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	10.0792	0.0036	10.0792	3.1748
No log	2.0	2	8.9278	0.0	8.9278	2.9879
No log	3.0	3	8.1745	0.0	8.1745	2.8591
No log	4.0	4	7.6429	0.0	7.6429	2.7646
No log	5.0	5	7.2633	0.0	7.2633	2.6950
No log	6.0	6	6.9462	0.0	6.9462	2.6356
No log	7.0	7	6.5034	0.0	6.5034	2.5502
No log	8.0	8	6.0778	0.0004	6.0778	2.4653
No log	9.0	9	5.6882	0.0112	5.6882	2.3850
No log	10.0	10	5.2821	0.0115	5.2821	2.2983
No log	11.0	11	4.8817	0.0115	4.8817	2.2095
No log	12.0	12	4.5290	0.0039	4.5290	2.1281
No log	13.0	13	4.2435	0.0039	4.2435	2.0600
No log	14.0	14	3.8807	0.0	3.8807	1.9699
No log	15.0	15	3.4891	0.0	3.4891	1.8679
No log	16.0	16	3.1518	0.0	3.1518	1.7753
No log	17.0	17	2.8345	0.0	2.8345	1.6836
No log	18.0	18	2.5146	0.0610	2.5146	1.5857
No log	19.0	19	2.2406	0.1023	2.2406	1.4969
No log	20.0	20	2.0230	0.0689	2.0230	1.4223
No log	21.0	21	1.7872	0.0484	1.7872	1.3369
No log	22.0	22	1.5666	0.0316	1.5666	1.2516
No log	23.0	23	1.4124	0.0316	1.4124	1.1885
No log	24.0	24	1.2918	0.0316	1.2918	1.1366
No log	25.0	25	1.2230	0.0316	1.2230	1.1059
No log	26.0	26	1.1187	0.0316	1.1187	1.0577
No log	27.0	27	0.9915	0.0316	0.9915	0.9957
No log	28.0	28	0.8917	0.0316	0.8917	0.9443
No log	29.0	29	0.8244	0.3192	0.8244	0.9080
No log	30.0	30	0.7925	0.3781	0.7925	0.8902
No log	31.0	31	0.8180	0.2870	0.8180	0.9044
No log	32.0	32	0.7150	0.4322	0.7150	0.8456
No log	33.0	33	0.6521	0.3544	0.6521	0.8075
No log	34.0	34	0.6408	0.3327	0.6408	0.8005
No log	35.0	35	0.5893	0.3934	0.5893	0.7676
No log	36.0	36	0.5874	0.4755	0.5874	0.7664
No log	37.0	37	0.5655	0.4940	0.5655	0.7520
No log	38.0	38	0.5182	0.4634	0.5182	0.7198
No log	39.0	39	0.5028	0.4594	0.5028	0.7091
No log	40.0	40	0.4931	0.4728	0.4931	0.7022
No log	41.0	41	0.4981	0.5249	0.4981	0.7057
No log	42.0	42	0.4853	0.5302	0.4853	0.6966
No log	43.0	43	0.4808	0.5007	0.4808	0.6934
No log	44.0	44	0.4803	0.5308	0.4803	0.6930
No log	45.0	45	0.4824	0.5391	0.4824	0.6945
No log	46.0	46	0.4923	0.5757	0.4923	0.7016
No log	47.0	47	0.4966	0.5986	0.4966	0.7047
No log	48.0	48	0.4860	0.6301	0.4860	0.6971
No log	49.0	49	0.4896	0.6521	0.4896	0.6997
No log	50.0	50	0.4908	0.6494	0.4908	0.7006
No log	51.0	51	0.4963	0.6679	0.4963	0.7045
No log	52.0	52	0.4995	0.6508	0.4995	0.7068
No log	53.0	53	0.4745	0.6616	0.4745	0.6888
No log	54.0	54	0.4697	0.6621	0.4697	0.6853
No log	55.0	55	0.5053	0.6509	0.5053	0.7108
No log	56.0	56	0.4823	0.6505	0.4823	0.6945
No log	57.0	57	0.4819	0.6600	0.4819	0.6942
No log	58.0	58	0.4731	0.6560	0.4731	0.6878
No log	59.0	59	0.4898	0.6665	0.4898	0.6998
No log	60.0	60	0.5554	0.6493	0.5554	0.7453
No log	61.0	61	0.5383	0.6546	0.5383	0.7337
No log	62.0	62	0.4944	0.6711	0.4944	0.7031
No log	63.0	63	0.4855	0.6615	0.4855	0.6967
No log	64.0	64	0.5286	0.6394	0.5286	0.7270
No log	65.0	65	0.5080	0.6517	0.5080	0.7127
No log	66.0	66	0.5364	0.6409	0.5364	0.7324
No log	67.0	67	0.4963	0.6525	0.4963	0.7045
No log	68.0	68	0.4912	0.6351	0.4912	0.7009
No log	69.0	69	0.5065	0.6389	0.5065	0.7117
No log	70.0	70	0.5125	0.6661	0.5125	0.7159
No log	71.0	71	0.5237	0.6650	0.5237	0.7237
No log	72.0	72	0.5725	0.6488	0.5725	0.7567
No log	73.0	73	0.5646	0.6555	0.5646	0.7514
No log	74.0	74	0.5134	0.6702	0.5134	0.7165
No log	75.0	75	0.4951	0.6622	0.4951	0.7036
No log	76.0	76	0.4889	0.6569	0.4889	0.6992
No log	77.0	77	0.5081	0.6529	0.5081	0.7128
No log	78.0	78	0.5764	0.6311	0.5764	0.7592
No log	79.0	79	0.5854	0.6292	0.5854	0.7651
No log	80.0	80	0.5370	0.6624	0.5370	0.7328
No log	81.0	81	0.4891	0.6540	0.4891	0.6994
No log	82.0	82	0.4832	0.6542	0.4832	0.6951

Framework versions

Transformers 4.47.0
Pytorch 2.5.1+cu121
Datasets 3.2.0
Tokenizers 0.21.0

genki10/Version3ASAP_FineTuningBERT_AugV12_k1_task1_organization_k1_k1_fold0

Version3ASAP_FineTuningBERT_AugV12_k1_task1_organization_k1_k1_fold0

Model description

Intended uses & limitations

Training and evaluation data

Training procedure

Training hyperparameters

Training results

Framework versions

genki10/
Version3ASAP_FineTuningBERT_AugV12_k1_task1_organization_k1_k1_fold0