Modelpublic

XiaPinJohnKe/test-trainer

sourceHugging Faceapache-2.0updated 10mo agoView on Hugging Face

0likes169downloads

Model Card

test-trainer

This model is a fine-tuned version of bert-base-uncased on an unknown dataset. It achieves the following results on the evaluation set:

—Loss: 0.5037
—Accuracy: 0.7794
—F1: 0.8534

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: 1.5e-06
—trainbatchsize: 32
—evalbatchsize: 32
—seed: 42
—optimizer: Use OptimizerNames.ADAMWTORCHFUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
—lrschedulertype: linear
—num_epochs: 12.0

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy	F1
0.8051	0.8696	100	0.6291	0.6838	0.8122
0.6129	1.7391	200	0.5857	0.6912	0.8158
0.587	2.6087	300	0.5586	0.7034	0.8207
0.5516	3.4783	400	0.5361	0.7132	0.8235
0.5423	4.3478	500	0.5208	0.7279	0.8290
0.5153	5.2174	600	0.5096	0.7451	0.8344
0.4977	6.0870	700	0.5098	0.75	0.8376
0.4968	6.9565	800	0.5057	0.7574	0.8411
0.4818	7.8261	900	0.5051	0.7647	0.8452
0.4719	8.6957	1000	0.5031	0.7770	0.8520
0.4674	9.5652	1100	0.5046	0.7794	0.8539
0.4624	10.4348	1200	0.5033	0.7794	0.8534
0.4555	11.3043	1300	0.5037	0.7794	0.8534

Framework versions

—Transformers 4.57.2
—Pytorch 2.9.0+cu126
—Datasets 4.0.0
—Tokenizers 0.22.1