finbert-finetuned-financial-news-sentiment-analysis-european

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

• eval_loss: 0.8996
• eval_accuracy: 0.7613
• eval_macro_precision: 0.7581
• eval_macro_recall: 0.7615
• eval_macro_f1: 0.7595
• eval_neutral_precision: 0.7898
• eval_neutral_recall: 0.7629
• eval_neutral_f1: 0.7761
• eval_positive_precision: 0.7981
• eval_positive_recall: 0.8005
• eval_positive_f1: 0.7993
• eval_negative_precision: 0.6863
• eval_negative_recall: 0.7210
• eval_negative_f1: 0.7033
• eval_runtime: 224.4354
• eval_samples_per_second: 37.026
• eval_steps_per_second: 2.317
• step: 0

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: 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
• lr_scheduler_warmup_steps: 846
• num_epochs: 7
• mixed_precision_training: Native AMP

Framework versions

• Transformers 4.35.2
• Pytorch 2.1.1+cu121
• Datasets 2.14.5
• Tokenizers 0.15.1