Hugging Face's logo

tringuyen-uit
/
MRC_ER_vit5-large_syl_ViWikiFC

Question Answering
Transformers
Safetensors
t5
Generated from Trainer
text-generation-inference
Inference Endpoints
Model card Files Community
MRC_ER_vit5-large_syl_ViWikiFC / README.md
tringuyen-uit's picture
tringuyen-uit
End of training
faa1537 verified
preview code
|
raw
history blame contribute delete
No virus
1.63 kB
metadata
base_model: tringuyen-uit/MRC_ER_vit5-large_syl_ViWikiFC
tags:
  - generated_from_trainer
metrics:
  - f1
model-index:
  - name: MRC_ER_vit5-large_syl_ViWikiFC
    results: []

MRC_ER_vit5-large_syl_ViWikiFC

This model is a fine-tuned version of tringuyen-uit/MRC_ER_vit5-large_syl_ViWikiFC on the None dataset. It achieves the following results on the evaluation set:

  • Loss: 3.5576
  • Exact Match: 0.8024
  • F1: 0.8241

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: 2
  • eval_batch_size: 2
  • 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 Exact Match F1
0.3388 1.0 8369 2.1133 0.7995 0.8224
0.3827 2.0 16738 2.3313 0.8029 0.8255
0.0881 3.0 25107 3.5576 0.8024 0.8241

Framework versions

  • Transformers 4.41.2
  • Pytorch 2.2.1
  • Datasets 2.19.2
  • Tokenizers 0.19.1