Modelpublic

genki10/Version_Test_ASAP_FineTuningBERT_AugV14_k1_task1_organization_k1_k1_fold1

sourceHugging Faceapache-2.0updated 2y agoView on Hugging Face

0likes1downloads

Model Card

VersionTestASAPFineTuningBERTAugV14k1task1organizationk1k1fold1

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: 0.5467
—Qwk: 0.6606
—Mse: 0.5460
—Rmse: 0.7389

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	9.4276	0.0071	9.4250	3.0700
No log	2.0	4	7.6910	0.0	7.6887	2.7729
No log	3.0	6	6.6100	0.0	6.6076	2.5705
No log	4.0	8	5.6193	0.0251	5.6171	2.3700
No log	5.0	10	4.2055	0.0118	4.2033	2.0502
No log	6.0	12	3.1511	0.0	3.1492	1.7746
No log	7.0	14	2.5306	0.0631	2.5287	1.5902
No log	8.0	16	1.9104	0.1300	1.9087	1.3815
No log	9.0	18	1.5468	0.0482	1.5451	1.2430
No log	10.0	20	1.2976	0.0315	1.2961	1.1385
No log	11.0	22	1.0645	0.0106	1.0630	1.0310
No log	12.0	24	0.9105	0.0970	0.9091	0.9535
No log	13.0	26	0.8993	0.1222	0.8980	0.9476
No log	14.0	28	0.9768	0.0500	0.9757	0.9878
No log	15.0	30	0.8901	0.0713	0.8891	0.9429
No log	16.0	32	0.6796	0.3826	0.6785	0.8237
No log	17.0	34	0.6125	0.4585	0.6114	0.7820
No log	18.0	36	0.6242	0.3413	0.6233	0.7895
No log	19.0	38	0.5227	0.4383	0.5219	0.7224
No log	20.0	40	0.4881	0.5922	0.4873	0.6981
No log	21.0	42	0.5733	0.5945	0.5725	0.7567
No log	22.0	44	0.4660	0.6316	0.4653	0.6821
No log	23.0	46	0.4607	0.7170	0.4601	0.6783
No log	24.0	48	0.4547	0.7062	0.4540	0.6738
No log	25.0	50	0.5672	0.6640	0.5666	0.7527
No log	26.0	52	0.5305	0.6646	0.5297	0.7278
No log	27.0	54	0.4908	0.6909	0.4900	0.7000
No log	28.0	56	1.4321	0.3747	1.4316	1.1965
No log	29.0	58	1.7818	0.2654	1.7813	1.3346
No log	30.0	60	0.9834	0.4707	0.9828	0.9913
No log	31.0	62	0.4568	0.6873	0.4560	0.6752
No log	32.0	64	0.4486	0.7048	0.4478	0.6692
No log	33.0	66	0.7104	0.5923	0.7098	0.8425
No log	34.0	68	0.7871	0.5641	0.7865	0.8868
No log	35.0	70	0.5207	0.6953	0.5200	0.7211
No log	36.0	72	0.5976	0.6464	0.5967	0.7725
No log	37.0	74	0.6912	0.6006	0.6904	0.8309
No log	38.0	76	0.4499	0.6787	0.4492	0.6703
No log	39.0	78	0.9081	0.5488	0.9075	0.9526
No log	40.0	80	0.9073	0.5216	0.9067	0.9522
No log	41.0	82	0.5003	0.6537	0.4995	0.7068
No log	42.0	84	0.4349	0.6636	0.4341	0.6589
No log	43.0	86	0.5467	0.6606	0.5460	0.7389

Framework versions

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