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	1	12.6260	0.0	12.6238	3.5530
No log	2.0	2	11.2539	0.0041	11.2520	3.3544
No log	3.0	3	9.9764	0.0018	9.9747	3.1583
No log	4.0	4	8.6982	0.0	8.6965	2.9490
No log	5.0	5	7.9045	0.0	7.9028	2.8112
No log	6.0	6	7.1139	0.0	7.1123	2.6669
No log	7.0	7	6.2566	0.0080	6.2552	2.5010
No log	8.0	8	5.7901	0.0362	5.7887	2.4060
No log	9.0	9	5.0940	0.0181	5.0927	2.2567
No log	10.0	10	4.8561	0.0038	4.8547	2.2033
No log	11.0	11	4.3571	0.0038	4.3558	2.0871
No log	12.0	12	3.8330	0.0	3.8319	1.9575
No log	13.0	13	3.7185	0.0	3.7175	1.9281
No log	14.0	14	3.4140	0.0	3.4131	1.8474
No log	15.0	15	2.9758	0.0	2.9748	1.7247
No log	16.0	16	2.7067	0.0002	2.7057	1.6449
No log	17.0	17	2.4280	0.0542	2.4271	1.5579
No log	18.0	18	2.1508	0.0713	2.1501	1.4663
No log	19.0	19	2.0258	0.0545	2.0251	1.4231
No log	20.0	20	1.7422	0.0488	1.7416	1.3197
No log	21.0	21	1.5560	0.0202	1.5553	1.2471
No log	22.0	22	1.3955	0.0202	1.3949	1.1810
No log	23.0	23	1.2420	0.0202	1.2415	1.1142
No log	24.0	24	1.1464	0.0202	1.1459	1.0705
No log	25.0	25	1.0193	0.0202	1.0189	1.0094
No log	26.0	26	0.9439	0.0312	0.9435	0.9714
No log	27.0	27	0.8961	0.2559	0.8957	0.9464
No log	28.0	28	0.8896	0.2445	0.8892	0.9430
No log	29.0	29	0.7810	0.3695	0.7807	0.8836
No log	30.0	30	0.7692	0.3249	0.7689	0.8769
No log	31.0	31	0.7452	0.3337	0.7450	0.8631
No log	32.0	32	0.6755	0.3875	0.6753	0.8218
No log	33.0	33	0.7730	0.3287	0.7726	0.8790
No log	34.0	34	0.8199	0.3131	0.8195	0.9052
No log	35.0	35	0.7357	0.3906	0.7354	0.8576
No log	36.0	36	0.6259	0.4447	0.6258	0.7910
No log	37.0	37	0.6343	0.4650	0.6341	0.7963
No log	38.0	38	0.6073	0.4763	0.6072	0.7792
No log	39.0	39	0.6722	0.4725	0.6720	0.8198
No log	40.0	40	0.6670	0.4836	0.6669	0.8166
No log	41.0	41	0.7018	0.4739	0.7016	0.8376
No log	42.0	42	0.8858	0.3739	0.8855	0.9410
No log	43.0	43	0.9017	0.3682	0.9014	0.9494
No log	44.0	44	0.7579	0.4714	0.7577	0.8705
No log	45.0	45	0.6497	0.5237	0.6497	0.8060
No log	46.0	46	0.6723	0.5102	0.6723	0.8199
No log	47.0	47	0.8328	0.4522	0.8326	0.9125
No log	48.0	48	0.8906	0.4194	0.8904	0.9436
No log	49.0	49	0.9959	0.3584	0.9957	0.9978
No log	50.0	50	0.9230	0.4152	0.9228	0.9606
No log	51.0	51	0.7877	0.4705	0.7876	0.8875
No log	52.0	52	0.7571	0.4902	0.7571	0.8701
No log	53.0	53	0.7161	0.4931	0.7161	0.8462
No log	54.0	54	0.7758	0.4720	0.7758	0.8808
No log	55.0	55	0.8115	0.4513	0.8114	0.9008
No log	56.0	56	0.7614	0.4681	0.7613	0.8725
No log	57.0	57	0.6979	0.4899	0.6978	0.8354
No log	58.0	58	0.7175	0.5023	0.7174	0.8470
No log	59.0	59	0.8342	0.4403	0.8338	0.9131
No log	60.0	60	0.9922	0.3623	0.9916	0.9958
No log	61.0	61	0.9980	0.3601	0.9974	0.9987
No log	62.0	62	0.8782	0.3954	0.8777	0.9369
No log	63.0	63	0.7254	0.4947	0.7252	0.8516
No log	64.0	64	0.6958	0.4935	0.6956	0.8340
No log	65.0	65	0.7126	0.5004	0.7123	0.8440
No log	66.0	66	0.7956	0.4397	0.7953	0.8918
No log	67.0	67	0.8412	0.4026	0.8408	0.9170
No log	68.0	68	0.8334	0.4006	0.8330	0.9127
No log	69.0	69	0.8944	0.3900	0.8940	0.9455
No log	70.0	70	0.8792	0.3934	0.8788	0.9375
No log	71.0	71	0.9084	0.3892	0.9080	0.9529
No log	72.0	72	0.8644	0.4006	0.8641	0.9296
No log	73.0	73	0.8321	0.4090	0.8317	0.9120
No log	74.0	74	0.8366	0.4101	0.8363	0.9145
No log	75.0	75	0.8309	0.3996	0.8306	0.9114

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_lo100_k1_k1_fold3

BERT_V8_sp10_lw20_ex200_lo100_k1_k1_fold3

Model description

Intended uses & limitations

Training and evaluation data

Training procedure

Training hyperparameters

Training results

Framework versions

genki10/
BERT_V8_sp10_lw20_ex200_lo100_k1_k1_fold3