bart_qa_model / README.md
smrynrz20's picture
End of training
6b5e34b verified
|
raw
history blame
1.62 kB
metadata
license: apache-2.0
base_model: facebook/bart-base
tags:
  - generated_from_trainer
metrics:
  - f1
model-index:
  - name: bart_qa_model
    results: []

bart_qa_model

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

  • Loss: 1.1988
  • F1: 0.7649
  • Exact Match: 0.634

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: 3.7185140364032e-05
  • train_batch_size: 16
  • eval_batch_size: 16
  • seed: 42
  • gradient_accumulation_steps: 2
  • total_train_batch_size: 32
  • 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 F1 Exact Match
0.8014 1.0 125 1.3209 0.7185 0.579
0.9114 2.0 250 1.1532 0.7515 0.623
0.6644 3.0 375 1.1988 0.7649 0.634

Framework versions

  • Transformers 4.41.2
  • Pytorch 2.3.0+cu121
  • Datasets 2.20.0
  • Tokenizers 0.19.1