distilroberta-roberta-finetuned-financial-news-sentiment-analysis-european

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

• eval_loss: 0.6637
• eval_model_preparation_time: 0.0015
• eval_accuracy: 0.7764
• eval_macro_precision: 0.7737
• eval_macro_recall: 0.7865
• eval_macro_f1: 0.7762
• eval_neutral_precision: 0.8569
• eval_neutral_recall: 0.7260
• eval_neutral_f1: 0.7860
• eval_positive_precision: 0.7815
• eval_positive_recall: 0.8178
• eval_positive_f1: 0.7992
• eval_negative_precision: 0.6827
• eval_negative_recall: 0.8157
• eval_negative_f1: 0.7433
• eval_runtime: 18.4835
• eval_samples_per_second: 449.589
• eval_steps_per_second: 28.133
• 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: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
• lr_scheduler_type: linear
• lr_scheduler_warmup_steps: 846
• num_epochs: 7
• mixed_precision_training: Native AMP

Framework versions

• Transformers 4.51.3
• Pytorch 2.7.0+cu128
• Datasets 3.6.0
• Tokenizers 0.21.1