Modelpublic

jtatman/finetuning-twitter-finance-sentiment-distilbert

sourceHugging Faceapache-2.0updated 5mo agoView on Hugging Face

0likes11downloads

Model Card

finetuning-twitter-finance-sentiment-distilbert

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

—Loss: 1.1919
—Accuracy: 0.8617
—F1: 0.8608

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: 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: 20

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy	F1
No log	1.0	478	0.4181	0.8455	0.8442
0.5595	2.0	956	0.3985	0.8633	0.8615
0.3088	3.0	1434	0.5320	0.8544	0.8510
0.1747	4.0	1912	0.6241	0.8612	0.8589
0.0993	5.0	2390	0.7062	0.8601	0.8588
0.0669	6.0	2868	0.8449	0.8643	0.8621
0.0431	7.0	3346	0.8722	0.8591	0.8591
0.0279	8.0	3824	0.8808	0.8612	0.8611
0.0194	9.0	4302	1.0386	0.8476	0.8459
0.0165	10.0	4780	1.0698	0.8554	0.8524
0.0116	11.0	5258	1.0383	0.8669	0.8646
0.0059	12.0	5736	1.0721	0.8664	0.8649
0.0076	13.0	6214	1.1274	0.8559	0.8554
0.0062	14.0	6692	1.1637	0.8596	0.8587
0.0042	15.0	7170	1.1986	0.8617	0.8593
0.0030	16.0	7648	1.1985	0.8596	0.8578
0.0041	17.0	8126	1.2391	0.8628	0.8602
0.0025	18.0	8604	1.1915	0.8607	0.8599
0.0017	19.0	9082	1.2073	0.8633	0.8617
0.0008	20.0	9560	1.1919	0.8617	0.8608

Framework versions

—Transformers 5.0.0
—Pytorch 2.10.0+cu128
—Datasets 4.0.0
—Tokenizers 0.22.2