Modelpublic

genki10/Version_Test_ASAP_FineTuningBERT_AugV14_k5_task1_organization_k5_k5_fold1

sourceHugging Faceapache-2.0updated 2y agoView on Hugging Face

0likes2downloads

Model Card

VersionTestASAPFineTuningBERTAugV14k5task1organizationk5k5fold1

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: 0.7436
—Qwk: 0.5892
—Mse: 0.7430
—Rmse: 0.8620

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	4	7.6442	0.0	7.6417	2.7644
No log	2.0	8	4.2129	0.0191	4.2108	2.0520
No log	3.0	12	2.3820	0.0517	2.3801	1.5428
No log	4.0	16	1.3807	0.0418	1.3791	1.1744
No log	5.0	20	1.0839	-0.0014	1.0828	1.0406
No log	6.0	24	0.8269	0.2314	0.8257	0.9087
No log	7.0	28	1.0063	0.0571	1.0054	1.0027
No log	8.0	32	0.7084	0.2313	0.7075	0.8411
No log	9.0	36	0.6095	0.4046	0.6087	0.7802
No log	10.0	40	0.4894	0.5973	0.4886	0.6990
No log	11.0	44	0.4988	0.5953	0.4979	0.7057
No log	12.0	48	0.4515	0.6543	0.4508	0.6714
No log	13.0	52	0.7950	0.5421	0.7944	0.8913
No log	14.0	56	0.4800	0.6436	0.4789	0.6921
No log	15.0	60	0.4691	0.6304	0.4681	0.6842
No log	16.0	64	0.5950	0.5981	0.5940	0.7707
No log	17.0	68	0.6786	0.5884	0.6778	0.8233
No log	18.0	72	0.5584	0.6398	0.5577	0.7468
No log	19.0	76	0.5286	0.6318	0.5276	0.7264
No log	20.0	80	0.8446	0.5061	0.8438	0.9186
No log	21.0	84	0.6494	0.6055	0.6486	0.8054
No log	22.0	88	0.5859	0.6223	0.5851	0.7649
No log	23.0	92	0.5458	0.5943	0.5450	0.7382
No log	24.0	96	0.5456	0.6208	0.5448	0.7381
No log	25.0	100	0.5912	0.6131	0.5904	0.7684
No log	26.0	104	0.7743	0.5674	0.7737	0.8796
No log	27.0	108	0.5610	0.6295	0.5604	0.7486
No log	28.0	112	0.5330	0.6314	0.5322	0.7295
No log	29.0	116	0.7874	0.5398	0.7868	0.8870
No log	30.0	120	0.7254	0.6040	0.7248	0.8513
No log	31.0	124	0.5510	0.6407	0.5503	0.7418
No log	32.0	128	0.7436	0.5892	0.7430	0.8620

Framework versions

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