Modelpublic

HerbertAIHug/Finetuned-Roberta-Base-Sentiment-identifier

sourceHugging Facemitupdated 3y agoView on Hugging Face

0likes7downloads

Model Card

Finetuned-Roberta-Base-Sentiment-identifier

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

—Loss: 0.7332
—F1: 0.6622

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: 5e-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	F1
0.8545	0.5	500	0.8251	0.6428
0.7952	1.0	1000	0.7831	0.6445
0.7962	1.5	1500	0.7935	0.6495
0.7669	2.01	2000	0.7544	0.6520
0.7468	2.51	2500	0.7614	0.6724
0.76	3.01	3000	0.7332	0.6622
0.7352	3.51	3500	0.8651	0.6036
0.7454	4.01	4000	0.7420	0.6584
0.7302	4.51	4500	0.7652	0.6573
0.7099	5.02	5000	0.7372	0.6697
0.73	5.52	5500	0.7806	0.6654
0.7265	6.02	6000	0.7476	0.6656
0.7092	6.52	6500	0.7632	0.6535
0.7322	7.02	7000	0.8017	0.6126
0.7168	7.52	7500	0.8046	0.6711
0.7279	8.02	8000	0.7734	0.6652
0.6884	8.53	8500	0.7806	0.6662
0.6942	9.03	9000	0.7790	0.6670
0.6865	9.53	9500	0.7835	0.6650

Framework versions

—Transformers 4.33.1
—Pytorch 2.0.1+cu118
—Datasets 2.14.5
—Tokenizers 0.13.3