Modelpublic

jayanta/ProsusAI-finbert-sentiment-finetuned-memes

sourceHugging Faceupdated 4y agoView on Hugging Face

0likes24downloads

Model Card

ProsusAI-finbert-sentiment-finetuned-memes

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

—Loss: 1.3093
—Accuracy: 0.8407
—Precision: 0.8412
—Recall: 0.8407
—F1: 0.8409

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: 8
—evalbatchsize: 8
—seed: 42
—optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
—lrschedulertype: linear
—num_epochs: 10

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy	Precision	Recall	F1
0.467	1.0	2147	0.4178	0.7898	0.7882	0.7898	0.7883
0.3669	2.0	4294	0.4876	0.7940	0.8073	0.7940	0.7961
0.2801	3.0	6441	0.6222	0.8040	0.8034	0.8040	0.8037
0.2402	4.0	8588	0.8062	0.8229	0.8219	0.8229	0.8211
0.2099	5.0	10735	0.9219	0.8197	0.8263	0.8197	0.8211
0.16	6.0	12882	1.0393	0.8312	0.8342	0.8312	0.8321
0.1192	7.0	15029	1.1263	0.8333	0.8337	0.8333	0.8335
0.0979	8.0	17176	1.2048	0.8328	0.8324	0.8328	0.8326
0.0691	9.0	19323	1.2891	0.8323	0.8327	0.8323	0.8325
0.0458	10.0	21470	1.3093	0.8407	0.8412	0.8407	0.8409

Framework versions

—Transformers 4.13.0.dev0
—Pytorch 1.11.0+cu102
—Datasets 1.15.2.dev0
—Tokenizers 0.10.1