Modelpublic

minoosh/finetuned_roberta-base-on-IEMOCAP_3

sourceHugging Faceupdated 3y agoView on Hugging Face

0likes11downloads

Model Card

finetunedroberta-base-on-IEMOCAP3

This model is a fine-tuned version of cardiffnlp/twitter-roberta-base-emotion on an unknown dataset. It achieves the following results on the evaluation set:

—Loss: 1.0811
—Accuracy: 0.6481

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: 32
—evalbatchsize: 32
—seed: 42
—optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
—lrschedulertype: linear
—num_epochs: 15

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
0.8961	1.0	110	0.8901	0.6435
0.7964	2.0	220	0.8135	0.6731
0.6132	3.0	330	0.8108	0.6993
0.3977	4.0	440	0.8360	0.7198
0.308	5.0	550	0.8994	0.6982
0.264	6.0	660	1.0231	0.6970
0.2477	7.0	770	1.0716	0.6993
0.1822	8.0	880	1.0890	0.6970
0.1438	9.0	990	1.1732	0.7039
0.1445	10.0	1100	1.2182	0.6902
0.1143	11.0	1210	1.2504	0.6993
0.1266	12.0	1320	1.3046	0.6970
0.094	13.0	1430	1.3148	0.7130
0.0985	14.0	1540	1.3253	0.7175
0.0947	15.0	1650	1.3411	0.7118

Framework versions

—Transformers 4.34.0
—Pytorch 2.0.1+cu118
—Datasets 2.14.5
—Tokenizers 0.14.1