climate_text_classification_mini_model

This model is a fine-tuned version of distilbert-base-uncased on the climate-tagging-labelled-datasets dataset. It achieves the following results on the evaluation set:

• Loss: 0.7516
• Precision: 0.7941
• Recall: 0.9643
• Accuracy: 0.8
• F1: {'f1': 0.8709677419354839}

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: 0.0002
• train_batch_size: 16
• eval_batch_size: 16
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 2

Training results

Training Loss	Epoch	Step	Validation Loss	Precision	Recall	Accuracy	F1
No log	1.0	10	0.5469	0.875	0.75	0.75	{'f1': 0.8076923076923077}
No log	2.0	20	0.7516	0.7941	0.9643	0.8	{'f1': 0.8709677419354839}

Framework versions

• Transformers 4.26.1
• Pytorch 1.7.0a0
• Datasets 2.9.0
• Tokenizers 0.13.2