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: 150

Training results

Training Loss	Epoch	Step	Validation Loss	Qwk	Mse	Rmse
No log	1.0	3	11.3351	-0.0072	11.3329	3.3664
No log	2.0	6	9.7051	0.0	9.7031	3.1150
No log	3.0	9	8.2573	0.0	8.2556	2.8733
No log	4.0	12	7.8667	0.0	7.8650	2.8045
No log	5.0	15	7.3739	0.0	7.3722	2.7152
No log	6.0	18	5.7551	0.0352	5.7539	2.3987
No log	7.0	21	4.2212	0.0	4.2203	2.0543
No log	8.0	24	2.9631	0.0	2.9624	1.7212
No log	9.0	27	1.9396	0.0822	1.9390	1.3925
No log	10.0	30	1.3639	0.0	1.3634	1.1676
No log	11.0	33	1.0583	0.0	1.0580	1.0286
No log	12.0	36	1.0199	0.0246	1.0196	1.0097
No log	13.0	39	0.8240	0.3778	0.8237	0.9076
No log	14.0	42	1.0772	0.0430	1.0768	1.0377
No log	15.0	45	1.2302	0.0932	1.2298	1.1089
No log	16.0	48	0.8211	0.3509	0.8209	0.9060
No log	17.0	51	1.5579	0.1549	1.5575	1.2480
No log	18.0	54	1.4417	0.1562	1.4413	1.2005
No log	19.0	57	0.7936	0.3836	0.7936	0.8908
No log	20.0	60	1.1179	0.2341	1.1178	1.0573
No log	21.0	63	1.1838	0.2695	1.1835	1.0879
No log	22.0	66	1.3385	0.2698	1.3380	1.1567
No log	23.0	69	1.1868	0.2950	1.1864	1.0892
No log	24.0	72	0.8528	0.4239	0.8526	0.9234
No log	25.0	75	1.1383	0.2895	1.1380	1.0668
No log	26.0	78	1.0203	0.3873	1.0201	1.0100
No log	27.0	81	2.1610	0.1663	2.1605	1.4699
No log	28.0	84	1.4498	0.2677	1.4496	1.2040
No log	29.0	87	0.8211	0.4845	0.8210	0.9061
No log	30.0	90	1.7177	0.2374	1.7174	1.3105
No log	31.0	93	1.2017	0.3067	1.2015	1.0961
No log	32.0	96	1.2651	0.3062	1.2649	1.1247
No log	33.0	99	1.2595	0.3011	1.2593	1.1222
No log	34.0	102	1.7762	0.2336	1.7758	1.3326
No log	35.0	105	1.3984	0.2849	1.3981	1.1824
No log	36.0	108	1.4557	0.2724	1.4554	1.2064
No log	37.0	111	0.9782	0.3926	0.9781	0.9890
No log	38.0	114	1.6398	0.2317	1.6395	1.2804
No log	39.0	117	1.5183	0.2442	1.5181	1.2321
No log	40.0	120	1.1179	0.3512	1.1178	1.0572
No log	41.0	123	1.7611	0.2203	1.7606	1.3269
No log	42.0	126	1.6201	0.2500	1.6197	1.2727
No log	43.0	129	0.7610	0.4956	0.7609	0.8723
No log	44.0	132	0.8869	0.4586	0.8868	0.9417
No log	45.0	135	1.9474	0.2136	1.9469	1.3953
No log	46.0	138	1.7729	0.2233	1.7726	1.3314
No log	47.0	141	1.0381	0.3820	1.0381	1.0189
No log	48.0	144	1.2253	0.3235	1.2253	1.1069
No log	49.0	147	1.3780	0.2867	1.3778	1.1738
No log	50.0	150	1.3069	0.3017	1.3068	1.1431
No log	51.0	153	1.2035	0.3372	1.2034	1.0970
No log	52.0	156	1.3612	0.2845	1.3611	1.1667
No log	53.0	159	0.9554	0.4047	0.9554	0.9774
No log	54.0	162	1.0488	0.3491	1.0487	1.0241
No log	55.0	165	1.3629	0.2894	1.3628	1.1674
No log	56.0	168	0.9352	0.3983	0.9353	0.9671
No log	57.0	171	1.1248	0.3512	1.1251	1.0607
No log	58.0	174	1.2077	0.3230	1.2078	1.0990

Framework versions

Transformers 4.47.0
Pytorch 2.5.1+cu121
Datasets 3.3.1
Tokenizers 0.21.0

genki10/Trial3BERT_AugV8_k3_task1_organization_sp010_lw020_fold3

Trial3BERT_AugV8_k3_task1_organization_sp010_lw020_fold3

Model description

Intended uses & limitations

Training and evaluation data

Training procedure

Training hyperparameters

Training results

Framework versions

genki10/
Trial3BERT_AugV8_k3_task1_organization_sp010_lw020_fold3