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	3	8.5568	0.0	8.5550	2.9249
No log	2.0	6	6.5800	0.0	6.5787	2.5649
No log	3.0	9	4.3749	0.0076	4.3738	2.0914
No log	4.0	12	3.0292	0.0	3.0279	1.7401
No log	5.0	15	2.0958	0.1576	2.0951	1.4474
No log	6.0	18	1.6572	0.0202	1.6563	1.2870
No log	7.0	21	1.3759	0.0634	1.3756	1.1728
No log	8.0	24	1.1313	0.0488	1.1306	1.0633
No log	9.0	27	1.4789	0.0463	1.4779	1.2157
No log	10.0	30	1.1053	0.1061	1.1046	1.0510
No log	11.0	33	1.4466	0.0623	1.4456	1.2023
No log	12.0	36	0.8963	0.1907	0.8958	0.9464
No log	13.0	39	1.1117	0.1301	1.1109	1.0540
No log	14.0	42	0.8731	0.2912	0.8728	0.9342
No log	15.0	45	0.9381	0.2343	0.9377	0.9683
No log	16.0	48	0.7893	0.3631	0.7891	0.8883
No log	17.0	51	0.8842	0.2353	0.8837	0.9401
No log	18.0	54	0.7447	0.3097	0.7443	0.8628
No log	19.0	57	1.4381	0.0602	1.4369	1.1987
No log	20.0	60	0.7359	0.3431	0.7357	0.8577
No log	21.0	63	0.8016	0.3522	0.8009	0.8950
No log	22.0	66	0.9983	0.2581	0.9972	0.9986
No log	23.0	69	0.9029	0.2619	0.9025	0.9500
No log	24.0	72	1.1850	0.1787	1.1836	1.0879
No log	25.0	75	0.7963	0.3828	0.7958	0.8921
No log	26.0	78	1.0005	0.3463	0.9991	0.9995
No log	27.0	81	0.8820	0.3843	0.8814	0.9388
No log	28.0	84	1.3506	0.1771	1.3491	1.1615
No log	29.0	87	0.9139	0.3968	0.9136	0.9558
No log	30.0	90	1.3869	0.1859	1.3855	1.1771
No log	31.0	93	0.8308	0.4616	0.8304	0.9113
No log	32.0	96	0.9541	0.3727	0.9532	0.9763
No log	33.0	99	0.7363	0.5331	0.7359	0.8579
No log	34.0	102	0.9581	0.3646	0.9574	0.9785
No log	35.0	105	0.8653	0.4341	0.8649	0.9300
No log	36.0	108	1.0735	0.2805	1.0726	1.0357
No log	37.0	111	0.8493	0.4277	0.8488	0.9213
No log	38.0	114	1.1224	0.2804	1.1212	1.0589
No log	39.0	117	0.8647	0.4013	0.8641	0.9296
No log	40.0	120	1.0673	0.2958	1.0662	1.0326
No log	41.0	123	0.9637	0.3388	0.9629	0.9813
No log	42.0	126	1.0672	0.2871	1.0661	1.0325
No log	43.0	129	0.9832	0.3327	0.9822	0.9911
No log	44.0	132	0.8803	0.4294	0.8798	0.9380
No log	45.0	135	1.2422	0.2363	1.2410	1.1140
No log	46.0	138	0.8254	0.4421	0.8251	0.9084
No log	47.0	141	0.8097	0.4671	0.8093	0.8996
No log	48.0	144	1.1045	0.2484	1.1035	1.0505
No log	49.0	147	0.9610	0.3842	0.9608	0.9802
No log	50.0	150	1.2186	0.2284	1.2176	1.1035
No log	51.0	153	0.9843	0.3541	0.9835	0.9917
No log	52.0	156	0.9984	0.3317	0.9974	0.9987
No log	53.0	159	0.8913	0.4182	0.8905	0.9437
No log	54.0	162	1.3527	0.1577	1.3515	1.1626
No log	55.0	165	1.1152	0.2686	1.1145	1.0557
No log	56.0	168	1.0269	0.2945	1.0265	1.0132
No log	57.0	171	1.1644	0.2335	1.1633	1.0786
No log	58.0	174	0.9821	0.3655	0.9812	0.9906
No log	59.0	177	1.0150	0.3536	1.0140	1.0070
No log	60.0	180	1.0328	0.3619	1.0316	1.0157
No log	61.0	183	0.9515	0.3701	0.9507	0.9750
No log	62.0	186	1.1359	0.2473	1.1348	1.0653
No log	63.0	189	1.0437	0.2851	1.0428	1.0212

Framework versions

Transformers 4.47.0
Pytorch 2.5.1+cu121
Datasets 3.3.1
Tokenizers 0.21.0

genki10/BERT_V8_sp20_lw10_ex100_lo00_k3_k3_fold3

BERT_V8_sp20_lw10_ex100_lo00_k3_k3_fold3

Model description

Intended uses & limitations

Training and evaluation data

Training procedure

Training hyperparameters

Training results

Framework versions

genki10/
BERT_V8_sp20_lw10_ex100_lo00_k3_k3_fold3