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	12.4010	-0.0037	12.4010	3.5215
No log	2.0	2	11.2493	-0.0219	11.2493	3.3540
No log	3.0	3	9.8277	0.0014	9.8277	3.1349
No log	4.0	4	8.7589	0.0018	8.7589	2.9595
No log	5.0	5	7.8818	0.0018	7.8818	2.8075
No log	6.0	6	6.9881	0.0018	6.9881	2.6435
No log	7.0	7	6.2673	0.0018	6.2673	2.5035
No log	8.0	8	5.5928	0.0327	5.5928	2.3649
No log	9.0	9	4.9321	0.0138	4.9321	2.2208
No log	10.0	10	4.3651	0.0118	4.3651	2.0893
No log	11.0	11	3.8373	0.0040	3.8373	1.9589
No log	12.0	12	3.3731	0.0040	3.3731	1.8366
No log	13.0	13	3.0336	0.0040	3.0336	1.7417
No log	14.0	14	2.6637	0.0040	2.6637	1.6321
No log	15.0	15	2.3619	0.1240	2.3619	1.5368
No log	16.0	16	2.1081	0.1135	2.1081	1.4519
No log	17.0	17	1.8970	0.0734	1.8970	1.3773
No log	18.0	18	1.6968	0.0445	1.6968	1.3026
No log	19.0	19	1.5262	0.0445	1.5262	1.2354
No log	20.0	20	1.3746	0.0445	1.3746	1.1724
No log	21.0	21	1.2498	0.0420	1.2498	1.1180
No log	22.0	22	1.1445	0.0316	1.1445	1.0698
No log	23.0	23	1.0524	0.0316	1.0524	1.0258
No log	24.0	24	0.9766	0.0420	0.9766	0.9882
No log	25.0	25	0.9037	0.0420	0.9037	0.9507
No log	26.0	26	0.8385	0.1800	0.8385	0.9157
No log	27.0	27	0.7841	0.3800	0.7841	0.8855
No log	28.0	28	0.7582	0.4291	0.7582	0.8707
No log	29.0	29	0.6947	0.5197	0.6947	0.8335
No log	30.0	30	0.6575	0.4635	0.6575	0.8108
No log	31.0	31	0.6163	0.4862	0.6163	0.7850
No log	32.0	32	0.6305	0.5810	0.6305	0.7940
No log	33.0	33	0.6321	0.5809	0.6321	0.7950
No log	34.0	34	0.5477	0.5531	0.5477	0.7400
No log	35.0	35	0.5483	0.5027	0.5483	0.7405
No log	36.0	36	0.5287	0.5354	0.5287	0.7271
No log	37.0	37	0.5595	0.5992	0.5595	0.7480
No log	38.0	38	0.5619	0.6082	0.5619	0.7496
No log	39.0	39	0.5111	0.5761	0.5111	0.7149
No log	40.0	40	0.5313	0.5053	0.5313	0.7289
No log	41.0	41	0.5294	0.5098	0.5294	0.7276
No log	42.0	42	0.5067	0.5708	0.5067	0.7118
No log	43.0	43	0.5420	0.5775	0.5420	0.7362
No log	44.0	44	0.5406	0.5679	0.5406	0.7353
No log	45.0	45	0.5360	0.5287	0.5360	0.7321
No log	46.0	46	0.5466	0.5119	0.5466	0.7393
No log	47.0	47	0.5415	0.5084	0.5415	0.7358
No log	48.0	48	0.5428	0.5393	0.5428	0.7367
No log	49.0	49	0.5481	0.5595	0.5481	0.7403
No log	50.0	50	0.5324	0.5614	0.5324	0.7297
No log	51.0	51	0.5458	0.5527	0.5458	0.7388
No log	52.0	52	0.5570	0.5666	0.5570	0.7463
No log	53.0	53	0.5434	0.5439	0.5434	0.7371
No log	54.0	54	0.5458	0.5707	0.5458	0.7388
No log	55.0	55	0.5602	0.5685	0.5602	0.7485
No log	56.0	56	0.5690	0.5617	0.5690	0.7543
No log	57.0	57	0.5603	0.5587	0.5603	0.7486
No log	58.0	58	0.5646	0.5670	0.5646	0.7514
No log	59.0	59	0.5409	0.5851	0.5409	0.7354
No log	60.0	60	0.5135	0.6102	0.5135	0.7166
No log	61.0	61	0.5146	0.6181	0.5146	0.7174
No log	62.0	62	0.5281	0.6157	0.5281	0.7267
No log	63.0	63	0.5571	0.5892	0.5571	0.7464
No log	64.0	64	0.5579	0.5626	0.5579	0.7469
No log	65.0	65	0.5784	0.5508	0.5784	0.7605
No log	66.0	66	0.6138	0.5511	0.6138	0.7834
No log	67.0	67	0.6034	0.5593	0.6034	0.7768
No log	68.0	68	0.5828	0.5653	0.5828	0.7634
No log	69.0	69	0.5484	0.5647	0.5484	0.7405
No log	70.0	70	0.5438	0.5889	0.5438	0.7374
No log	71.0	71	0.5400	0.5841	0.5400	0.7348
No log	72.0	72	0.5537	0.5914	0.5537	0.7441
No log	73.0	73	0.5771	0.5864	0.5771	0.7596
No log	74.0	74	0.5688	0.5845	0.5688	0.7542
No log	75.0	75	0.5501	0.5904	0.5501	0.7417
No log	76.0	76	0.5538	0.5796	0.5538	0.7442
No log	77.0	77	0.5597	0.5786	0.5597	0.7481
No log	78.0	78	0.5741	0.5781	0.5741	0.7577
No log	79.0	79	0.5852	0.5637	0.5852	0.7650
No log	80.0	80	0.6118	0.5597	0.6118	0.7822
No log	81.0	81	0.6085	0.5596	0.6085	0.7801
No log	82.0	82	0.5887	0.5580	0.5887	0.7672
No log	83.0	83	0.5761	0.5719	0.5761	0.7590
No log	84.0	84	0.5761	0.5799	0.5761	0.7590
No log	85.0	85	0.5835	0.5710	0.5835	0.7639
No log	86.0	86	0.5988	0.5627	0.5988	0.7738
No log	87.0	87	0.6201	0.5516	0.6201	0.7875
No log	88.0	88	0.6400	0.5487	0.6400	0.8000
No log	89.0	89	0.6405	0.5468	0.6405	0.8003
No log	90.0	90	0.6262	0.5601	0.6262	0.7913
No log	91.0	91	0.6084	0.5641	0.6084	0.7800

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_lo100_k1_k1_fold4

BERT_V8_sp10_lw20_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_lw20_ex100_lo100_k1_k1_fold4