Jasontth's picture
Update README.md
c74a0a3
|
raw
history blame
1.63 kB
---
license: mit
base_model: roberta-base
datasets: climate_fever
tags:
- fact-checking
- climate
- text entailment
metrics:
- accuracy
- f1
model-index:
- name: results
results: []
widget:
- text: "The Great Barrier Reef is experiencing the most widespread bleaching ever recorded [SEP] A March 2016 report stated that coral bleaching was more widespread than previously thought, seriously affecting the northern parts of the reef as a result of warming ocean temperatures."
example_title: "Claim Verification"
---
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->
# results
This model is a fine-tuned version of [roberta-base](https://huggingface.co/roberta-base) on Jasontth/climate_fever_plus (https://huggingface.co/datasets/Jasontth/climate_fever_plus), enlarged CLIMATE-FEVER dataset (The dataset provided combines the Climate-Fever dataset and claim reviews from the website Climate Feedback (https://climatefeedback.org/)
It achieves the following results on the test set:
- Loss: 0.6970
- Accuracy: 0.7288
- F1: 0.7229
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 1e-05
- train_batch_size: 16
- eval_batch_size: 32
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 500
- num_epochs: 10
- mixed_precision_training: Native AMP
### Framework versions
- Transformers 4.35.2
- Pytorch 2.1.0+cu121
- Datasets 2.15.0
- Tokenizers 0.15.0