.0316	1.3348	1.1553
No log	22.0	22	1.2586	0.0316	1.2586	1.1219
No log	23.0	23	1.1435	0.0316	1.1435	1.0693
No log	24.0	24	1.0400	0.0316	1.0400	1.0198
No log	25.0	25	0.9711	0.0316	0.9711	0.9855
No log	26.0	26	0.8977	0.0316	0.8977	0.9475
No log	27.0	27	0.8350	0.1900	0.8350	0.9138
No log	28.0	28	0.8352	0.2469	0.8352	0.9139
No log	29.0	29	0.7911	0.3490	0.7911	0.8895
No log	30.0	30	0.6920	0.5126	0.6920	0.8319
No log	31.0	31	0.6548	0.4853	0.6548	0.8092
No log	32.0	32	0.6254	0.5262	0.6254	0.7908
No log	33.0	33	0.6797	0.5505	0.6797	0.8244
No log	34.0	34	0.7301	0.5113	0.7301	0.8544
No log	35.0	35	0.6555	0.5875	0.6555	0.8097
No log	36.0	36	0.5606	0.5580	0.5606	0.7487
No log	37.0	37	0.5550	0.5617	0.5550	0.7450
No log	38.0	38	0.6133	0.5809	0.6133	0.7831
No log	39.0	39	0.6506	0.5687	0.6506	0.8066
No log	40.0	40	0.5972	0.5790	0.5972	0.7728
No log	41.0	41	0.5412	0.5819	0.5412	0.7357
No log	42.0	42	0.5362	0.5789	0.5362	0.7323
No log	43.0	43	0.5810	0.5777	0.5810	0.7623
No log	44.0	44	0.5875	0.5901	0.5875	0.7665
No log	45.0	45	0.5354	0.5723	0.5354	0.7317
No log	46.0	46	0.5247	0.5430	0.5247	0.7243
No log	47.0	47	0.5329	0.5555	0.5329	0.7300
No log	48.0	48	0.5487	0.5462	0.5487	0.7408
No log	49.0	49	0.5828	0.5254	0.5828	0.7634
No log	50.0	50	0.5609	0.5278	0.5609	0.7489
No log	51.0	51	0.5600	0.5518	0.5600	0.7483
No log	52.0	52	0.5875	0.5428	0.5875	0.7665
No log	53.0	53	0.5802	0.5584	0.5802	0.7617
No log	54.0	54	0.6102	0.5763	0.6102	0.7811
No log	55.0	55	0.6032	0.5995	0.6032	0.7766
No log	56.0	56	0.6416	0.5835	0.6416	0.8010
No log	57.0	57	0.6322	0.5879	0.6322	0.7951
No log	58.0	58	0.6316	0.5817	0.6316	0.7948
No log	59.0	59	0.6561	0.5849	0.6561	0.8100
No log	60.0	60	0.6107	0.5956	0.6107	0.7815
No log	61.0	61	0.5881	0.6059	0.5881	0.7668
No log	62.0	62	0.5598	0.6078	0.5598	0.7482
No log	63.0	63	0.5635	0.6007	0.5635	0.7507
No log	64.0	64	0.5971	0.6021	0.5971	0.7727
No log	65.0	65	0.5933	0.5986	0.5933	0.7703
No log	66.0	66	0.5663	0.5736	0.5663	0.7525
No log	67.0	67	0.5681	0.5765	0.5681	0.7538
No log	68.0	68	0.5843	0.5925	0.5843	0.7644
No log	69.0	69	0.5991	0.5972	0.5991	0.7740
No log	70.0	70	0.5868	0.5768	0.5868	0.7660
No log	71.0	71	0.5956	0.5864	0.5956	0.7718
No log	72.0	72	0.5894	0.5763	0.5894	0.7677
No log	73.0	73	0.6004	0.5845	0.6004	0.7749
No log	74.0	74	0.6303	0.5887	0.6303	0.7939
No log	75.0	75	0.6360	0.5804	0.6360	0.7975
No log	76.0	76	0.6209	0.5800	0.6209	0.7879
No log	77.0	77	0.5915	0.5816	0.5915	0.7691
No log	78.0	78	0.5784	0.5640	0.5784	0.7605
No log	79.0	79	0.5787	0.5547	0.5787	0.7607
No log	80.0	80	0.5781	0.5601	0.5781	0.7603
No log	81.0	81	0.5879	0.5618	0.5879	0.7667
No log	82.0	82	0.6271	0.5700	0.6271	0.7919
No log	83.0	83	0.6534	0.5693	0.6534	0.8083
No log	84.0	84	0.6534	0.5724	0.6534	0.8083
No log	85.0	85	0.6322	0.5708	0.6322	0.7951
No log	86.0	86	0.6058	0.5776	0.6058	0.7783
No log	87.0	87	0.5885	0.5562	0.5885	0.7671
No log	88.0	88	0.5887	0.5495	0.5887	0.7673
No log	89.0	89	0.5901	0.5521	0.5901	0.7682
No log	90.0	90	0.5889	0.5547	0.5889	0.7674
No log	91.0	91	0.5882	0.5539	0.5882	0.7669
No log	92.0	92	0.5911	0.5629	0.5911	0.7688

Framework versions

Transformers 4.51.1
Pytorch 2.5.1+cu124
Datasets 3.5.0
Tokenizers 0.21.0

genki10/BERT_V8_sp10_lw40_ex100_lo100_k1_k1_fold4

BERT_V8_sp10_lw40_ex100_lo100_k1_k1_fold4

Model description

Intended uses & limitations

Training and evaluation data

Training procedure

Training hyperparameters

Training results

Framework versions

genki10/
BERT_V8_sp10_lw40_ex100_lo100_k1_k1_fold4