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	10.4660	0.0	10.4642	3.2348
No log	2.0	4	9.9107	0.0	9.9087	3.1478
No log	3.0	6	9.2222	0.0	9.2204	3.0365
No log	4.0	8	7.3995	0.0	7.3980	2.7199
No log	5.0	10	7.2883	0.0	7.2866	2.6994
No log	6.0	12	6.3206	-0.0011	6.3191	2.5138
No log	7.0	14	4.9417	0.0	4.9405	2.2227
No log	8.0	16	4.1595	0.0	4.1584	2.0392
No log	9.0	18	3.4538	0.0	3.4528	1.8582
No log	10.0	20	3.0115	0.0	3.0105	1.7351
No log	11.0	22	2.4608	0.0417	2.4599	1.5684
No log	12.0	24	1.9996	0.0102	1.9988	1.4138
No log	13.0	26	1.8019	0.0102	1.8011	1.3421
No log	14.0	28	1.6475	0.0102	1.6468	1.2833
No log	15.0	30	1.4575	0.0102	1.4569	1.2070
No log	16.0	32	1.3696	0.0102	1.3690	1.1700
No log	17.0	34	1.2683	0.0102	1.2677	1.1259
No log	18.0	36	1.1266	0.0365	1.1261	1.0612
No log	19.0	38	1.3010	0.0694	1.3006	1.1404
No log	20.0	40	1.1943	0.0694	1.1940	1.0927
No log	21.0	42	0.9193	0.1185	0.9189	0.9586
No log	22.0	44	0.8907	0.2659	0.8902	0.9435
No log	23.0	46	0.8356	0.3325	0.8352	0.9139
No log	24.0	48	0.9572	0.1989	0.9571	0.9783
No log	25.0	50	0.8150	0.4274	0.8151	0.9028
No log	26.0	52	0.6790	0.4875	0.6791	0.8241
No log	27.0	54	0.8860	0.4552	0.8863	0.9415
No log	28.0	56	1.9870	0.1842	1.9876	1.4098
No log	29.0	58	2.1734	0.1806	2.1740	1.4744
No log	30.0	60	1.1277	0.3589	1.1283	1.0622
No log	31.0	62	0.6382	0.5371	0.6385	0.7991
No log	32.0	64	0.6713	0.5256	0.6716	0.8195
No log	33.0	66	0.9597	0.3703	0.9601	0.9798
No log	34.0	68	1.1341	0.3170	1.1345	1.0651
No log	35.0	70	1.0336	0.3356	1.0340	1.0168
No log	36.0	72	0.9251	0.4077	0.9254	0.9620
No log	37.0	74	1.0750	0.3201	1.0754	1.0370
No log	38.0	76	0.8497	0.4656	0.8501	0.9220
No log	39.0	78	0.7963	0.4591	0.7968	0.8927
No log	40.0	80	1.0741	0.3540	1.0746	1.0366
No log	41.0	82	1.6319	0.2437	1.6321	1.2776
No log	42.0	84	1.4850	0.2739	1.4853	1.2187
No log	43.0	86	1.0606	0.3439	1.0611	1.0301
No log	44.0	88	1.2634	0.3076	1.2638	1.1242
No log	45.0	90	1.7327	0.2038	1.7330	1.3164
No log	46.0	92	1.7869	0.1952	1.7872	1.3369
No log	47.0	94	1.2550	0.3115	1.2555	1.1205
No log	48.0	96	0.9811	0.4135	0.9818	0.9909
No log	49.0	98	1.0458	0.3953	1.0465	1.0230
No log	50.0	100	1.5684	0.2306	1.5686	1.2524
No log	51.0	102	1.5915	0.2209	1.5917	1.2616
No log	52.0	104	1.1692	0.3231	1.1696	1.0815
No log	53.0	106	1.0563	0.3499	1.0569	1.0280
No log	54.0	108	1.2633	0.3043	1.2636	1.1241
No log	55.0	110	1.7090	0.1803	1.7091	1.3073
No log	56.0	112	1.6684	0.1922	1.6686	1.2917
No log	57.0	114	1.2039	0.3186	1.2043	1.0974
No log	58.0	116	1.0755	0.3320	1.0761	1.0373
No log	59.0	118	1.1507	0.3443	1.1513	1.0730
No log	60.0	120	1.5049	0.2412	1.5053	1.2269
No log	61.0	122	1.6870	0.1749	1.6872	1.2989

Framework versions

Transformers 4.47.0
Pytorch 2.5.1+cu121
Datasets 3.3.1
Tokenizers 0.21.0

genki10/BERT_V8_sp20_lw10_ex30_lo00_k1_k1_fold3

BERT_V8_sp20_lw10_ex30_lo00_k1_k1_fold3

Model description

Intended uses & limitations

Training and evaluation data

Training procedure

Training hyperparameters

Training results

Framework versions

genki10/
BERT_V8_sp20_lw10_ex30_lo00_k1_k1_fold3