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	3	8.5936	0.0	8.5938	2.9315
No log	2.0	6	6.4304	0.0	6.4305	2.5359
No log	3.0	9	4.8713	0.0102	4.8715	2.2072
No log	4.0	12	3.4208	0.0	3.4211	1.8496
No log	5.0	15	2.3530	0.1286	2.3534	1.5341
No log	6.0	18	1.6334	0.0280	1.6337	1.2782
No log	7.0	21	1.1215	0.0107	1.1219	1.0592
No log	8.0	24	1.1657	0.0107	1.1662	1.0799
No log	9.0	27	0.7898	0.3442	0.7903	0.8890
No log	10.0	30	0.8306	0.1611	0.8310	0.9116
No log	11.0	33	1.0342	0.0875	1.0346	1.0171
No log	12.0	36	0.6920	0.4277	0.6923	0.8320
No log	13.0	39	0.8449	0.2860	0.8452	0.9194
No log	14.0	42	0.7467	0.3972	0.7470	0.8643
No log	15.0	45	0.6532	0.4403	0.6534	0.8083
No log	16.0	48	0.7208	0.4676	0.7210	0.8491
No log	17.0	51	0.6031	0.4712	0.6032	0.7767
No log	18.0	54	0.6595	0.5072	0.6595	0.8121
No log	19.0	57	0.6646	0.5208	0.6646	0.8152
No log	20.0	60	0.5305	0.6035	0.5303	0.7282
No log	21.0	63	1.4858	0.3180	1.4858	1.2189
No log	22.0	66	0.6223	0.5293	0.6221	0.7888
No log	23.0	69	0.5328	0.5917	0.5326	0.7298
No log	24.0	72	0.8937	0.3542	0.8937	0.9454
No log	25.0	75	0.5174	0.5633	0.5174	0.7193
No log	26.0	78	0.5613	0.5248	0.5612	0.7492
No log	27.0	81	0.9702	0.3565	0.9702	0.9850
No log	28.0	84	0.5281	0.5528	0.5279	0.7266
No log	29.0	87	0.9891	0.3671	0.9890	0.9945
No log	30.0	90	0.9355	0.3809	0.9354	0.9672
No log	31.0	93	0.4945	0.5867	0.4943	0.7031
No log	32.0	96	0.6917	0.4518	0.6915	0.8316
No log	33.0	99	0.8254	0.4023	0.8252	0.9084
No log	34.0	102	0.5053	0.5452	0.5052	0.7108
No log	35.0	105	0.7413	0.4330	0.7411	0.8609
No log	36.0	108	0.6220	0.4819	0.6217	0.7885
No log	37.0	111	0.6184	0.5053	0.6182	0.7862
No log	38.0	114	0.7743	0.4270	0.7741	0.8798
No log	39.0	117	0.6755	0.4591	0.6753	0.8217
No log	40.0	120	0.6848	0.4384	0.6846	0.8274
No log	41.0	123	0.5342	0.5320	0.5340	0.7308
No log	42.0	126	0.6045	0.5006	0.6042	0.7773
No log	43.0	129	0.5897	0.5168	0.5895	0.7678
No log	44.0	132	0.5954	0.5035	0.5952	0.7715
No log	45.0	135	0.7638	0.4302	0.7636	0.8738
No log	46.0	138	0.6257	0.5051	0.6254	0.7908
No log	47.0	141	0.7981	0.4183	0.7979	0.8933
No log	48.0	144	0.6160	0.5173	0.6158	0.7847
No log	49.0	147	0.7008	0.4770	0.7007	0.8371
No log	50.0	150	0.6533	0.4873	0.6530	0.8081

Framework versions

Transformers 4.51.1
Pytorch 2.5.1+cu124
Datasets 3.5.0
Tokenizers 0.21.0

genki10/BERT_V8_sp10_lw40_ex50_lo100_k5_k5_fold2

BERT_V8_sp10_lw40_ex50_lo100_k5_k5_fold2

Model description

Intended uses & limitations

Training and evaluation data

Training procedure

Training hyperparameters

Training results

Framework versions

genki10/
BERT_V8_sp10_lw40_ex50_lo100_k5_k5_fold2