metadata
license: apache-2.0
base_model: cm309/distilbert-base-uncased-finetuned-Financial-News-Superior
tags:
- generated_from_trainer
metrics:
- accuracy
- precision
- recall
- f1
model-index:
- name: classification_bert_da_superior
results: []
classification_bert_da_superior
This model is a fine-tuned version of cm309/distilbert-base-uncased-finetuned-Financial-News-Superior on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.3962
- Accuracy: 0.8576
- Precision: 0.8576
- Recall: 0.8576
- F1: 0.8568
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
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 5
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | Precision | Recall | F1 |
|---|---|---|---|---|---|---|---|
| 0.5961 | 1.0 | 597 | 0.4288 | 0.8300 | 0.8336 | 0.8300 | 0.8312 |
| 0.3723 | 2.0 | 1194 | 0.3962 | 0.8576 | 0.8576 | 0.8576 | 0.8568 |
| 0.2497 | 3.0 | 1791 | 0.4695 | 0.8677 | 0.8668 | 0.8677 | 0.8665 |
| 0.1816 | 4.0 | 2388 | 0.5746 | 0.8677 | 0.8677 | 0.8677 | 0.8676 |
| 0.1281 | 5.0 | 2985 | 0.6205 | 0.8618 | 0.8610 | 0.8618 | 0.8612 |
Framework versions
- Transformers 4.41.0
- Pytorch 2.3.0+cu121
- Datasets 2.19.1
- Tokenizers 0.19.1