Update README.md

README.md

@@ -1,71 +1,73 @@
----
-license: mit
-tags:
-- generated_from_trainer
-metrics:
-- accuracy
-- precision
-- recall
-- f1
-model-index:
-- name: Climate-TwitterBERT-step1
-  results: []
----
+# Model Card Climate-TwitterBERT-step-1 
 
-<!-- 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. -->
+## Overview:
 
-# Climate-TwitterBERT-step1
+Using Covid-Twitter-BERT-v2 (https://huggingface.co/digitalepidemiologylab/covid-twitter-bert-v2) as the starting model, we continued domain-adaptive pre-training on a corpus of firm tweets between 2007 and 2020. The model was then fine-tuned on the downstream task to classify whether a given tweet is related to climate change topics.
+
+The model provides a label and probability score, indicating whether a given tweet is related to climate change topics (label = 1) or not (label = 0).
+
+## Performance metrics:
+
+Based on the test set, the model achieves the following results:
+
+•	Loss: 0.0632
+•	F1-weighted: 0.9778      
+•	F1: 0.9148
+•	Accuracy: 0.9775
+•	Precision: 0. 8841
+•	Recall: 0. 9477
+
+## Example usage:
+
+```python
+from transformers import pipeline, AutoTokenizer, AutoModelForSequenceClassification
+
+task_name = 'binary'
+model_name = Climate-TwitterBERT/ Climate-TwitterBERT-step1'
+
+tokenizer = AutoTokenizer.from_pretrained(model_name)
+model = AutoModelForSequenceClassification.from_pretrained(model_name)
+
+pipe = pipeline(task=‘binary‘, model=model, tokenizer=tokenizer)
+
+tweet = "We are committed to significantly cutting our carbon emissions by 30% before 2030."
+result = pipe(tweet)
+# The 'result' variable will contain the classification output: 0 = non-climate tweet, 1= climate tweet
+```
+
+## Citation: 
+
+```bibtex
+@article{fzz2023climatetwitter,
+  title={Responding to Climate Change crisis - firms' tradeoffs},
+  author={Fritsch, Felix and Zhang, Qi and Zheng, Xiang},
+  journal={Working paper},
+  year={2023},
+  institution={University of Mannheim, the Chinese University of Hong Kong, and NHH Norwegian School of Economics},
+url={https://ssrn.com/XXXXXXX}
+}
+```
+
+Fritsch, F., Zhang, Q., & Zheng, X. (2023). Responding to Climate Change crisis - firms' tradeoffs [Working paper]. University of Mannheim, the Chinese University of Hong Kong, and NHH Norwegian School of Economics.
+
+
+## Framework versions
+•	Transformers 4.28.1
+•	Pytorch 2.0.1+cu118
+•	Datasets 2.14.1
+•	Tokenizers 0.13.3
 
-This model is a fine-tuned version of [Climate-TwitterBERT/ctbert_corporate_mlm](https://huggingface.co/Climate-TwitterBERT/ctbert_corporate_mlm) on an unknown dataset.
-It achieves the following results on the evaluation set:
-- Loss: 0.0693
-- Accuracy: 0.9767
-- Precision: 0.8882
-- Recall: 0.9346
-- F1-weighted: 0.9769
-- F1: 0.9108
 
-## 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: 1e-05
-- train_batch_size: 128
-- eval_batch_size: 2
-- seed: 42
-- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
-- lr_scheduler_type: linear
-- lr_scheduler_warmup_ratio: 0.05
-- num_epochs: 4
 
-### Training results
 
-| Training Loss | Epoch | Step | Validation Loss | Accuracy | Precision | Recall | F1-weighted | F1     |
-|:-------------:|:-----:|:----:|:---------------:|:--------:|:---------:|:------:|:-----------:|:------:|
-| 0.2835        | 0.76  | 50   | 0.0636          | 0.9767   | 0.9252    | 0.8889 | 0.9765      | 0.9067 |
-| 0.0821        | 1.52  | 100  | 0.0632          | 0.9775   | 0.8841    | 0.9477 | 0.9778      | 0.9148 |
-| 0.0763        | 2.27  | 150  | 0.0627          | 0.9767   | 0.8882    | 0.9346 | 0.9769      | 0.9108 |
-| 0.0561        | 3.03  | 200  | 0.0670          | 0.9742   | 0.8720    | 0.9346 | 0.9745      | 0.9022 |
-| 0.0429        | 3.79  | 250  | 0.0693          | 0.9767   | 0.8882    | 0.9346 | 0.9769      | 0.9108 |
 
 
-### Framework versions
 
-- Transformers 4.28.1
-- Pytorch 2.0.1+cu118
-- Datasets 2.14.1
-- Tokenizers 0.13.3