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	8.1486	0.0	8.1486	2.8546
No log	2.0	6	7.0378	0.0	7.0378	2.6529
No log	3.0	9	5.8096	0.0143	5.8096	2.4103
No log	4.0	12	4.6246	0.0039	4.6246	2.1505
No log	5.0	15	3.5618	0.0	3.5618	1.8873
No log	6.0	18	2.5016	0.0697	2.5016	1.5816
No log	7.0	21	1.6926	0.0316	1.6926	1.3010
No log	8.0	24	1.2430	0.0316	1.2430	1.1149
No log	9.0	27	1.2680	0.0382	1.2680	1.1260
No log	10.0	30	0.9008	0.0696	0.9008	0.9491
No log	11.0	33	1.0559	0.0771	1.0559	1.0276
No log	12.0	36	1.0765	0.1247	1.0765	1.0375
No log	13.0	39	0.7794	0.4331	0.7794	0.8828
No log	14.0	42	1.6132	0.1869	1.6132	1.2701
No log	15.0	45	1.1586	0.2545	1.1586	1.0764
No log	16.0	48	0.6809	0.4517	0.6809	0.8252
No log	17.0	51	0.9968	0.3353	0.9968	0.9984
No log	18.0	54	0.6128	0.3811	0.6128	0.7828
No log	19.0	57	1.1462	0.2970	1.1462	1.0706
No log	20.0	60	0.9797	0.3227	0.9797	0.9898
No log	21.0	63	0.6444	0.3911	0.6444	0.8027
No log	22.0	66	1.2089	0.2524	1.2089	1.0995
No log	23.0	69	0.7659	0.3676	0.7659	0.8751
No log	24.0	72	0.7441	0.3938	0.7441	0.8626
No log	25.0	75	1.0442	0.3130	1.0442	1.0219
No log	26.0	78	0.8293	0.3930	0.8293	0.9106
No log	27.0	81	1.1414	0.2589	1.1414	1.0684
No log	28.0	84	0.7861	0.3600	0.7861	0.8866
No log	29.0	87	1.0653	0.2746	1.0653	1.0321
No log	30.0	90	0.9975	0.3187	0.9975	0.9988
No log	31.0	93	1.8111	0.1825	1.8111	1.3458
No log	32.0	96	1.2631	0.2392	1.2631	1.1239
No log	33.0	99	0.6856	0.4869	0.6856	0.8280
No log	34.0	102	0.9124	0.4005	0.9124	0.9552
No log	35.0	105	1.2030	0.2612	1.2030	1.0968
No log	36.0	108	0.8839	0.3469	0.8839	0.9402
No log	37.0	111	1.2700	0.2333	1.2700	1.1269
No log	38.0	114	1.1038	0.2885	1.1038	1.0506
No log	39.0	117	1.1927	0.2731	1.1927	1.0921
No log	40.0	120	0.8404	0.4150	0.8404	0.9167
No log	41.0	123	1.3378	0.2417	1.3378	1.1566
No log	42.0	126	1.2578	0.2482	1.2578	1.1215
No log	43.0	129	0.8350	0.3794	0.8350	0.9138
No log	44.0	132	1.2477	0.2589	1.2477	1.1170
No log	45.0	135	1.1937	0.2881	1.1937	1.0926
No log	46.0	138	0.7877	0.4127	0.7877	0.8875
No log	47.0	141	0.9220	0.3687	0.9220	0.9602
No log	48.0	144	1.3375	0.2432	1.3375	1.1565
No log	49.0	147	0.9237	0.3632	0.9237	0.9611
No log	50.0	150	0.7863	0.3617	0.7863	0.8867
No log	51.0	153	1.2297	0.2277	1.2297	1.1089
No log	52.0	156	1.3158	0.2117	1.3158	1.1471
No log	53.0	159	0.7836	0.3770	0.7836	0.8852
No log	54.0	162	0.7269	0.4388	0.7269	0.8526
No log	55.0	165	1.0464	0.3099	1.0464	1.0229
No log	56.0	168	1.2653	0.2310	1.2653	1.1249
No log	57.0	171	0.9551	0.3506	0.9551	0.9773
No log	58.0	174	1.0240	0.3341	1.0240	1.0119
No log	59.0	177	1.0147	0.3358	1.0147	1.0073
No log	60.0	180	0.9984	0.3321	0.9984	0.9992
No log	61.0	183	1.2169	0.2744	1.2169	1.1031
No log	62.0	186	1.1927	0.2734	1.1927	1.0921
No log	63.0	189	0.9334	0.3547	0.9334	0.9661

Framework versions

Transformers 4.47.0
Pytorch 2.5.1+cu121
Datasets 3.3.1
Tokenizers 0.21.0

genki10/BERT_V8_sp20_lw10_ex30_lo00_k3_k3_fold0

BERT_V8_sp20_lw10_ex30_lo00_k3_k3_fold0

Model description

Intended uses & limitations

Training and evaluation data

Training procedure

Training hyperparameters

Training results

Framework versions

genki10/
BERT_V8_sp20_lw10_ex30_lo00_k3_k3_fold0