metadata
license: apache-2.0
tags:
- generated_from_trainer
metrics:
- accuracy
- f1
- precision
- recall
model-index:
- name: bert-sst2-sentiment
results: []
datasets:
- stanfordnlp/sst2
language:
- en
base_model:
- google-bert/bert-base-uncased
pipeline_tag: text-classification
bert-sst2-sentiment
This model is a fine-tuned version of bert-base-uncased on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.2764
- Accuracy: 0.9197
- F1: 0.9197
- Precision: 0.9201
- Recall: 0.9197
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: 64
- eval_batch_size: 64
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 3
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 | Precision | Recall |
|---|---|---|---|---|---|---|---|
| 0.1654 | 1.0 | 1053 | 0.2157 | 0.9243 | 0.9243 | 0.9247 | 0.9243 |
| 0.099 | 2.0 | 2106 | 0.2533 | 0.9197 | 0.9197 | 0.9197 | 0.9197 |
| 0.0779 | 3.0 | 3159 | 0.2764 | 0.9197 | 0.9197 | 0.9201 | 0.9197 |
Framework versions
- Transformers 4.28.1
- Pytorch 2.2.1+cu121
- Datasets 3.1.0
- Tokenizers 0.13.3