Modelpublic

PathofthePeople/TrainedSentiment

sourceHugging Faceapache-2.0updated 2y agoView on Hugging Face

0likes5downloads

Model Card

TrainedSentiment

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: 0.0299
—Accuracy: 0.9833

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: Adam with betas=(0.9,0.999) and epsilon=1e-08
—lrschedulertype: linear
—num_epochs: 20

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
No log	1.0	38	0.6023	0.6233
No log	2.0	76	0.4643	0.7883
No log	3.0	114	0.4152	0.8233
No log	4.0	152	0.2017	0.93
No log	5.0	190	0.1128	0.9617
No log	6.0	228	0.0679	0.9767
No log	7.0	266	0.0548	0.9783
No log	8.0	304	0.0476	0.98
No log	9.0	342	0.0460	0.9817
No log	10.0	380	0.0414	0.9833
No log	11.0	418	0.0414	0.9817
No log	12.0	456	0.0387	0.9817
No log	13.0	494	0.0377	0.9833
0.2188	14.0	532	0.0353	0.9833
0.2188	15.0	570	0.0329	0.9833
0.2188	16.0	608	0.0314	0.985
0.2188	17.0	646	0.0308	0.985
0.2188	18.0	684	0.0300	0.985
0.2188	19.0	722	0.0297	0.985
0.2188	20.0	760	0.0299	0.9833

Framework versions

—Transformers 4.32.1
—Pytorch 2.3.0+cu121
—Datasets 2.12.0
—Tokenizers 0.13.2