Modelpublic

ANGKJ1995/generic-course-prediction-12062026

sourceHugging Faceapache-2.0updated 4mo agoView on Hugging Face

0likes6downloads

Model Card

myawesomemodel

This model is a fine-tuned version of distilbert/distilbert-base-uncased on the None dataset. It achieves the following results on the evaluation set:

—Loss: 0.9340
—F1: 0.7508

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: 16
—evalbatchsize: 16
—seed: 123
—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: 30
—mixedprecisiontraining: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	F1
0.3199	1.0	1408	0.2834	0.6815
0.2423	2.0	2816	0.2862	0.6955
0.1847	3.0	4224	0.3313	0.7126
0.1411	4.0	5632	0.3398	0.7236
0.1205	5.0	7040	0.4494	0.7317
0.0877	6.0	8448	0.4884	0.7301
0.0780	7.0	9856	0.5614	0.7311
0.0620	8.0	11264	0.5494	0.7258
0.0521	9.0	12672	0.6617	0.7215
0.0423	10.0	14080	0.6533	0.7371
0.0329	11.0	15488	0.7038	0.7217
0.0292	12.0	16896	0.7464	0.7322
0.0301	13.0	18304	0.6408	0.7376
0.0257	14.0	19712	0.7520	0.7343
0.0222	15.0	21120	0.7650	0.7379
0.0134	16.0	22528	0.8251	0.7365
0.0218	17.0	23936	0.7849	0.7407
0.0186	18.0	25344	0.7665	0.7385
0.0086	19.0	26752	0.7849	0.7480
0.0098	20.0	28160	0.8165	0.7454
0.0084	21.0	29568	0.8955	0.7432
0.0082	22.0	30976	0.8867	0.7415
0.0038	23.0	32384	0.8941	0.7482
0.0040	24.0	33792	0.9198	0.7461
0.0030	25.0	35200	0.9340	0.7508
0.0048	26.0	36608	0.9430	0.7423
0.0036	27.0	38016	0.9477	0.7450
0.0042	28.0	39424	0.9695	0.7474
0.0003	29.0	40832	0.9826	0.7472
0.0010	30.0	42240	0.9860	0.7482

Framework versions

—Transformers 5.10.1
—Pytorch 2.11.0+cu128
—Datasets 4.0.0
—Tokenizers 0.22.2