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_alpha
    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: 0.6203703703703703
          - name: F1
            type: f1
            value: 0.620923254123051

scenario-TCR-XLMV_data-cardiffnlp_tweet_sentiment_multilingual_all_alpha

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: 1.6081
Accuracy: 0.6204
F1: 0.6209

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: 1123
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
1.0299	1.09	500	0.8919	0.5992	0.5922
0.8433	2.17	1000	0.8574	0.6150	0.6101
0.7031	3.26	1500	0.9338	0.6354	0.6292
0.5854	4.35	2000	1.1318	0.6227	0.6207
0.4556	5.43	2500	1.1376	0.6277	0.6270
0.357	6.52	3000	1.1730	0.6208	0.6195
0.2777	7.61	3500	1.3259	0.6246	0.6211
0.2198	8.7	4000	1.6081	0.6204	0.6209

Framework versions

Transformers 4.33.3
Pytorch 2.1.1+cu121
Datasets 2.14.5
Tokenizers 0.13.3