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	2	8.8516	0.0	8.8516	2.9752
No log	2.0	4	7.5226	0.0	7.5226	2.7427
No log	3.0	6	6.7368	0.0	6.7368	2.5955
No log	4.0	8	5.9058	0.0329	5.9058	2.4302
No log	5.0	10	5.0358	0.0115	5.0358	2.2441
No log	6.0	12	4.2744	0.0039	4.2744	2.0675
No log	7.0	14	3.4531	0.0	3.4531	1.8583
No log	8.0	16	2.7066	0.0	2.7066	1.6452
No log	9.0	18	2.0602	0.0627	2.0602	1.4353
No log	10.0	20	1.6077	0.0316	1.6077	1.2680
No log	11.0	22	1.2784	0.0316	1.2784	1.1307
No log	12.0	24	1.0229	0.0316	1.0229	1.0114
No log	13.0	26	0.8538	0.2860	0.8538	0.9240
No log	14.0	28	0.7453	0.3141	0.7453	0.8633
No log	15.0	30	0.6771	0.4212	0.6771	0.8229
No log	16.0	32	0.5915	0.3736	0.5915	0.7691
No log	17.0	34	0.5262	0.4526	0.5262	0.7254
No log	18.0	36	0.4956	0.4935	0.4956	0.7040
No log	19.0	38	0.5525	0.5333	0.5525	0.7433
No log	20.0	40	0.4630	0.5520	0.4630	0.6804
No log	21.0	42	0.6333	0.4950	0.6333	0.7958
No log	22.0	44	0.4563	0.6062	0.4563	0.6755
No log	23.0	46	0.5580	0.5541	0.5580	0.7470
No log	24.0	48	0.5275	0.6007	0.5275	0.7263
No log	25.0	50	0.4898	0.5969	0.4898	0.6999
No log	26.0	52	0.5369	0.5357	0.5369	0.7327
No log	27.0	54	0.5453	0.5560	0.5453	0.7384
No log	28.0	56	0.5787	0.5173	0.5787	0.7607
No log	29.0	58	0.5522	0.5869	0.5522	0.7431
No log	30.0	60	0.6241	0.5406	0.6241	0.7900
No log	31.0	62	0.5817	0.5370	0.5817	0.7627
No log	32.0	64	0.5811	0.5279	0.5811	0.7623
No log	33.0	66	0.5602	0.5670	0.5602	0.7485
No log	34.0	68	0.5118	0.5928	0.5118	0.7154
No log	35.0	70	0.6262	0.4918	0.6262	0.7914
No log	36.0	72	0.5180	0.6000	0.5180	0.7197
No log	37.0	74	0.6407	0.5712	0.6407	0.8004
No log	38.0	76	0.5374	0.6060	0.5374	0.7331
No log	39.0	78	0.8694	0.4341	0.8694	0.9324
No log	40.0	80	0.7138	0.4788	0.7138	0.8449
No log	41.0	82	0.5634	0.5783	0.5634	0.7506
No log	42.0	84	0.6058	0.5733	0.6058	0.7783
No log	43.0	86	0.5311	0.5745	0.5311	0.7288
No log	44.0	88	0.5915	0.5088	0.5915	0.7691
No log	45.0	90	0.5103	0.5943	0.5103	0.7144
No log	46.0	92	0.5186	0.5969	0.5186	0.7201
No log	47.0	94	0.5606	0.5688	0.5606	0.7487
No log	48.0	96	0.5279	0.6250	0.5279	0.7266
No log	49.0	98	0.5279	0.6039	0.5279	0.7265
No log	50.0	100	0.6029	0.5354	0.6029	0.7765
No log	51.0	102	0.5210	0.5983	0.5210	0.7218
No log	52.0	104	0.5131	0.6099	0.5131	0.7163
No log	53.0	106	0.5472	0.5606	0.5472	0.7398
No log	54.0	108	0.5435	0.5711	0.5435	0.7372
No log	55.0	110	0.5022	0.6088	0.5022	0.7087
No log	56.0	112	0.5028	0.6009	0.5028	0.7091
No log	57.0	114	0.5713	0.5538	0.5713	0.7559
No log	58.0	116	0.5156	0.5867	0.5156	0.7180
No log	59.0	118	0.5246	0.6107	0.5246	0.7243
No log	60.0	120	0.5038	0.6036	0.5038	0.7098
No log	61.0	122	0.6076	0.4982	0.6076	0.7795
No log	62.0	124	0.6683	0.4749	0.6683	0.8175
No log	63.0	126	0.5530	0.5430	0.5530	0.7437
No log	64.0	128	0.5185	0.5855	0.5185	0.7201
No log	65.0	130	0.5675	0.5629	0.5675	0.7533
No log	66.0	132	0.5120	0.5984	0.5120	0.7156
No log	67.0	134	0.5382	0.5498	0.5382	0.7336
No log	68.0	136	0.5363	0.5555	0.5363	0.7323
No log	69.0	138	0.5136	0.6027	0.5136	0.7167
No log	70.0	140	0.5187	0.6112	0.5187	0.7202
No log	71.0	142	0.5582	0.5553	0.5582	0.7472
No log	72.0	144	0.5803	0.5467	0.5803	0.7618
No log	73.0	146	0.5325	0.5801	0.5325	0.7297
No log	74.0	148	0.5118	0.6119	0.5118	0.7154
No log	75.0	150	0.5079	0.6074	0.5079	0.7126
No log	76.0	152	0.5403	0.5463	0.5403	0.7350
No log	77.0	154	0.5305	0.5676	0.5305	0.7283
No log	78.0	156	0.4980	0.6096	0.4980	0.7057

Framework versions

Transformers 4.47.0
Pytorch 2.5.1+cu121
Datasets 3.3.1
Tokenizers 0.21.0

genki10/BERT_V8_sp10_lw20_ex200_lo50_k3_k3_fold0

BERT_V8_sp10_lw20_ex200_lo50_k3_k3_fold0

Model description

Intended uses & limitations

Training and evaluation data

Training procedure

Training hyperparameters

Training results

Framework versions

genki10/
BERT_V8_sp10_lw20_ex200_lo50_k3_k3_fold0