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	11.6011	0.0016	11.5984	3.4056
No log	2.0	2	10.2314	0.0003	10.2286	3.1982
No log	3.0	3	9.1099	0.0	9.1072	3.0178
No log	4.0	4	8.0940	0.0	8.0915	2.8446
No log	5.0	5	7.0137	0.0	7.0113	2.6479
No log	6.0	6	5.6771	0.0534	5.6747	2.3822
No log	7.0	7	4.8635	0.0087	4.8614	2.2049
No log	8.0	8	4.0322	0.0137	4.0303	2.0076
No log	9.0	9	3.8799	0.0074	3.8776	1.9692
No log	10.0	10	3.3466	0.0	3.3444	1.8288
No log	11.0	11	2.8475	0.0	2.8458	1.6869
No log	12.0	12	2.9091	0.0046	2.9075	1.7052
No log	13.0	13	2.3950	0.0789	2.3934	1.5471
No log	14.0	14	2.0214	0.1223	2.0196	1.4211
No log	15.0	15	1.9162	0.0947	1.9144	1.3836
No log	16.0	16	1.7367	0.0615	1.7350	1.3172
No log	17.0	17	1.5330	0.0340	1.5314	1.2375
No log	18.0	18	1.3839	0.0276	1.3824	1.1757
No log	19.0	19	1.2843	0.0172	1.2830	1.1327
No log	20.0	20	1.1283	0.0	1.1270	1.0616
No log	21.0	21	1.0504	0.0	1.0490	1.0242
No log	22.0	22	1.0043	0.0	1.0028	1.0014
No log	23.0	23	0.9250	0.1316	0.9239	0.9612
No log	24.0	24	0.9443	0.1783	0.9434	0.9713
No log	25.0	25	0.8845	0.2314	0.8836	0.9400
No log	26.0	26	0.8340	0.2149	0.8329	0.9126
No log	27.0	27	0.8584	0.2446	0.8571	0.9258
No log	28.0	28	0.8324	0.2540	0.8312	0.9117
No log	29.0	29	0.7887	0.2499	0.7875	0.8874
No log	30.0	30	0.7384	0.2983	0.7373	0.8587
No log	31.0	31	0.6961	0.3742	0.6950	0.8337
No log	32.0	32	0.6587	0.3887	0.6576	0.8110
No log	33.0	33	0.6314	0.3928	0.6303	0.7939
No log	34.0	34	0.6187	0.3654	0.6178	0.7860
No log	35.0	35	0.6131	0.3693	0.6122	0.7824
No log	36.0	36	0.5887	0.4063	0.5879	0.7668
No log	37.0	37	0.5353	0.4599	0.5346	0.7312
No log	38.0	38	0.4793	0.5344	0.4786	0.6918
No log	39.0	39	0.4762	0.5658	0.4756	0.6896
No log	40.0	40	0.4749	0.5672	0.4744	0.6888
No log	41.0	41	0.4790	0.5809	0.4785	0.6917
No log	42.0	42	0.4968	0.5906	0.4963	0.7045
No log	43.0	43	0.5077	0.5897	0.5072	0.7122
No log	44.0	44	0.5184	0.5882	0.5179	0.7196
No log	45.0	45	0.5233	0.5978	0.5227	0.7230
No log	46.0	46	0.5469	0.6140	0.5464	0.7392
No log	47.0	47	0.5765	0.6214	0.5759	0.7589
No log	48.0	48	0.6200	0.5738	0.6195	0.7871
No log	49.0	49	0.6088	0.5905	0.6082	0.7799
No log	50.0	50	0.5914	0.5946	0.5908	0.7686
No log	51.0	51	0.5535	0.6233	0.5529	0.7436
No log	52.0	52	0.5565	0.6208	0.5559	0.7456
No log	53.0	53	0.5709	0.6085	0.5704	0.7552
No log	54.0	54	0.6093	0.6032	0.6088	0.7803
No log	55.0	55	0.6050	0.5946	0.6046	0.7776
No log	56.0	56	0.5728	0.6039	0.5723	0.7565
No log	57.0	57	0.5653	0.6064	0.5648	0.7515
No log	58.0	58	0.5639	0.6059	0.5633	0.7506
No log	59.0	59	0.5883	0.5910	0.5878	0.7667
No log	60.0	60	0.5922	0.5821	0.5917	0.7692
No log	61.0	61	0.5726	0.6081	0.5721	0.7563
No log	62.0	62	0.5695	0.6034	0.5689	0.7543
No log	63.0	63	0.5790	0.6008	0.5784	0.7605
No log	64.0	64	0.6236	0.5812	0.6232	0.7894
No log	65.0	65	0.6618	0.5609	0.6614	0.8133
No log	66.0	66	0.6524	0.5469	0.6519	0.8074
No log	67.0	67	0.6248	0.5571	0.6243	0.7901
No log	68.0	68	0.6228	0.5562	0.6222	0.7888
No log	69.0	69	0.6281	0.5536	0.6275	0.7921
No log	70.0	70	0.6437	0.5612	0.6432	0.8020
No log	71.0	71	0.6580	0.5439	0.6575	0.8109
No log	72.0	72	0.6700	0.5517	0.6695	0.8182
No log	73.0	73	0.6493	0.5639	0.6489	0.8055
No log	74.0	74	0.6069	0.5798	0.6064	0.7787
No log	75.0	75	0.5894	0.5802	0.5889	0.7674
No log	76.0	76	0.5853	0.5820	0.5848	0.7647
No log	77.0	77	0.5817	0.5918	0.5812	0.7623
No log	78.0	78	0.5869	0.5827	0.5864	0.7658
No log	79.0	79	0.5863	0.5831	0.5858	0.7653
No log	80.0	80	0.5954	0.5828	0.5948	0.7712
No log	81.0	81	0.6200	0.5707	0.6195	0.7871

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_fold1

BERT_V8_sp10_lw20_ex200_lo50_k1_k1_fold1

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_fold1