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	11.7038	0.0112	11.7020	3.4208
No log	2.0	6	8.7591	0.0	8.7575	2.9593
No log	3.0	9	5.4715	0.0248	5.4705	2.3389
No log	4.0	12	3.7999	0.0151	3.7991	1.9491
No log	5.0	15	2.9884	0.0061	2.9876	1.7285
No log	6.0	18	2.0642	0.0613	2.0634	1.4365
No log	7.0	21	1.3526	0.0401	1.3521	1.1628
No log	8.0	24	0.8934	0.2405	0.8931	0.9451
No log	9.0	27	0.7509	0.3477	0.7508	0.8665
No log	10.0	30	0.7424	0.2121	0.7423	0.8616
No log	11.0	33	0.6219	0.3929	0.6216	0.7884
No log	12.0	36	0.7143	0.2966	0.7144	0.8452
No log	13.0	39	0.6505	0.3888	0.6506	0.8066
No log	14.0	42	0.8685	0.3838	0.8683	0.9318
No log	15.0	45	1.0012	0.3658	1.0010	1.0005
No log	16.0	48	0.5241	0.5841	0.5241	0.7239
No log	17.0	51	0.4875	0.5226	0.4875	0.6982
No log	18.0	54	0.5083	0.6021	0.5082	0.7129
No log	19.0	57	0.5328	0.6372	0.5326	0.7298
No log	20.0	60	0.5713	0.6122	0.5712	0.7558
No log	21.0	63	0.4961	0.6657	0.4960	0.7042
No log	22.0	66	0.5191	0.6394	0.5189	0.7203
No log	23.0	69	0.5166	0.6602	0.5164	0.7186
No log	24.0	72	0.5400	0.6621	0.5397	0.7347
No log	25.0	75	0.5496	0.6425	0.5491	0.7410
No log	26.0	78	0.5223	0.6610	0.5219	0.7224
No log	27.0	81	0.5601	0.6238	0.5599	0.7482
No log	28.0	84	0.4831	0.6289	0.4830	0.6950
No log	29.0	87	0.6384	0.5928	0.6382	0.7988
No log	30.0	90	0.4759	0.6470	0.4757	0.6897
No log	31.0	93	0.5292	0.6542	0.5289	0.7273
No log	32.0	96	0.5525	0.6584	0.5520	0.7430
No log	33.0	99	0.5709	0.6536	0.5705	0.7553
No log	34.0	102	0.6045	0.5994	0.6044	0.7774
No log	35.0	105	0.5951	0.5996	0.5950	0.7714
No log	36.0	108	0.5257	0.6390	0.5256	0.7250
No log	37.0	111	0.7633	0.5696	0.7632	0.8736
No log	38.0	114	0.5285	0.6510	0.5284	0.7269
No log	39.0	117	0.5132	0.6530	0.5131	0.7163
No log	40.0	120	0.5046	0.6568	0.5045	0.7103
No log	41.0	123	0.5314	0.6435	0.5313	0.7289
No log	42.0	126	0.4841	0.6649	0.4840	0.6957
No log	43.0	129	0.5205	0.6519	0.5202	0.7213
No log	44.0	132	0.5005	0.6631	0.5003	0.7073
No log	45.0	135	0.5430	0.6465	0.5427	0.7367
No log	46.0	138	0.5266	0.6675	0.5263	0.7255
No log	47.0	141	0.5163	0.6577	0.5162	0.7184
No log	48.0	144	0.4880	0.6721	0.4879	0.6985
No log	49.0	147	0.5256	0.6609	0.5253	0.7248
No log	50.0	150	0.4880	0.6684	0.4878	0.6984
No log	51.0	153	0.5489	0.6424	0.5488	0.7408
No log	52.0	156	0.5850	0.6285	0.5849	0.7648
No log	53.0	159	0.5358	0.6640	0.5355	0.7318
No log	54.0	162	0.5468	0.6705	0.5465	0.7392
No log	55.0	165	0.6027	0.6083	0.6026	0.7762
No log	56.0	168	0.5721	0.6174	0.5720	0.7563
No log	57.0	171	0.5065	0.6732	0.5063	0.7116
No log	58.0	174	0.5059	0.6859	0.5057	0.7111
No log	59.0	177	0.5029	0.6643	0.5028	0.7091
No log	60.0	180	0.4884	0.6573	0.4883	0.6988
No log	61.0	183	0.4937	0.6587	0.4936	0.7025
No log	62.0	186	0.5062	0.6509	0.5060	0.7114
No log	63.0	189	0.5311	0.6556	0.5309	0.7287
No log	64.0	192	0.5597	0.6527	0.5596	0.7480
No log	65.0	195	0.5498	0.6711	0.5496	0.7413
No log	66.0	198	0.5554	0.6449	0.5553	0.7452
No log	67.0	201	0.5423	0.6550	0.5422	0.7363
No log	68.0	204	0.5261	0.6668	0.5259	0.7252
No log	69.0	207	0.5304	0.6452	0.5302	0.7282
No log	70.0	210	0.4896	0.6610	0.4895	0.6997
No log	71.0	213	0.5056	0.6727	0.5055	0.7110
No log	72.0	216	0.5047	0.6598	0.5046	0.7104
No log	73.0	219	0.5169	0.6760	0.5167	0.7188
No log	74.0	222	0.5226	0.6538	0.5224	0.7228
No log	75.0	225	0.5369	0.6623	0.5367	0.7326
No log	76.0	228	0.5231	0.6600	0.5229	0.7231
No log	77.0	231	0.5386	0.6483	0.5384	0.7337
No log	78.0	234	0.5294	0.6533	0.5292	0.7274
No log	79.0	237	0.5112	0.6573	0.5111	0.7149
No log	80.0	240	0.5161	0.6563	0.5160	0.7183
No log	81.0	243	0.5041	0.6635	0.5039	0.7099
No log	82.0	246	0.5238	0.6482	0.5236	0.7236
No log	83.0	249	0.5244	0.6462	0.5241	0.7240
No log	84.0	252	0.5120	0.6565	0.5118	0.7154
No log	85.0	255	0.5370	0.6637	0.5369	0.7327
No log	86.0	258	0.5322	0.6587	0.5320	0.7294
No log	87.0	261	0.5280	0.6691	0.5277	0.7265
No log	88.0	264	0.5314	0.6660	0.5311	0.7288

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_lo50_k5_k5_fold3

BERT_V8_sp10_lw20_ex100_lo50_k5_k5_fold3

Model description

Intended uses & limitations

Training and evaluation data

Training procedure

Training hyperparameters

Training results

Framework versions

genki10/
BERT_V8_sp10_lw20_ex100_lo50_k5_k5_fold3