metadata
license: apache-2.0
base_model: bert-base-uncased
tags:
- generated_from_trainer
metrics:
- accuracy
- precision
- recall
- f1
model-index:
- name: bert-base
results: []
bert-base
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: 0.5726
- Accuracy: 0.6855
- Precision: 0.6780
- Recall: 0.7066
- F1: 0.6920
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: 1e-05
- train_batch_size: 32
- eval_batch_size: 32
- 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 | Precision | Recall | F1 |
|---|---|---|---|---|---|---|---|
| 0.6944 | 1.0 | 1074 | 0.6932 | 0.4921 | 0.4901 | 0.3924 | 0.4359 |
| 0.6935 | 2.0 | 2148 | 0.6914 | 0.5337 | 0.5443 | 0.4139 | 0.4702 |
| 0.5977 | 3.0 | 3222 | 0.5726 | 0.6855 | 0.6780 | 0.7066 | 0.6920 |
Framework versions
- Transformers 4.36.2
- Pytorch 2.1.0+cu121
- Datasets 2.16.1
- Tokenizers 0.15.0