Modelpublic

genki10/Version_Test_ASAP_FineTuningBERT_AugV14_k1_task1_organization_k1_k1_fold0

sourceHugging Faceapache-2.0updated 2y agoView on Hugging Face

0likes3downloads

Model Card

VersionTestASAPFineTuningBERTAugV14k1task1organizationk1k1fold0

This model is a fine-tuned version of bert-base-uncased on the None dataset. It achieves the following results on the evaluation set:

—Loss: 0.6221
—Qwk: 0.5802
—Mse: 0.6221
—Rmse: 0.7887

Model description

More information needed

Intended uses & limitations

More information needed

Training and evaluation data

More information needed

Training procedure

Training hyperparameters

The following hyperparameters were used during training:

—learning_rate: 2e-05
—trainbatchsize: 64
—evalbatchsize: 64
—seed: 42
—optimizer: Use adamwtorch with betas=(0.9,0.999) and epsilon=1e-08 and optimizerargs=No additional optimizer arguments
—lrschedulertype: linear
—num_epochs: 100

Training results

Training Loss	Epoch	Step	Validation Loss	Qwk	Mse	Rmse
No log	1.0	2	9.6887	0.0056	9.6887	3.1127
No log	2.0	4	7.2573	0.0	7.2573	2.6939
No log	3.0	6	6.1284	0.0376	6.1284	2.4756
No log	4.0	8	4.0163	0.0115	4.0163	2.0041
No log	5.0	10	3.1802	0.0115	3.1802	1.7833
No log	6.0	12	2.1477	0.1379	2.1477	1.4655
No log	7.0	14	1.7331	0.0583	1.7331	1.3165
No log	8.0	16	1.4636	0.0419	1.4636	1.2098
No log	9.0	18	1.1101	0.0419	1.1101	1.0536
No log	10.0	20	0.8784	0.1127	0.8784	0.9372
No log	11.0	22	0.7659	0.2863	0.7659	0.8752
No log	12.0	24	0.7276	0.1724	0.7276	0.8530
No log	13.0	26	0.6972	0.1652	0.6972	0.8350
No log	14.0	28	0.6612	0.2078	0.6612	0.8131
No log	15.0	30	0.5798	0.3170	0.5798	0.7614
No log	16.0	32	0.5824	0.4912	0.5824	0.7631
No log	17.0	34	0.6057	0.5244	0.6057	0.7783
No log	18.0	36	0.5687	0.4652	0.5687	0.7541
No log	19.0	38	0.6198	0.4583	0.6198	0.7872
No log	20.0	40	0.5883	0.5658	0.5883	0.7670
No log	21.0	42	0.8473	0.4782	0.8473	0.9205
No log	22.0	44	0.6963	0.5400	0.6963	0.8344
No log	23.0	46	0.6370	0.5533	0.6370	0.7981
No log	24.0	48	0.7032	0.5172	0.7032	0.8386
No log	25.0	50	0.5278	0.5286	0.5278	0.7265
No log	26.0	52	0.5625	0.5504	0.5625	0.7500
No log	27.0	54	0.5055	0.5761	0.5055	0.7110
No log	28.0	56	0.5833	0.5803	0.5833	0.7637
No log	29.0	58	0.5375	0.6108	0.5375	0.7331
No log	30.0	60	0.5190	0.5993	0.5190	0.7204
No log	31.0	62	0.5756	0.5950	0.5756	0.7587
No log	32.0	64	0.6691	0.5513	0.6691	0.8180
No log	33.0	66	0.5189	0.6120	0.5189	0.7204
No log	34.0	68	0.5225	0.6017	0.5225	0.7229
No log	35.0	70	0.5925	0.5768	0.5925	0.7697
No log	36.0	72	0.6192	0.5803	0.6192	0.7869
No log	37.0	74	0.5648	0.6150	0.5648	0.7515
No log	38.0	76	0.6529	0.5755	0.6529	0.8080
No log	39.0	78	0.6343	0.5876	0.6343	0.7964
No log	40.0	80	0.6349	0.6045	0.6349	0.7968
No log	41.0	82	0.6605	0.5847	0.6605	0.8127
No log	42.0	84	0.6486	0.5951	0.6486	0.8053
No log	43.0	86	0.6973	0.5744	0.6973	0.8351
No log	44.0	88	0.9177	0.5138	0.9177	0.9580
No log	45.0	90	0.7331	0.5506	0.7331	0.8562
No log	46.0	92	0.7349	0.5550	0.7349	0.8573
No log	47.0	94	0.8854	0.5078	0.8854	0.9410
No log	48.0	96	0.7441	0.5407	0.7441	0.8626
No log	49.0	98	0.7021	0.5863	0.7021	0.8379
No log	50.0	100	0.8005	0.5552	0.8005	0.8947
No log	51.0	102	0.8081	0.5631	0.8081	0.8989
No log	52.0	104	0.6907	0.5890	0.6907	0.8311
No log	53.0	106	0.6859	0.6009	0.6859	0.8282
No log	54.0	108	0.7496	0.5834	0.7496	0.8658
No log	55.0	110	0.6285	0.5876	0.6285	0.7928
No log	56.0	112	0.6160	0.5768	0.6160	0.7848
No log	57.0	114	0.6221	0.5802	0.6221	0.7887

Framework versions

—Transformers 4.47.0
—Pytorch 2.5.1+cu121
—Datasets 3.2.0
—Tokenizers 0.21.0