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	4	9.8446	0.0018	9.8430	3.1373
No log	2.0	8	5.9072	0.0397	5.9059	2.4302
No log	3.0	12	3.3760	0.0038	3.3751	1.8371
No log	4.0	16	1.8449	0.0528	1.8441	1.3580
No log	5.0	20	1.3460	0.0202	1.3454	1.1599
No log	6.0	24	1.9634	0.0389	1.9623	1.4008
No log	7.0	28	1.1576	0.0301	1.1569	1.0756
No log	8.0	32	1.0220	0.0416	1.0214	1.0107
No log	9.0	36	1.8466	0.0368	1.8455	1.3585
No log	10.0	40	1.0735	0.0850	1.0731	1.0359
No log	11.0	44	1.2817	0.1172	1.2811	1.1319
No log	12.0	48	0.9403	0.1883	0.9402	0.9696
No log	13.0	52	0.8251	0.2450	0.8255	0.9086
No log	14.0	56	0.9225	0.1661	0.9228	0.9606
No log	15.0	60	0.8264	0.1660	0.8268	0.9093
No log	16.0	64	1.1788	0.0626	1.1787	1.0857
No log	17.0	68	0.7751	0.2384	0.7754	0.8806
No log	18.0	72	1.0888	0.2563	1.0889	1.0435
No log	19.0	76	0.6586	0.3917	0.6587	0.8116
No log	20.0	80	1.1507	0.2356	1.1505	1.0726
No log	21.0	84	0.7814	0.3744	0.7814	0.8840
No log	22.0	88	0.7189	0.4060	0.7189	0.8479
No log	23.0	92	1.0817	0.2559	1.0815	1.0400
No log	24.0	96	0.6389	0.4832	0.6391	0.7994
No log	25.0	100	1.1363	0.2825	1.1362	1.0659
No log	26.0	104	0.6795	0.4921	0.6798	0.8245
No log	27.0	108	1.4067	0.2310	1.4068	1.1861
No log	28.0	112	0.8172	0.4086	0.8175	0.9041
No log	29.0	116	0.8851	0.3992	0.8854	0.9409
No log	30.0	120	0.8646	0.3972	0.8649	0.9300
No log	31.0	124	1.0341	0.3241	1.0344	1.0170
No log	32.0	128	0.8890	0.3760	0.8892	0.9430
No log	33.0	132	0.9643	0.3456	0.9646	0.9821
No log	34.0	136	0.9097	0.3894	0.9102	0.9540
No log	35.0	140	1.2907	0.2418	1.2910	1.1362
No log	36.0	144	1.0270	0.3168	1.0273	1.0136
No log	37.0	148	0.8853	0.3358	0.8855	0.9410
No log	38.0	152	1.2340	0.2141	1.2338	1.1108
No log	39.0	156	0.8634	0.3599	0.8636	0.9293
No log	40.0	160	0.9880	0.2947	0.9881	0.9940
No log	41.0	164	1.0491	0.2818	1.0493	1.0244
No log	42.0	168	1.2317	0.2343	1.2316	1.1098
No log	43.0	172	0.8480	0.3907	0.8482	0.9210
No log	44.0	176	1.3779	0.1962	1.3775	1.1737
No log	45.0	180	0.9521	0.3074	0.9522	0.9758
No log	46.0	184	0.9400	0.3312	0.9403	0.9697
No log	47.0	188	1.0369	0.2631	1.0370	1.0183
No log	48.0	192	0.8182	0.4164	0.8186	0.9048
No log	49.0	196	1.1026	0.2894	1.1028	1.0502
No log	50.0	200	0.9911	0.3391	0.9914	0.9957
No log	51.0	204	1.1358	0.2479	1.1358	1.0658
No log	52.0	208	0.9931	0.2869	0.9931	0.9966
No log	53.0	212	1.1632	0.2364	1.1632	1.0785
No log	54.0	216	0.9689	0.3125	0.9692	0.9845
No log	55.0	220	1.2184	0.2379	1.2186	1.1039
No log	56.0	224	1.0929	0.2794	1.0931	1.0455

Framework versions

Transformers 4.47.0
Pytorch 2.5.1+cu121
Datasets 3.3.1
Tokenizers 0.21.0

genki10/BERT_V8_sp20_lw10_ex50_lo00_k5_k5_fold3

BERT_V8_sp20_lw10_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_sp20_lw10_ex50_lo00_k5_k5_fold3