Modelpublic

genki10/Version_Test_ASAP_FineTuningBERT_AugV14_k5_task1_organization_k5_k5_fold3

sourceHugging Faceapache-2.0updated 2y agoView on Hugging Face

0likes3downloads

Model Card

VersionTestASAPFineTuningBERTAugV14k5task1organizationk5k5fold3

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: 0.6467
—Qwk: 0.6250
—Mse: 0.6468
—Rmse: 0.8043

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	8.4387	0.0	8.4370	2.9046
No log	2.0	8	6.0886	0.0536	6.0872	2.4672
No log	3.0	12	4.2058	0.0	4.2047	2.0505
No log	4.0	16	2.6833	-0.0011	2.6823	1.6378
No log	5.0	20	1.7248	0.0302	1.7241	1.3130
No log	6.0	24	1.1400	0.0	1.1394	1.0674
No log	7.0	28	0.8742	0.1899	0.8737	0.9347
No log	8.0	32	0.8764	0.0570	0.8760	0.9360
No log	9.0	36	0.8376	0.1641	0.8376	0.9152
No log	10.0	40	0.6280	0.5344	0.6281	0.7925
No log	11.0	44	0.5942	0.6180	0.5944	0.7709
No log	12.0	48	0.6831	0.6061	0.6833	0.8266
No log	13.0	52	0.7694	0.5319	0.7696	0.8773
No log	14.0	56	0.5474	0.6590	0.5475	0.7399
No log	15.0	60	0.5619	0.5923	0.5620	0.7497
No log	16.0	64	0.5327	0.6157	0.5329	0.7300
No log	17.0	68	0.5314	0.6285	0.5315	0.7290
No log	18.0	72	0.6020	0.5932	0.6022	0.7760
No log	19.0	76	0.5508	0.6418	0.5510	0.7423
No log	20.0	80	0.5244	0.6523	0.5246	0.7243
No log	21.0	84	0.5931	0.6042	0.5931	0.7701
No log	22.0	88	0.5891	0.6293	0.5893	0.7676
No log	23.0	92	0.6425	0.6414	0.6426	0.8016
No log	24.0	96	0.5954	0.6487	0.5955	0.7717
No log	25.0	100	0.5923	0.6589	0.5923	0.7696
No log	26.0	104	0.5614	0.6619	0.5614	0.7493
No log	27.0	108	0.5410	0.6735	0.5410	0.7355
No log	28.0	112	0.5847	0.6522	0.5846	0.7646
No log	29.0	116	0.5488	0.6425	0.5489	0.7409
No log	30.0	120	0.6433	0.6269	0.6432	0.8020
No log	31.0	124	0.5887	0.6546	0.5887	0.7673
No log	32.0	128	0.5463	0.6315	0.5464	0.7392
No log	33.0	132	0.5668	0.6418	0.5669	0.7529
No log	34.0	136	0.5750	0.6403	0.5751	0.7584
No log	35.0	140	0.5550	0.6423	0.5550	0.7450
No log	36.0	144	0.5474	0.6301	0.5475	0.7399
No log	37.0	148	0.6727	0.6316	0.6726	0.8201
No log	38.0	152	0.6734	0.5700	0.6736	0.8208
No log	39.0	156	0.9281	0.5488	0.9280	0.9633
No log	40.0	160	0.5880	0.6385	0.5880	0.7668
No log	41.0	164	0.5692	0.6386	0.5693	0.7545
No log	42.0	168	0.5863	0.6228	0.5865	0.7658
No log	43.0	172	0.5682	0.6523	0.5683	0.7539
No log	44.0	176	0.5621	0.6357	0.5622	0.7498
No log	45.0	180	0.7136	0.5947	0.7137	0.8448
No log	46.0	184	0.5941	0.6241	0.5943	0.7709
No log	47.0	188	0.6467	0.6250	0.6468	0.8043

Framework versions

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