fineTuningXLMRoberta-TokenClassification-latest

This model is a fine-tuned version of cardiffnlp/twitter-xlm-roberta-base-sentiment on the None dataset. It achieves the following results on the evaluation set:

  • Loss: 0.8366
  • Precision: 0.1689
  • Recall: 0.1683
  • F1: 0.1686
  • Accuracy: 0.6766

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: 15

Training results

Training Loss Epoch Step Validation Loss Precision Recall F1 Accuracy
No log 1.0 33 0.7181 0.1472 0.1219 0.1333 0.6725
No log 2.0 66 0.7405 0.1414 0.1644 0.1521 0.6716
No log 3.0 99 0.6809 0.1694 0.1393 0.1529 0.6976
No log 4.0 132 0.7435 0.1216 0.1393 0.1298 0.6450
No log 5.0 165 0.7392 0.1709 0.1431 0.1558 0.6904
No log 6.0 198 0.7356 0.1768 0.1741 0.1754 0.6880
No log 7.0 231 0.7665 0.1699 0.1683 0.1691 0.6841
No log 8.0 264 0.7958 0.1540 0.1683 0.1608 0.6537
No log 9.0 297 0.8161 0.1607 0.1567 0.1587 0.6742
No log 10.0 330 0.8132 0.1776 0.1721 0.1749 0.6778
No log 11.0 363 0.8387 0.1617 0.1663 0.1640 0.6672
No log 12.0 396 0.8290 0.1770 0.1760 0.1765 0.6795
No log 13.0 429 0.8456 0.1770 0.1760 0.1765 0.6750
No log 14.0 462 0.8377 0.1692 0.1702 0.1697 0.6762
No log 15.0 495 0.8366 0.1689 0.1683 0.1686 0.6766

Framework versions

  • Transformers 4.44.0
  • Pytorch 2.4.0
  • Datasets 2.21.0
  • Tokenizers 0.19.1
Downloads last month
7
Safetensors
Model size
277M params
Tensor type
F32
·
Inference API
Unable to determine this model's library. Check the docs .

Model tree for Hina541/fineTuningXLMRoberta-TokenClassification-latest

Finetuned
(30)
this model