CoolFace
Modelpublic

lucaordronneau/twitter-roberta-base-sentiment-latest-finetuned-FG-CONCAT_SENTENCE-H-NEWS

sourceHugging Faceupdated 4y agoView on Hugging Face
0likes53downloads
Model Card

<!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. -->

twitter-roberta-base-sentiment-latest-finetuned-FG-CONCAT_SENTENCE-H-NEWS

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

  • —Loss: 3.6335
  • —Accuracy: 0.5275
  • —F1: 0.5198

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: 6e-05
  • —trainbatchsize: 12
  • —evalbatchsize: 12
  • —seed: 42
  • —optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • —lrschedulertype: linear
  • —num_epochs: 20

Training results

Training LossEpochStepValidation LossAccuracyF1
No log1.0611.05680.43960.2684
No log2.01221.05180.43960.2684
No log3.01831.05840.43960.2684
No log4.02441.17200.39560.3223
No log5.03051.24730.52750.5196
No log6.03661.07890.52200.5301
No log7.04271.35560.56040.5426
No log8.04881.73140.53300.5158
0.80459.05492.27740.53300.5161
0.804510.06102.83620.44510.4512
0.804511.06712.91300.52750.4931
0.804512.07323.10230.51100.5010
0.804513.07933.26700.53850.5208
0.804514.08543.41510.49450.4856
0.804515.09153.76140.46150.4458
0.804516.09763.52240.52200.5122
0.053517.010373.51960.51650.5102
0.053518.010983.57910.51100.5039
0.053519.011593.62200.52200.5137
0.053520.012203.63350.52750.5198

Framework versions

  • —Transformers 4.16.2
  • —Pytorch 1.9.1
  • —Datasets 1.18.4
  • —Tokenizers 0.11.6