Hugging Face's logo

Flamgrise
/
ENG-full-fined-tuned

Text Classification
Transformers
TensorBoard
Safetensors
bart
Generated from Trainer
Inference Endpoints
Model card Files Metrics Community
ENG-full-fined-tuned / README.md
Flamgrise's picture
Flamgrise
Fine-tuned BART model for League of Legends biographies classification
fafb787 verified
preview code
|
raw
history blame contribute delete
2.02 kB
metadata
license: mit
base_model: facebook/bart-large-mnli
tags:
  - generated_from_trainer
metrics:
  - f1
model-index:
  - name: ENG-full-fined-tuned
    results: []

ENG-full-fined-tuned

This model is a fine-tuned version of facebook/bart-large-mnli on an unknown dataset. It achieves the following results on the evaluation set:

  • Loss: 2.8437
  • F1: 0.3541

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: 3
  • eval_batch_size: 3
  • seed: 42
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: linear
  • num_epochs: 12

Training results

Training Loss Epoch Step Validation Loss F1
No log 1.0 88 1.7166 0.0753
No log 2.0 176 1.7786 0.0482
No log 3.0 264 1.7416 0.0575
No log 4.0 352 1.6967 0.1203
No log 5.0 440 1.6729 0.1636
1.7288 6.0 528 1.6480 0.2956
1.7288 7.0 616 1.7791 0.3345
1.7288 8.0 704 2.1510 0.3117
1.7288 9.0 792 2.2252 0.3376
1.7288 10.0 880 2.5299 0.3613
1.7288 11.0 968 2.7822 0.3640
0.2608 12.0 1056 2.8437 0.3541

Framework versions

  • Transformers 4.38.2
  • Pytorch 2.2.1+cu121
  • Datasets 2.18.0
  • Tokenizers 0.15.2