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	12.0813	-0.0005	12.0815	3.4758
No log	2.0	2	11.2299	-0.0101	11.2299	3.3511
No log	3.0	3	10.5622	-0.0036	10.5621	3.2499
No log	4.0	4	9.6416	0.0	9.6417	3.1051
No log	5.0	5	8.6140	0.0	8.6142	2.9350
No log	6.0	6	7.7467	0.0	7.7470	2.7833
No log	7.0	7	6.8769	0.0	6.8773	2.6225
No log	8.0	8	6.1017	0.0041	6.1021	2.4702
No log	9.0	9	5.5162	0.0302	5.5165	2.3487
No log	10.0	10	5.0181	0.0155	5.0184	2.2402
No log	11.0	11	4.5490	0.0039	4.5493	2.1329
No log	12.0	12	4.1017	0.0	4.1020	2.0253
No log	13.0	13	3.6719	0.0	3.6723	1.9163
No log	14.0	14	3.2678	0.0	3.2682	1.8078
No log	15.0	15	2.9224	0.0	2.9228	1.7096
No log	16.0	16	2.6085	0.0	2.6090	1.6152
No log	17.0	17	2.3091	0.1455	2.3096	1.5197
No log	18.0	18	2.0448	0.0577	2.0452	1.4301
No log	19.0	19	1.8063	0.0422	1.8068	1.3442
No log	20.0	20	1.6224	0.0213	1.6229	1.2739
No log	21.0	21	1.4900	0.0107	1.4905	1.2208
No log	22.0	22	1.3782	0.0107	1.3787	1.1742
No log	23.0	23	1.2490	0.0107	1.2495	1.1178
No log	24.0	24	1.1298	0.0	1.1302	1.0631
No log	25.0	25	1.0240	0.0	1.0244	1.0121
No log	26.0	26	0.9410	0.0	0.9415	0.9703
No log	27.0	27	0.8846	0.0299	0.8851	0.9408
No log	28.0	28	0.8267	0.3850	0.8272	0.9095
No log	29.0	29	0.7775	0.4012	0.7779	0.8820
No log	30.0	30	0.7274	0.4168	0.7278	0.8531
No log	31.0	31	0.6959	0.4268	0.6962	0.8344
No log	32.0	32	0.6548	0.4292	0.6551	0.8094
No log	33.0	33	0.6196	0.4370	0.6198	0.7873
No log	34.0	34	0.5885	0.4557	0.5887	0.7673
No log	35.0	35	0.5504	0.4859	0.5505	0.7419
No log	36.0	36	0.5593	0.5013	0.5594	0.7479
No log	37.0	37	0.5704	0.5064	0.5704	0.7552
No log	38.0	38	0.5372	0.5375	0.5372	0.7329
No log	39.0	39	0.4932	0.5244	0.4930	0.7021
No log	40.0	40	0.5134	0.5471	0.5132	0.7164
No log	41.0	41	0.6521	0.5186	0.6520	0.8075
No log	42.0	42	0.9660	0.4780	0.9662	0.9830
No log	43.0	43	0.9654	0.4737	0.9656	0.9827
No log	44.0	44	0.7057	0.5279	0.7058	0.8401
No log	45.0	45	0.5167	0.5859	0.5165	0.7187
No log	46.0	46	0.5038	0.6026	0.5036	0.7096
No log	47.0	47	0.5093	0.6235	0.5091	0.7135
No log	48.0	48	0.6305	0.5574	0.6306	0.7941
No log	49.0	49	0.7097	0.5317	0.7098	0.8425
No log	50.0	50	0.6417	0.5488	0.6419	0.8012
No log	51.0	51	0.5209	0.5827	0.5209	0.7217
No log	52.0	52	0.5050	0.5518	0.5049	0.7106
No log	53.0	53	0.5248	0.5219	0.5247	0.7244
No log	54.0	54	0.5145	0.5443	0.5145	0.7173
No log	55.0	55	0.5106	0.5856	0.5106	0.7146
No log	56.0	56	0.5672	0.5644	0.5673	0.7532
No log	57.0	57	0.5736	0.5727	0.5737	0.7574
No log	58.0	58	0.5237	0.6247	0.5237	0.7237
No log	59.0	59	0.5179	0.5963	0.5178	0.7196
No log	60.0	60	0.5393	0.6028	0.5392	0.7343
No log	61.0	61	0.5348	0.5848	0.5347	0.7313
No log	62.0	62	0.5662	0.5883	0.5663	0.7525
No log	63.0	63	0.5925	0.5689	0.5927	0.7699
No log	64.0	64	0.5661	0.5815	0.5663	0.7525
No log	65.0	65	0.5413	0.5850	0.5414	0.7358
No log	66.0	66	0.5417	0.5780	0.5417	0.7360
No log	67.0	67	0.5423	0.5924	0.5423	0.7364
No log	68.0	68	0.5305	0.6005	0.5305	0.7283
No log	69.0	69	0.5578	0.6265	0.5580	0.7470
No log	70.0	70	0.5874	0.6117	0.5875	0.7665
No log	71.0	71	0.5754	0.6111	0.5756	0.7587
No log	72.0	72	0.5532	0.6309	0.5532	0.7438
No log	73.0	73	0.5481	0.6148	0.5480	0.7403
No log	74.0	74	0.5554	0.6140	0.5553	0.7452
No log	75.0	75	0.5482	0.6188	0.5481	0.7404
No log	76.0	76	0.5493	0.6305	0.5493	0.7412
No log	77.0	77	0.5887	0.6034	0.5889	0.7674
No log	78.0	78	0.6233	0.5761	0.6236	0.7897
No log	79.0	79	0.6169	0.5725	0.6171	0.7855
No log	80.0	80	0.5800	0.6070	0.5801	0.7617
No log	81.0	81	0.5564	0.5910	0.5565	0.7460
No log	82.0	82	0.5416	0.6256	0.5416	0.7359
No log	83.0	83	0.5409	0.6177	0.5409	0.7355
No log	84.0	84	0.5427	0.6281	0.5427	0.7367
No log	85.0	85	0.5525	0.6009	0.5525	0.7433
No log	86.0	86	0.5847	0.5944	0.5848	0.7647
No log	87.0	87	0.6082	0.5788	0.6084	0.7800
No log	88.0	88	0.6190	0.5655	0.6192	0.7869
No log	89.0	89	0.6136	0.5762	0.6138	0.7834
No log	90.0	90	0.5960	0.5883	0.5961	0.7721
No log	91.0	91	0.5783	0.6022	0.5784	0.7605
No log	92.0	92	0.5650	0.6057	0.5650	0.7517
No log	93.0	93	0.5626	0.6155	0.5626	0.7501
No log	94.0	94	0.5636	0.6202	0.5636	0.7507
No log	95.0	95	0.5660	0.6114	0.5661	0.7524
No log	96.0	96	0.5702	0.5920	0.5702	0.7551
No log	97.0	97	0.5762	0.5899	0.5763	0.7591
No log	98.0	98	0.5834	0.6008	0.5835	0.7639
No log	99.0	99	0.5891	0.6007	0.5892	0.7676
No log	100.0	100	0.5927	0.5980	0.5928	0.7700

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_fold2

BERT_V8_sp10_lw20_ex100_lo100_k1_k1_fold2

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_fold2