Modelpublic

genki10/ASAP_FineTuningBERT_UnAugV7_k1_task1_organization_k1_k1_fold3

sourceHugging Faceapache-2.0updated 2y agoView on Hugging Face

0likes

Model Card

ASAPFineTuningBERTUnAugV7k1task1organizationk1k1fold3

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: 2.1270
—Qwk: 0.0374
—Mse: 2.1263
—Rmse: 1.4582

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	1	13.8595	-0.0011	13.8578	3.7226
No log	2.0	2	10.0654	0.0047	10.0639	3.1724
No log	3.0	3	9.5908	0.0018	9.5891	3.0966
No log	4.0	4	9.1866	0.0	9.1848	3.0307
No log	5.0	5	8.7108	0.0	8.7091	2.9511
No log	6.0	6	8.2242	0.0	8.2226	2.8675
No log	7.0	7	7.7083	0.0	7.7067	2.7761
No log	8.0	8	7.1433	0.0	7.1418	2.6724
No log	9.0	9	6.5056	0.0	6.5042	2.5503
No log	10.0	10	5.8066	0.0554	5.8052	2.4094
No log	11.0	11	5.2442	0.0069	5.2428	2.2897
No log	12.0	12	4.9310	0.0022	4.9297	2.2203
No log	13.0	13	4.2875	0.0	4.2863	2.0703
No log	14.0	14	3.9747	0.0	3.9736	1.9934
No log	15.0	15	3.7456	0.0	3.7445	1.9351
No log	16.0	16	3.4377	0.0	3.4367	1.8538
No log	17.0	17	3.0401	0.0	3.0391	1.7433
No log	18.0	18	2.5682	0.0448	2.5673	1.6023
No log	19.0	19	2.4585	0.0432	2.4577	1.5677
No log	20.0	20	2.1270	0.0374	2.1263	1.4582

Framework versions

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