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	4	6.7824	0.0	6.7829	2.6044
No log	2.0	8	3.5173	0.0	3.5177	1.8756
No log	3.0	12	1.9637	0.0551	1.9641	1.4015
No log	4.0	16	1.0658	0.0	1.0662	1.0326
No log	5.0	20	1.0440	-0.0117	1.0445	1.0220
No log	6.0	24	1.0042	0.0414	1.0043	1.0022
No log	7.0	28	0.7907	0.3704	0.7909	0.8893
No log	8.0	32	1.0952	0.0061	1.0955	1.0467
No log	9.0	36	0.7817	0.4858	0.7818	0.8842
No log	10.0	40	1.1726	0.3705	1.1728	1.0830
No log	11.0	44	0.8218	0.1342	0.8223	0.9068
No log	12.0	48	0.8315	0.1188	0.8319	0.9121
No log	13.0	52	0.8267	0.1337	0.8272	0.9095
No log	14.0	56	0.5288	0.4425	0.5290	0.7273
No log	15.0	60	0.5154	0.4417	0.5155	0.7180
No log	16.0	64	0.5871	0.4629	0.5872	0.7663
No log	17.0	68	0.5482	0.5123	0.5483	0.7405
No log	18.0	72	0.5475	0.5366	0.5475	0.7399
No log	19.0	76	0.5353	0.5510	0.5354	0.7317
No log	20.0	80	0.8169	0.3352	0.8169	0.9038
No log	21.0	84	0.5950	0.5684	0.5951	0.7714
No log	22.0	88	1.0602	0.2641	1.0601	1.0296
No log	23.0	92	0.5758	0.5366	0.5758	0.7588
No log	24.0	96	0.9585	0.2754	0.9584	0.9790
No log	25.0	100	0.6601	0.4910	0.6601	0.8125
No log	26.0	104	0.9466	0.1632	0.9467	0.9730
No log	27.0	108	0.6321	0.4446	0.6322	0.7951
No log	28.0	112	1.1341	0.1928	1.1342	1.0650
No log	29.0	116	0.6432	0.4323	0.6432	0.8020
No log	30.0	120	0.8493	0.3348	0.8493	0.9216
No log	31.0	124	0.6041	0.5111	0.6041	0.7773
No log	32.0	128	0.7558	0.3650	0.7559	0.8694
No log	33.0	132	0.6522	0.4294	0.6522	0.8076
No log	34.0	136	0.8709	0.2306	0.8710	0.9333
No log	35.0	140	0.7592	0.3107	0.7593	0.8714
No log	36.0	144	0.7837	0.3100	0.7839	0.8854
No log	37.0	148	0.7193	0.3317	0.7194	0.8482
No log	38.0	152	0.7632	0.3436	0.7633	0.8736
No log	39.0	156	0.8133	0.3425	0.8133	0.9018
No log	40.0	160	0.6703	0.3881	0.6704	0.8188
No log	41.0	164	0.8297	0.2721	0.8299	0.9110
No log	42.0	168	0.6391	0.4333	0.6392	0.7995
No log	43.0	172	0.9019	0.2817	0.9021	0.9498
No log	44.0	176	0.6207	0.4611	0.6207	0.7879
No log	45.0	180	0.8123	0.3388	0.8124	0.9013
No log	46.0	184	0.6285	0.4050	0.6287	0.7929
No log	47.0	188	0.8760	0.2538	0.8761	0.9360
No log	48.0	192	0.6147	0.4281	0.6148	0.7841
No log	49.0	196	0.8894	0.2991	0.8895	0.9431
No log	50.0	200	0.6398	0.4365	0.6398	0.7999
No log	51.0	204	0.8058	0.3333	0.8058	0.8976

Framework versions

Transformers 4.51.1
Pytorch 2.5.1+cu124
Datasets 3.5.0
Tokenizers 0.21.0

genki10/BERT_V8_sp10_lw40_ex100_lo00_k5_k5_fold2

BERT_V8_sp10_lw40_ex100_lo00_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_ex100_lo00_k5_k5_fold2