learning_rate: 2e-05
train_batch_size: 64
eval_batch_size: 64
seed: 42
optimizer: Use OptimizerNames.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	5	9.9370	0.0	9.9373	3.1523
No log	2.0	10	7.7774	0.0	7.7777	2.7888
No log	3.0	15	6.2641	-0.0015	6.2643	2.5029
No log	4.0	20	3.7965	0.0	3.7968	1.9485
No log	5.0	25	1.8951	0.0831	1.8954	1.3767
No log	6.0	30	0.9883	0.0107	0.9887	0.9943
No log	7.0	35	0.8269	0.2308	0.8272	0.9095
No log	8.0	40	0.6805	0.2489	0.6807	0.8251
No log	9.0	45	0.7831	0.2858	0.7833	0.8850
No log	10.0	50	0.7531	0.4092	0.7531	0.8678
No log	11.0	55	0.6948	0.3556	0.6949	0.8336
No log	12.0	60	0.6575	0.4464	0.6574	0.8108
No log	13.0	65	0.5273	0.5392	0.5272	0.7261
No log	14.0	70	0.4931	0.6004	0.4929	0.7021
No log	15.0	75	0.5847	0.5449	0.5846	0.7646
No log	16.0	80	0.5270	0.5724	0.5268	0.7258
No log	17.0	85	0.8420	0.4404	0.8419	0.9176
No log	18.0	90	0.5603	0.5035	0.5600	0.7483
No log	19.0	95	0.5442	0.5778	0.5439	0.7375
No log	20.0	100	0.5290	0.5285	0.5288	0.7272
No log	21.0	105	0.5567	0.4885	0.5565	0.7460
No log	22.0	110	0.5999	0.4936	0.5997	0.7744
No log	23.0	115	0.6316	0.4901	0.6314	0.7946
No log	24.0	120	0.5861	0.5134	0.5859	0.7654
No log	25.0	125	0.5245	0.5581	0.5242	0.7240
No log	26.0	130	0.5928	0.5007	0.5926	0.7698
No log	27.0	135	0.6025	0.5126	0.6023	0.7761
No log	28.0	140	0.5607	0.5049	0.5605	0.7487
No log	29.0	145	0.6283	0.4589	0.6281	0.7925
No log	30.0	150	0.5949	0.4772	0.5947	0.7712
No log	31.0	155	0.5458	0.5235	0.5455	0.7386
No log	32.0	160	0.5750	0.4973	0.5748	0.7581
No log	33.0	165	0.6461	0.4886	0.6459	0.8037
No log	34.0	170	0.5790	0.4816	0.5789	0.7608
No log	35.0	175	0.6036	0.4751	0.6035	0.7769
No log	36.0	180	0.5244	0.5399	0.5242	0.7240
No log	37.0	185	0.5861	0.4850	0.5860	0.7655
No log	38.0	190	0.5865	0.4762	0.5864	0.7658
No log	39.0	195	0.5430	0.5094	0.5428	0.7367
No log	40.0	200	0.6242	0.4854	0.6241	0.7900
No log	41.0	205	0.5794	0.4877	0.5793	0.7611
No log	42.0	210	0.5890	0.4883	0.5889	0.7674
No log	43.0	215	0.5885	0.4679	0.5883	0.7670
No log	44.0	220	0.5848	0.4753	0.5846	0.7646

Framework versions

Transformers 4.51.1
Pytorch 2.5.1+cu124
Datasets 3.5.0
Tokenizers 0.21.0

genki10/BERT_V8_sp10_lw20_ex100_lo100_k10_k10_fold2

BERT_V8_sp10_lw20_ex100_lo100_k10_k10_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_k10_k10_fold2