metadata

license: mit
tags:
  - generated_from_trainer
datasets:
  - xtreme_en_token_drift
metrics:
  - accuracy
  - f1
widget:
  - text: My name is Julia, I study at Imperial College, in London
    example_title: Example 1
  - text: My name is Sarah and I live in Paris
    example_title: Example 2
  - text: My name is Clara and I live in Berkeley, California
    example_title: Example 3
model-index:
  - name: XLM-RoBERTa-xtreme-en-token-drift
    results:
      - task:
          name: Token Classification
          type: token-classification
        dataset:
          name: xtreme_en_token_drift
          type: xtreme_en_token_drift
          args: default
        metrics:
          - name: Accuracy
            type: accuracy
            value: 0.908855961405927
          - name: F1
            type: f1
            value: 0.76126567683807

XLM-RoBERTa-xtreme-en-token-drift

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

Loss: 0.2802
Accuracy: 0.9089
F1: 0.7613

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
train_batch_size: 32
eval_batch_size: 32
seed: 42
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: linear
num_epochs: 3

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy	F1
0.6398	1.0	161	0.3421	0.8973	0.7111
0.3268	2.0	322	0.2846	0.9097	0.7611
0.2701	3.0	483	0.2802	0.9089	0.7613

Framework versions

Transformers 4.20.1
Pytorch 1.11.0+cu113
Datasets 2.3.2
Tokenizers 0.12.1