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	2	9.1716	0.0	9.1716	3.0285
No log	2.0	4	7.7794	0.0	7.7794	2.7892
No log	3.0	6	7.1598	0.0	7.1598	2.6758
No log	4.0	8	6.4864	0.0	6.4864	2.5468
No log	5.0	10	5.8109	0.0156	5.8109	2.4106
No log	6.0	12	5.1322	0.0115	5.1322	2.2654
No log	7.0	14	4.4290	0.0115	4.4290	2.1045
No log	8.0	16	3.9460	0.0115	3.9460	1.9865
No log	9.0	18	3.2290	0.0	3.2290	1.7970
No log	10.0	20	2.8397	0.0	2.8397	1.6851
No log	11.0	22	2.2748	0.0447	2.2748	1.5082
No log	12.0	24	1.7308	0.0316	1.7308	1.3156
No log	13.0	26	1.4196	0.0316	1.4196	1.1915
No log	14.0	28	1.1564	0.0316	1.1564	1.0753
No log	15.0	30	1.0433	0.0316	1.0433	1.0214
No log	16.0	32	0.9687	0.0316	0.9687	0.9842
No log	17.0	34	0.9325	0.0316	0.9325	0.9657
No log	18.0	36	0.9770	0.0316	0.9770	0.9884
No log	19.0	38	1.0274	0.0426	1.0274	1.0136
No log	20.0	40	0.8755	0.1918	0.8755	0.9357
No log	21.0	42	0.8065	0.3405	0.8065	0.8981
No log	22.0	44	0.8073	0.3776	0.8073	0.8985
No log	23.0	46	1.1344	0.1331	1.1344	1.0651
No log	24.0	48	1.2613	0.1594	1.2613	1.1231
No log	25.0	50	0.8401	0.3380	0.8401	0.9166
No log	26.0	52	0.7072	0.3952	0.7072	0.8409
No log	27.0	54	0.8914	0.3397	0.8914	0.9441
No log	28.0	56	1.0505	0.3183	1.0505	1.0249
No log	29.0	58	0.7100	0.4600	0.7100	0.8426
No log	30.0	60	0.8044	0.4201	0.8044	0.8969
No log	31.0	62	1.3400	0.2436	1.3400	1.1576
No log	32.0	64	1.2144	0.2774	1.2144	1.1020
No log	33.0	66	0.9170	0.3634	0.9170	0.9576
No log	34.0	68	0.9422	0.3604	0.9422	0.9707
No log	35.0	70	1.0244	0.3251	1.0244	1.0121
No log	36.0	72	1.5536	0.2351	1.5536	1.2464
No log	37.0	74	1.3381	0.2557	1.3381	1.1568
No log	38.0	76	0.8162	0.4102	0.8162	0.9035
No log	39.0	78	0.8134	0.4144	0.8134	0.9019
No log	40.0	80	1.1295	0.2983	1.1295	1.0628
No log	41.0	82	1.4143	0.2499	1.4143	1.1893
No log	42.0	84	1.3599	0.2490	1.3599	1.1662
No log	43.0	86	0.9394	0.3842	0.9394	0.9692
No log	44.0	88	0.9731	0.3782	0.9731	0.9865
No log	45.0	90	1.5497	0.2227	1.5497	1.2449
No log	46.0	92	1.7163	0.1940	1.7163	1.3101
No log	47.0	94	1.2245	0.2575	1.2245	1.1066
No log	48.0	96	0.8854	0.3725	0.8854	0.9409
No log	49.0	98	0.8688	0.3690	0.8688	0.9321
No log	50.0	100	0.8791	0.3511	0.8791	0.9376
No log	51.0	102	1.1111	0.2822	1.1111	1.0541
No log	52.0	104	1.3830	0.2070	1.3830	1.1760
No log	53.0	106	1.5326	0.1703	1.5326	1.2380
No log	54.0	108	1.5701	0.1764	1.5701	1.2530
No log	55.0	110	1.4320	0.2099	1.4320	1.1966
No log	56.0	112	1.1627	0.2702	1.1627	1.0783
No log	57.0	114	0.8939	0.3873	0.8939	0.9455
No log	58.0	116	0.8675	0.4041	0.8675	0.9314
No log	59.0	118	0.8554	0.4217	0.8554	0.9249

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_lo100_k1_k1_fold0

BERT_V8_sp10_lw40_ex100_lo100_k1_k1_fold0

Model description

Intended uses & limitations

Training and evaluation data

Training procedure

Training hyperparameters

Training results

Framework versions

genki10/
BERT_V8_sp10_lw40_ex100_lo100_k1_k1_fold0