haryoaw's picture
Initial Commit
838b667 verified
metadata
license: mit
base_model: facebook/xlm-v-base
tags:
  - generated_from_trainer
datasets:
  - tweet_sentiment_multilingual
metrics:
  - accuracy
  - f1
model-index:
  - name: scenario-TCR-XLMV_data-cardiffnlp_tweet_sentiment_multilingual_all_delta
    results:
      - task:
          name: Text Classification
          type: text-classification
        dataset:
          name: tweet_sentiment_multilingual
          type: tweet_sentiment_multilingual
          config: all
          split: validation
          args: all
        metrics:
          - name: Accuracy
            type: accuracy
            value: 0.3333333333333333
          - name: F1
            type: f1
            value: 0.16666666666666666

scenario-TCR-XLMV_data-cardiffnlp_tweet_sentiment_multilingual_all_delta

This model is a fine-tuned version of facebook/xlm-v-base on the tweet_sentiment_multilingual dataset. It achieves the following results on the evaluation set:

  • Loss: 1.0987
  • Accuracy: 0.3333
  • F1: 0.1667

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
  • train_batch_size: 32
  • eval_batch_size: 32
  • seed: 11213
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: linear
  • num_epochs: 500

Training results

Training Loss Epoch Step Validation Loss Accuracy F1
1.0872 1.09 500 1.0884 0.3978 0.3194
1.0993 2.17 1000 1.0988 0.3333 0.1667
1.0983 3.26 1500 1.1525 0.3329 0.1713
1.0994 4.35 2000 1.0997 0.3333 0.1667
1.0998 5.43 2500 1.0991 0.3333 0.1667
1.0997 6.52 3000 1.0987 0.3333 0.1667

Framework versions

  • Transformers 4.33.3
  • Pytorch 2.1.1+cu121
  • Datasets 2.14.5
  • Tokenizers 0.13.3