Modelpublic

genki10/Version_Test_ASAP_FineTuningBERT_AugV14_k10_task1_organization_k10_k10_fold3

sourceHugging Faceapache-2.0updated 2y agoView on Hugging Face

0likes1downloads

Model Card

VersionTestASAPFineTuningBERTAugV14k10task1organizationk10k10fold3

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: 0.6326
—Qwk: 0.6136
—Mse: 0.6324
—Rmse: 0.7952

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	7	6.1888	0.0125	6.1875	2.4875
No log	2.0	14	2.4193	0.1090	2.4184	1.5551
No log	3.0	21	1.0990	0.0	1.0984	1.0481
No log	4.0	28	0.8947	0.0314	0.8944	0.9457
No log	5.0	35	1.2837	0.2563	1.2836	1.1330
No log	6.0	42	0.9119	0.3718	0.9118	0.9549
No log	7.0	49	0.8044	0.4539	0.8042	0.8968
No log	8.0	56	0.5419	0.6029	0.5414	0.7358
No log	9.0	63	0.5201	0.6524	0.5197	0.7209
No log	10.0	70	0.6080	0.6202	0.6077	0.7795
No log	11.0	77	0.5384	0.6597	0.5382	0.7336
No log	12.0	84	0.5354	0.6486	0.5351	0.7315
No log	13.0	91	0.5673	0.6741	0.5670	0.7530
No log	14.0	98	0.5337	0.6080	0.5336	0.7305
No log	15.0	105	0.5707	0.6237	0.5706	0.7554
No log	16.0	112	0.6875	0.6039	0.6873	0.8290
No log	17.0	119	0.6650	0.6013	0.6646	0.8152
No log	18.0	126	0.5925	0.6668	0.5921	0.7695
No log	19.0	133	0.7376	0.5835	0.7374	0.8587
No log	20.0	140	0.9780	0.5314	0.9779	0.9889
No log	21.0	147	0.5658	0.6118	0.5655	0.7520
No log	22.0	154	0.5561	0.6352	0.5559	0.7456
No log	23.0	161	0.5953	0.6302	0.5950	0.7714
No log	24.0	168	0.5591	0.6470	0.5588	0.7475
No log	25.0	175	0.6125	0.5999	0.6123	0.7825
No log	26.0	182	0.5468	0.5738	0.5465	0.7393
No log	27.0	189	0.5549	0.6257	0.5546	0.7447
No log	28.0	196	0.5291	0.5987	0.5288	0.7272
No log	29.0	203	0.5544	0.6707	0.5542	0.7444
No log	30.0	210	0.5448	0.6283	0.5444	0.7379
No log	31.0	217	0.5417	0.6335	0.5414	0.7358
No log	32.0	224	0.5455	0.6266	0.5451	0.7383
No log	33.0	231	0.6326	0.6136	0.6324	0.7952

Framework versions

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