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	10.2241	0.0016	10.2213	3.1971
No log	2.0	2	8.9231	0.0	8.9203	2.9867
No log	3.0	3	8.2520	0.0	8.2493	2.8722
No log	4.0	4	7.6810	0.0	7.6785	2.7710
No log	5.0	5	6.9367	0.0	6.9342	2.6333
No log	6.0	6	6.1118	-0.0012	6.1094	2.4717
No log	7.0	7	5.4755	0.0220	5.4732	2.3395
No log	8.0	8	4.9072	0.0128	4.9050	2.2147
No log	9.0	9	4.5674	0.0050	4.5652	2.1366
No log	10.0	10	4.0050	0.0	4.0029	2.0007
No log	11.0	11	3.4971	0.0	3.4951	1.8695
No log	12.0	12	3.1792	0.0	3.1774	1.7825
No log	13.0	13	2.8023	0.0	2.8006	1.6735
No log	14.0	14	2.4070	0.0069	2.4052	1.5509
No log	15.0	15	2.1771	0.1350	2.1752	1.4748
No log	16.0	16	1.9524	0.0737	1.9506	1.3967
No log	17.0	17	1.7854	0.0418	1.7837	1.3356
No log	18.0	18	1.5615	0.0211	1.5598	1.2489
No log	19.0	19	1.3933	0.0211	1.3916	1.1797
No log	20.0	20	1.2586	0.0211	1.2569	1.1211
No log	21.0	21	1.1364	0.0106	1.1349	1.0653
No log	22.0	22	1.0709	0.0106	1.0693	1.0341
No log	23.0	23	0.9550	0.0	0.9536	0.9765
No log	24.0	24	0.9007	0.0628	0.8994	0.9484
No log	25.0	25	0.8401	0.2773	0.8386	0.9158
No log	26.0	26	0.7927	0.3270	0.7913	0.8895
No log	27.0	27	0.7613	0.3684	0.7600	0.8718
No log	28.0	28	0.7159	0.3933	0.7146	0.8454
No log	29.0	29	0.6833	0.4083	0.6820	0.8258
No log	30.0	30	0.6443	0.4239	0.6429	0.8018
No log	31.0	31	0.6146	0.4290	0.6133	0.7832
No log	32.0	32	0.7136	0.3145	0.7125	0.8441
No log	33.0	33	0.6919	0.3835	0.6908	0.8311
No log	34.0	34	0.5386	0.4784	0.5374	0.7331
No log	35.0	35	0.5378	0.5290	0.5366	0.7326
No log	36.0	36	0.5035	0.5310	0.5024	0.7088
No log	37.0	37	0.5509	0.4953	0.5499	0.7415
No log	38.0	38	0.5815	0.4867	0.5806	0.7619
No log	39.0	39	0.4798	0.5324	0.4788	0.6920
No log	40.0	40	0.4949	0.5987	0.4939	0.7028
No log	41.0	41	0.4831	0.6515	0.4821	0.6943
No log	42.0	42	0.4786	0.6403	0.4777	0.6912
No log	43.0	43	0.5689	0.6067	0.5682	0.7538
No log	44.0	44	0.5334	0.6308	0.5327	0.7299
No log	45.0	45	0.4586	0.6737	0.4578	0.6766
No log	46.0	46	0.4582	0.6741	0.4574	0.6763
No log	47.0	47	0.5098	0.6470	0.5091	0.7135
No log	48.0	48	0.5650	0.6318	0.5645	0.7513
No log	49.0	49	0.4985	0.6460	0.4979	0.7056
No log	50.0	50	0.5054	0.6484	0.5049	0.7105
No log	51.0	51	0.5661	0.6549	0.5656	0.7521
No log	52.0	52	0.5131	0.6490	0.5126	0.7159
No log	53.0	53	0.4776	0.6812	0.4770	0.6907
No log	54.0	54	0.4857	0.6828	0.4851	0.6965
No log	55.0	55	0.5969	0.6528	0.5965	0.7723
No log	56.0	56	0.6838	0.6299	0.6835	0.8267
No log	57.0	57	0.5963	0.6566	0.5959	0.7720
No log	58.0	58	0.4931	0.6851	0.4926	0.7019
No log	59.0	59	0.4884	0.6800	0.4879	0.6985
No log	60.0	60	0.5639	0.6579	0.5635	0.7507
No log	61.0	61	0.8053	0.6019	0.8052	0.8973
No log	62.0	62	0.8702	0.5877	0.8700	0.9327
No log	63.0	63	0.7335	0.6295	0.7333	0.8563
No log	64.0	64	0.5311	0.6660	0.5306	0.7284
No log	65.0	65	0.5007	0.6666	0.5002	0.7072
No log	66.0	66	0.5329	0.6704	0.5324	0.7297
No log	67.0	67	0.6487	0.6387	0.6484	0.8052
No log	68.0	68	0.6763	0.6235	0.6760	0.8222
No log	69.0	69	0.7333	0.6204	0.7332	0.8563
No log	70.0	70	0.6484	0.6445	0.6482	0.8051
No log	71.0	71	0.5737	0.6700	0.5734	0.7572
No log	72.0	72	0.5836	0.6555	0.5834	0.7638
No log	73.0	73	0.6731	0.6402	0.6730	0.8203
No log	74.0	74	0.7062	0.6150	0.7061	0.8403
No log	75.0	75	0.6335	0.6320	0.6332	0.7957
No log	76.0	76	0.5416	0.6649	0.5412	0.7357
No log	77.0	77	0.5333	0.6679	0.5329	0.7300
No log	78.0	78	0.5764	0.6473	0.5760	0.7590

Framework versions

Transformers 4.47.0
Pytorch 2.5.1+cu121
Datasets 3.3.1
Tokenizers 0.21.0

genki10/Version11ASAP_FineTuningBERT_AugV12_k1_task1_organization_k1_k1_fold1

Version11ASAP_FineTuningBERT_AugV12_k1_task1_organization_k1_k1_fold1

Model description

Intended uses & limitations

Training and evaluation data

Training procedure

Training hyperparameters

Training results

Framework versions

genki10/
Version11ASAP_FineTuningBERT_AugV12_k1_task1_organization_k1_k1_fold1