metadata
license: apache-2.0
tags:
- generated_from_trainer
metrics:
- accuracy
- f1
model-index:
- name: benchmark-finetuned-bert
results: []
benchmark-finetuned-bert
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: 0.4553
- Accuracy: 0.8267
- F1: 0.8270
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 |
|---|---|---|---|---|---|
| 0.803 | 1.0 | 48 | 0.6463 | 0.6997 | 0.6460 |
| 0.5508 | 2.0 | 96 | 0.5141 | 0.8042 | 0.8051 |
| 0.4111 | 3.0 | 144 | 0.4553 | 0.8267 | 0.8270 |
Framework versions
- Transformers 4.20.1
- Pytorch 1.11.0
- Datasets 2.1.0
- Tokenizers 0.12.1