metadata
license: apache-2.0
tags:
- Finance-sentiment-analysis
- generated_from_trainer
metrics:
- f1
- accuracy
- precision
- recall
model-index:
- name: bert-base-finance-sentiment-noisy-search
results: []
bert-base-finance-sentiment-noisy-search
This model is a fine-tuned version of bert-base-uncased on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.7819
- F1: 0.8708
- Accuracy: 0.8707
- Precision: 0.8713
- Recall: 0.8707
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: 5e-05
- train_batch_size: 8
- eval_batch_size: 8
- 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 | F1 | Accuracy | Precision | Recall |
---|---|---|---|---|---|---|---|
0.476 | 1.0 | 1022 | 0.4611 | 0.8268 | 0.8283 | 0.8289 | 0.8283 |
0.3193 | 2.0 | 2044 | 0.4427 | 0.8565 | 0.8565 | 0.8565 | 0.8565 |
0.1926 | 3.0 | 3066 | 0.5921 | 0.8583 | 0.8587 | 0.8585 | 0.8587 |
0.1104 | 4.0 | 4088 | 0.6870 | 0.8677 | 0.8674 | 0.8695 | 0.8674 |
0.0544 | 5.0 | 5110 | 0.7819 | 0.8708 | 0.8707 | 0.8713 | 0.8707 |
Framework versions
- Transformers 4.16.2
- Pytorch 1.10.0+cu111
- Datasets 1.18.3
- Tokenizers 0.11.0