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	9.2194	0.0	9.2178	3.0361
No log	2.0	8	4.9017	0.0337	4.9007	2.2137
No log	3.0	12	2.7614	0.0156	2.7605	1.6615
No log	4.0	16	2.0891	0.0016	2.0882	1.4451
No log	5.0	20	1.3756	0.0266	1.3749	1.1725
No log	6.0	24	0.8495	0.2459	0.8491	0.9215
No log	7.0	28	1.0580	0.0410	1.0574	1.0283
No log	8.0	32	0.8814	0.1794	0.8811	0.9386
No log	9.0	36	0.8909	0.1876	0.8906	0.9437
No log	10.0	40	0.6749	0.4971	0.6748	0.8215
No log	11.0	44	0.9803	0.2711	0.9801	0.9900
No log	12.0	48	0.6016	0.5083	0.6018	0.7757
No log	13.0	52	1.0762	0.3686	1.0762	1.0374
No log	14.0	56	0.5577	0.5290	0.5579	0.7470
No log	15.0	60	0.8091	0.4654	0.8093	0.8996
No log	16.0	64	0.6245	0.5398	0.6248	0.7905
No log	17.0	68	0.7876	0.4583	0.7878	0.8876
No log	18.0	72	0.6087	0.5394	0.6091	0.7804
No log	19.0	76	1.4285	0.2636	1.4285	1.1952
No log	20.0	80	0.6490	0.5135	0.6492	0.8057
No log	21.0	84	1.6227	0.2294	1.6225	1.2738
No log	22.0	88	0.7363	0.4601	0.7363	0.8581
No log	23.0	92	1.1057	0.3328	1.1055	1.0514
No log	24.0	96	0.7672	0.4633	0.7673	0.8760
No log	25.0	100	0.6707	0.5232	0.6710	0.8191
No log	26.0	104	1.0865	0.3370	1.0865	1.0423
No log	27.0	108	0.9168	0.3915	0.9169	0.9575
No log	28.0	112	1.0209	0.3719	1.0210	1.0104
No log	29.0	116	1.1632	0.3341	1.1632	1.0785
No log	30.0	120	1.1126	0.3359	1.1125	1.0548
No log	31.0	124	1.0436	0.3150	1.0435	1.0215
No log	32.0	128	1.1593	0.3053	1.1591	1.0766
No log	33.0	132	0.9408	0.3667	0.9406	0.9699
No log	34.0	136	0.8353	0.4006	0.8353	0.9139
No log	35.0	140	1.2841	0.2922	1.2839	1.1331
No log	36.0	144	0.8965	0.3903	0.8964	0.9468
No log	37.0	148	1.3041	0.2692	1.3038	1.1418
No log	38.0	152	0.7783	0.4134	0.7782	0.8822
No log	39.0	156	1.0766	0.3302	1.0764	1.0375
No log	40.0	160	1.0276	0.3355	1.0275	1.0137
No log	41.0	164	0.8647	0.3800	0.8647	0.9299
No log	42.0	168	1.3778	0.2505	1.3777	1.1737
No log	43.0	172	0.9568	0.3704	0.9568	0.9782
No log	44.0	176	1.0480	0.3070	1.0479	1.0237
No log	45.0	180	0.7678	0.4253	0.7679	0.8763
No log	46.0	184	1.4313	0.2219	1.4312	1.1963

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_lo00_k5_k5_fold3

BERT_V8_sp10_lw40_ex50_lo00_k5_k5_fold3

Model description

Intended uses & limitations

Training and evaluation data

Training procedure

Training hyperparameters

Training results

Framework versions

genki10/
BERT_V8_sp10_lw40_ex50_lo00_k5_k5_fold3