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	10.8868	0.0088	10.8871	3.2996
No log	2.0	2	9.1870	-0.0010	9.1872	3.0310
No log	3.0	3	7.9911	0.0	7.9913	2.8269
No log	4.0	4	7.1495	0.0	7.1497	2.6739
No log	5.0	5	6.5867	0.0	6.5869	2.5665
No log	6.0	6	6.1051	0.0	6.1054	2.4709
No log	7.0	7	5.6101	0.0	5.6104	2.3686
No log	8.0	8	5.0855	0.0	5.0858	2.2552
No log	9.0	9	4.5443	0.0	4.5446	2.1318
No log	10.0	10	4.0319	0.0	4.0323	2.0081
No log	11.0	11	3.5964	0.0	3.5967	1.8965
No log	12.0	12	3.2138	0.0	3.2142	1.7928
No log	13.0	13	2.8737	0.0	2.8741	1.6953
No log	14.0	14	2.6066	0.0	2.6071	1.6146
No log	15.0	15	2.3156	0.1046	2.3160	1.5219
No log	16.0	16	2.0373	0.0640	2.0378	1.4275
No log	17.0	17	1.8263	0.0449	1.8268	1.3516
No log	18.0	18	1.6361	0.0213	1.6365	1.2793
No log	19.0	19	1.4813	0.0213	1.4817	1.2173
No log	20.0	20	1.3407	0.0213	1.3411	1.1580
No log	21.0	21	1.2247	0.0280	1.2251	1.1068
No log	22.0	22	1.1189	0.0213	1.1193	1.0580
No log	23.0	23	1.0216	0.0280	1.0219	1.0109
No log	24.0	24	0.9350	0.0345	0.9353	0.9671
No log	25.0	25	0.8531	0.0345	0.8534	0.9238
No log	26.0	26	0.7806	0.3613	0.7808	0.8836
No log	27.0	27	0.7417	0.4375	0.7419	0.8614
No log	28.0	28	0.6817	0.4960	0.6819	0.8258
No log	29.0	29	0.7337	0.4857	0.7339	0.8567
No log	30.0	30	0.6550	0.4995	0.6551	0.8094
No log	31.0	31	0.5873	0.5043	0.5873	0.7663
No log	32.0	32	0.5667	0.5062	0.5667	0.7528
No log	33.0	33	0.5292	0.5300	0.5292	0.7274
No log	34.0	34	0.6140	0.5388	0.6141	0.7836
No log	35.0	35	0.5906	0.5325	0.5907	0.7686
No log	36.0	36	0.4941	0.5633	0.4940	0.7029
No log	37.0	37	0.5636	0.4593	0.5635	0.7506
No log	38.0	38	0.6044	0.4175	0.6042	0.7773
No log	39.0	39	0.5527	0.4651	0.5525	0.7433
No log	40.0	40	0.4717	0.5678	0.4715	0.6867
No log	41.0	41	0.5844	0.5502	0.5845	0.7645
No log	42.0	42	0.7303	0.5268	0.7306	0.8547
No log	43.0	43	0.6679	0.5490	0.6681	0.8174
No log	44.0	44	0.5086	0.5724	0.5086	0.7132
No log	45.0	45	0.4689	0.5591	0.4686	0.6846
No log	46.0	46	0.5584	0.4678	0.5581	0.7471
No log	47.0	47	0.5886	0.4347	0.5884	0.7671
No log	48.0	48	0.5510	0.4462	0.5509	0.7422
No log	49.0	49	0.5023	0.5293	0.5023	0.7087
No log	50.0	50	0.5104	0.5654	0.5104	0.7145
No log	51.0	51	0.5664	0.5404	0.5666	0.7527
No log	52.0	52	0.5764	0.5445	0.5766	0.7593
No log	53.0	53	0.5253	0.5465	0.5254	0.7249
No log	54.0	54	0.4565	0.5654	0.4565	0.6757
No log	55.0	55	0.4390	0.5534	0.4389	0.6625
No log	56.0	56	0.4400	0.5587	0.4399	0.6633
No log	57.0	57	0.4356	0.5786	0.4355	0.6600
No log	58.0	58	0.4521	0.5659	0.4521	0.6724
No log	59.0	59	0.5077	0.5519	0.5078	0.7126
No log	60.0	60	0.5598	0.5480	0.5599	0.7483
No log	61.0	61	0.5724	0.5358	0.5725	0.7567
No log	62.0	62	0.5519	0.5256	0.5520	0.7430
No log	63.0	63	0.5050	0.5444	0.5050	0.7106
No log	64.0	64	0.5035	0.5326	0.5035	0.7096
No log	65.0	65	0.5394	0.5045	0.5394	0.7344
No log	66.0	66	0.5824	0.4889	0.5823	0.7631
No log	67.0	67	0.5741	0.4850	0.5739	0.7576
No log	68.0	68	0.5478	0.5246	0.5477	0.7400
No log	69.0	69	0.5625	0.5169	0.5623	0.7498
No log	70.0	70	0.5512	0.5375	0.5510	0.7423
No log	71.0	71	0.5428	0.5679	0.5426	0.7366
No log	72.0	72	0.5684	0.5323	0.5682	0.7538
No log	73.0	73	0.5659	0.5419	0.5657	0.7521
No log	74.0	74	0.5477	0.5438	0.5475	0.7399
No log	75.0	75	0.5336	0.5834	0.5334	0.7303
No log	76.0	76	0.5311	0.5804	0.5309	0.7286
No log	77.0	77	0.5552	0.5594	0.5550	0.7450
No log	78.0	78	0.5489	0.5717	0.5487	0.7408
No log	79.0	79	0.5427	0.5737	0.5426	0.7366
No log	80.0	80	0.5290	0.5849	0.5289	0.7272
No log	81.0	81	0.5301	0.5780	0.5300	0.7280
No log	82.0	82	0.5542	0.5674	0.5541	0.7444
No log	83.0	83	0.6098	0.5176	0.6097	0.7808
No log	84.0	84	0.6492	0.4897	0.6491	0.8056
No log	85.0	85	0.6466	0.4850	0.6465	0.8040
No log	86.0	86	0.6102	0.5172	0.6101	0.7811
No log	87.0	87	0.5957	0.5291	0.5956	0.7717
No log	88.0	88	0.5671	0.5517	0.5669	0.7529
No log	89.0	89	0.5605	0.5619	0.5604	0.7486
No log	90.0	90	0.5593	0.5595	0.5592	0.7478
No log	91.0	91	0.5508	0.5650	0.5507	0.7421
No log	92.0	92	0.5512	0.5627	0.5511	0.7424
No log	93.0	93	0.5505	0.5643	0.5503	0.7418
No log	94.0	94	0.5473	0.5634	0.5472	0.7397
No log	95.0	95	0.5478	0.5615	0.5477	0.7401
No log	96.0	96	0.5536	0.5527	0.5535	0.7440
No log	97.0	97	0.5612	0.5424	0.5611	0.7491
No log	98.0	98	0.5670	0.5408	0.5669	0.7529
No log	99.0	99	0.5733	0.5471	0.5732	0.7571
No log	100.0	100	0.5749	0.5502	0.5748	0.7581

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_lo50_k1_k1_fold2

BERT_V8_sp10_lw40_ex100_lo50_k1_k1_fold2

Model description

Intended uses & limitations

Training and evaluation data

Training procedure

Training hyperparameters

Training results

Framework versions

genki10/
BERT_V8_sp10_lw40_ex100_lo50_k1_k1_fold2