Hugging Face's logo

eventdata-utd
/
ConfliBERT-Spanish-Multilingual-Cased-v2

Safetensors
bert
Generated from Trainer
Model card Files Community
ConfliBERT-Spanish-Multilingual-Cased-v2 / README.md
salsarra's picture
salsarra
Upload 9 files
98eead8 verified
preview code
|
raw
history blame
1.42 kB
metadata
tags:
  - generated_from_trainer
metrics:
  - accuracy
model-index:
  - name: ConfliBERT-multilingual-cased
    results: []

Visualize in Weights & Biases

ConfliBERT-multilingual-cased

This model is a fine-tuned version of ../models/bert-base-multilingual-cased on the None dataset. It achieves the following results on the evaluation set:

  • Loss: 0.8142
  • Accuracy: 0.8094

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: 42
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: linear
  • num_epochs: 3.0

Training results

Framework versions

  • Transformers 4.41.0.dev0
  • Pytorch 2.2.0.dev20231003+cu121
  • Datasets 2.14.5
  • Tokenizers 0.19.1